In this episode, we talk about how engineers are tackling the problem of sorting through piles using robotics and a platform that leverages fake data to train robots more efficiently.<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/ee270fa2-ec1d-485d-86fe-fffdf942a9f3?dark=false" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe><hr>This podcast is sponsored by&nbsp;<a href="https://www2.mouser.com/" id="isPasted" rel="nofollow" target="_blank">Mouser Electronics</a>. &nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjU4MjI3OTM1NzAxLU1vdXNlci1zcG9uc29yLTEtYS5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib"><hr><h3 id="isPasted">EPISODE NOTES</h3>(0:57) - Robots Finding Buried Objects🤖🔑(16:50) - Fake Data To Train Robots🤖🧠<hr>About the podcast:Every day, some of the most innovative universities, companies, and individual technology developers share their knowledge on Wevolver. To ensure we can also provide this knowledge for the growing group of podcast listeners, we started a collaboration with two young engineers, Daniel Scott Mitchell &amp; Farbod Moghaddam who discuss the most interesting content in this podcast series.&nbsp;To learn more about this show, please visit the <a href="https://www.wevolver.com/profile/the.next.byte" target="_blank">shows page</a>. By following the page, you will get automatic updates by email when a new show is published.Be sure to give us a follow and review on <a href="https://podcasts.apple.com/nl/podcast/the-next-byte/id1548255861?l=en" rel="nofollow" target="_blank">Apple</a> podcasts, <a href="https://open.spotify.com/show/6lPPsRtegnivsRUEsQ09R7?si=IPMiah7xT_apJtPjqvXMlA" rel="nofollow" target="_blank">Spotify</a>, and most of your favorite podcast platforms!Take a few seconds to leave us a review. It really helps! <a href="https://apple.co/2RIsbZ2" rel="nofollow" target="_blank">https://apple.co/2RIsbZ2&nbsp;</a>if you do it and send us proof, we’ll give you a shoutout on the show.

Peter Mitrano demonstrates a rope manipulation experiment. Software that he and Berenson developed can expand training data sets for challenges like rope manipulation, doubling the success rate of the robot. Credit: Daryl Marshke, Michigan Creative, University of Michigan. 

In this episode, we talk about how engineers are tackling the problem of sorting through piles using robotics and a platform that leverages fake data to train robots more efficiently.

Podcast: Teaching Robots To Find Buried Objects

As every athletic or fashion-conscious person knows, our body image is not always accurate or realistic, but it&rsquo;s an important piece of information that determines how we function in the world. When you get dressed or play ball, your brain is constantly planning ahead so that you can move your body without bumping, tripping, or falling over.We humans acquire our body-model as infants, and robots are following suit. A&nbsp;<a href="https://www.engineering.columbia.edu/" target="_blank">Columbia Engineering</a> team announced today they have created a robot that&mdash;for the first time&mdash;is able to learn a model of its entire body from scratch, without any human assistance. In a&nbsp;<a href="https://www.science.org/doi/10.1126/scirobotics.abn1944" target="_blank">new study published by&nbsp;Science Robotics</a>, the researchers demonstrate how their robot created a kinematic model of itself, and then used its self-model to plan motion, reach goals, and avoid obstacles in a variety of situations. It even automatically recognized and then compensated for damage to its body.<h2>Robot watches itself like an an infant exploring itself in a hall of mirrors</h2>The researchers placed a robotic arm inside a circle of five streaming video cameras. The robot watched itself through the cameras as it undulated freely. Like an infant exploring itself for the first time in a hall of mirrors, the robot wiggled and contorted to learn how exactly its body moved in response to various motor commands. After about three hours, the robot stopped. Its internal deep neural network had finished learning the relationship between the robot&rsquo;s motor actions and the volume it occupied in its environment.&ldquo;We were really curious to see how the robot imagined itself,&rdquo; said&nbsp;<a href="https://engineering.columbia.edu/faculty/hod-lipson" target="_blank">Hod Lipson</a>, professor of&nbsp;<a href="https://www.me.columbia.edu/" target="_blank">mechanical engineering</a> and director of Columbia&rsquo;s&nbsp;<a href="https://www.creativemachineslab.com/" target="_blank">Creative Machines Lab</a>, where the work was done. &ldquo;But you can&rsquo;t just peek into a neural network; it&rsquo;s a black box.&rdquo; After the researchers struggled with various visualization techniques, the self-image gradually emerged. &ldquo;It was a sort of gently flickering cloud that appeared to engulf the robot&rsquo;s three-dimensional body,&rdquo; said Lipson. &ldquo;As the robot moved, the flickering cloud gently followed it.&rdquo; The robot&rsquo;s self-model was accurate to about 1% of its workspace.<h2>Self-modeling robots will lead to more self-reliant autonomous systems</h2>The ability of robots to model themselves without being assisted by engineers is important for many reasons: Not only does it save labor, but it also allows the robot to keep up with its own wear-and-tear, and even detect and compensate for damage. The authors argue that this ability is important, as we need autonomous systems to be more self-reliant. A factory robot, for instance, could detect that something isn&rsquo;t moving right, and compensate or call for assistance.&ldquo;We humans clearly have a notion of self,&rdquo; explained the study&rsquo;s first author <a href="http://boyuanchen.com/" target="_blank">Boyuan Chen</a>, who led the work and is now an assistant professor at Duke University. &ldquo;Close your eyes and try to imagine how your own body would move if you were to take some action, such as stretch your arms forward or take a step backward. Somewhere inside our brain we have a notion of self, a self-model that informs us what volume of our immediate surroundings we occupy, and how that volume changes as we move.&rdquo;<iframe src="https://www.youtube.com/embed/3jbBEMfZTSg?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" style="width: 766px; height: 434px;"></iframe>A robot arm learns to reach a target sphere while avoiding the cuboid obstacle using the learned visual self-model. Credit: Boyuan Chen, Jane Nisselson/Columbia Engineering&nbsp;<h2 id="isPasted">Self-awareness in robots</h2>The work is part of Lipson&rsquo;s decades-long quest to find ways to grant robots some form of self-awareness. &ldquo;Self-modeling is a primitive form of self-awareness,&rdquo; he explained. &ldquo;If a robot, animal, or human has an accurate self-model, it can function better in the world, it can make better decisions, and it has an evolutionary advantage.&rdquo;The researchers are aware of the limits, risks, and controversies surrounding granting machines greater autonomy through self-awareness. Lipson is quick to admit that the kind of self-awareness demonstrated in this study is, as he noted, &ldquo;trivial compared to that of humans, but you have to start somewhere. We have to go slowly and carefully, so we can reap the benefits while minimizing the risks.&rdquo;

Columbia Engineers build a robot that learns to understand itself, rather than the world around it

A Robot Learns to Imagine Itself

This article was first published on <a href="https://www.csail.mit.edu/news/flexible-way-grab-items-feeling" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>. &nbsp;<hr>The notion of a large metallic robot that speaks in monotone and moves in lumbering, deliberate steps is somewhat hard to shake. But practitioners in the field of soft robotics have an entirely different image in mind &mdash; autonomous devices composed of compliant parts that are gentle to the touch, more closely resembling human fingers than R2-D2 or Robby the Robot.That model is now being pursued by Professor Edward Adelson and his Perceptual Science Group at MIT&rsquo;s Computer Science and Artificial Intelligence Laboratory (CSAIL). In a&nbsp;<a href="https://arxiv.org/abs/2204.07146" target="_blank">recent project</a>, Adelson and Sandra Liu &mdash; a mechanical engineering PhD student at CSAIL &mdash; have developed a robotic gripper using novel &ldquo;GelSight Fin Ray&rdquo; fingers that, like the human hand, is supple enough to manipulate objects. What sets this work apart from other efforts in the field is that Liu and Adelson have endowed their gripper with touch sensors that can meet or exceed the sensitivity of human skin.Their <a href="https://arxiv.org/abs/2204.07146" target="_blank">work was presented</a> last week at the 2022 IEEE 5th International Conference on Soft Robotics.<iframe src="https://www.youtube.com/embed/rvezSGdFPx0?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" style="width: 764px; height: 428px;"></iframe>The fin ray has become a popular item in soft robotics owing to a discovery made in 1997 by the German biologist Leif Kniese. He noticed that when he pushed against a fish&rsquo;s tail with his finger, the ray would bend toward the applied force, almost embracing his finger, rather than tilting away. The design has become popular, but it lacks tactile sensitivity. &ldquo;It&rsquo;s versatile because it can passively adapt to different shapes and therefore grasp a variety of objects,&rdquo; Liu explains. &ldquo;But in order to go beyond what others in the field had already done, we set out to incorporate a rich tactile sensor into our gripper.&rdquo;The gripper consists of two flexible fin ray fingers that conform to the shape of the object they come in contact with. The fingers themselves are assembled from flexible plastic materials made on a 3D printer, which is pretty standard in the field. However, the fingers typically used in soft robotic grippers have supportive cross-struts running through the length of their interiors, whereas Liu and Adelson hollowed out the interior region so they could create room for their camera and other sensory components.The camera is mounted to a semirigid backing on one end of the hollowed-out cavity, which is, itself, illuminated by LEDs. The camera faces a layer of &ldquo;sensory&rdquo; pads composed of silicone gel (known as &ldquo;GelSight&rdquo;) that is glued to a thin layer of acrylic material. The acrylic sheet, in turn, is attached to the plastic finger piece at the opposite end of the inner cavity. Upon touching an object, the finger will seamlessly fold around it, melding to the object&rsquo;s contours. By determining exactly how the silicone and acrylic sheets are deformed during this interaction, the camera &mdash; along with accompanying computational algorithms &mdash; can assess the general shape of the object, its surface roughness, its orientation in space, and the force being applied by (and imparted to) each finger.Liu and Adelson tested out their gripper in an experiment during which just one of the two fingers was &ldquo;sensorized.&rdquo; Their device successfully handled such items as a mini-screwdriver, a plastic strawberry, an acrylic paint tube, a Ball Mason jar, and a wine glass. While the gripper was holding the fake strawberry, for instance, the internal sensor was able to detect the &ldquo;seeds&rdquo; on its surface. The fingers grabbed the paint tube without squeezing so hard as to breach the container and spill its contents.The GelSight sensor could even make out the lettering on the Mason jar, and did so in a rather clever way. The overall shape of the jar was ascertained first by seeing how the acrylic sheet was bent when wrapped around it. That pattern was then subtracted, by a computer algorithm, from the deformation of the silicone pad, and what was left was the more subtle deformation due just to the letters.Glass objects are challenging for vision-based robots because of the refraction of the light. Tactile sensors are immune to such optical ambiguity. When the gripper picked up the wine glass, it could feel the orientation of the stem and could make sure the glass was pointing straight up before it was slowly lowered. When the base touched the tabletop, the gel pad sensed the contact. Proper placement occurred in seven out of 10 trials and, thankfully, no glass was harmed during the filming of this experiment.Wenzhen Yuan, an assistant professor in the Robotics Institute at Carnegie Mellon University who was not invovled with the research, says, &ldquo;Sensing with soft robots has been a big challenge, because it is difficult to set up sensors &mdash; which are traditionally rigid &mdash; on soft bodies,&rdquo; Yuan says. &ldquo;This paper provides a neat solution to that problem. The authors used a very smart design to make their vision-based sensor work for the compliant gripper, in this way generating very good results when robots grasp objects or interact with the external environment. The technology has lots of potential to be widely used for robotic grippers in real-world environments.&rdquo;Liu and Adelson can foresee many possible applications for the GelSight Fin Ray, but they are first contemplating some improvements. By hollowing out the finger to clear space for their sensory system, they introduced a structural instability, a tendency to twist, that they believe can be counteracted through better design. They want to make GelSight sensors that are compatible with soft robots devised by other research teams. And they also plan to develop a three-fingered gripper that could be useful in such tasks as picking up pieces of fruit and evaluating their ripeness.Tactile sensing, in their approach, is based on inexpensive components: a camera, some gel, and some LEDs. Liu hopes that with a technology like GelSight, &ldquo;it may be possible to come up with sensors that are both practical and affordable.&rdquo; That, at least, is one goal that she and others in the lab are striving toward.<hr>&quot;Reprinted with permission of&nbsp;<a href="https://www.csail.mit.edu/news/flexible-way-grab-items-feeling" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>&quot;&nbsp;

In a recent project, Professor Edward Adelson and Sandra Liu — a mechanical engineering PhD student at CSAIL — have developed a robotic gripper using novel “GelSight Fin Ray” fingers that, like the human hand, is supple enough to manipulate objects.

A flexible way to grab items with feeling

In this episode, we talk about how ostriches are inspiring a new generation of bipedal robots and the innovation enabling remote endovascular surgery. As always, you can find these and other interesting &amp; impactful engineering articles on Wevolver.com.<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/e2238814-9212-4010-afb6-ac48d637140f?dark=false" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true"></iframe><hr>This podcast is sponsored by <a href="https://www2.mouser.com/" id="isPasted" rel="nofollow" target="_blank">Mouser Electronics</a>.&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1651565842197-Mouser-sponsor-1-a.jpg" style="width: 766px;" class="fr-fic fr-dib"><hr>(0:50) -&nbsp;<a href="https://www.wevolver.com/article/birdbot-a-3d-printed-bipedal-robot-offers-major-efficiency-gains-through-avian-biomimicry" target="_blank">Using Bird Biology To Make Efficient Walking Robots</a>(20:45) -&nbsp;<a href="https://www.wevolver.com/article/joystick-operated-robot-could-help-surgeons-treat-stroke-remotely" target="_blank">Joystick-operated Robot For Treating Strokes</a>Episode 68 was brought to you by Mouser Electronics, Farbod &amp; Daniel&rsquo;s favorite electronics distributor. Click <a href="https://www.mouser.com/applications/future-robotics-singularity/" target="_blank">here</a> to read the article discussing the merger of technology and humanity.<hr>About the podcast:Every day, some of the most innovative universities, companies, and individual technology developers share their knowledge on Wevolver. To ensure we can also provide this knowledge for the growing group of podcast listeners, we started a collaboration with two young engineers, Daniel Scott Mitchell &amp; Farbod Moghaddam who discuss the most interesting content in this podcast series.&nbsp;To learn more about this show, please visit the <a href="https://www.wevolver.com/profile/the.next.byte" target="_blank">shows page</a>. By following the page, you will get automatic updates by email when a new show is published.Be sure to give us a follow and review on <a href="https://podcasts.apple.com/nl/podcast/the-next-byte/id1548255861?l=en" rel="nofollow" target="_blank">Apple</a> podcasts, <a href="https://open.spotify.com/show/6lPPsRtegnivsRUEsQ09R7?si=IPMiah7xT_apJtPjqvXMlA" rel="nofollow" target="_blank">Spotify</a>, and most of your favorite podcast platforms!Take a few seconds to leave us a review. It really helps! <a href="https://apple.co/2RIsbZ2" rel="nofollow" target="_blank">https://apple.co/2RIsbZ2&nbsp;</a>if you do it and send us proof, we&rsquo;ll give you a shoutout on the show.

The prototype motorized BirdBot, seen here with legs in the locked position, uses a quarter the energy of its immediate predecessor.

In this episode, we talk about how ostriches are inspiring a new generation of bipedal robots and the innovation enabling remote endovascular surgery. 

Podcast: Bird-inspired Bipedal Robots & Robotic Surgeons

<h3 id="isPasted"><style type="text/css" id="isPasted"></style><style type="text/css"></style><span data-sheets-formula="=PROPER(R[-1]C[0])" data-sheets-userformat='{"2":320,"9":2,"11":3}' data-sheets-value='{"1":2,"2":"What Is The Definition Of A ‘Degree Of Freedom’ (In The Context Of Robotic Arms)?"}'>What is the Definition of a &lsquo;Degree of Freedom&rsquo; (In the context of Robotic Arms)?</h3>A &lsquo;Degree of Freedom&rsquo; (DoF) as it relates to robotic arms, is an independent joint that can provide freedom of movement of the manipulator, either in a rotational or translational (linear) sense. For every geometric axis that a joint can rotate around or extend along, this is counted as a Single Degree of Freedom.&nbsp;In theory, there are quite a few types of joints that provide varying numbers of degrees of freedom in terms of rotation and translation (see the chart below). In practice, however, most robotic arms will be made up of a series of joints that provide one degree of freedom. The two most common joints are:Revolute Joint: Providing one degree of rotational freedomPrismatic Joint:&nbsp;Providing one degree of linear freedomAs such, robotic arms are often described in terms of how many total DoF they have. E.g. <a href="https://blueprintlab.com/products/manipulators/reach-bravo/" target="_blank">the Bravo 7</a> is a 6 Degree of Freedom robotic arm (Why not call it the Bravo 6? See the next section of this article). Of course, there are a <a href="https://www.nist.gov/blogs/manufacturing-innovation-blog/4-types-robots-every-manufacturer-should-know" rel="noreferrer noopener" target="_blank">variety of different types of robotic arms</a> across different industries, ranging from one degree of freedom (sometimes called an &lsquo;axis&rsquo;) to over seven.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1649929821040-kinematic-pairs.png" style="width: 766px;" class="fr-fic fr-dib">Chart Credit: Cavacece, Massimo &amp; Vita, L.. (2005). On the Computation of degrees-of-freedom: A Didactic Perspective. 10.1115/DETC2005-84109.&nbsp;Knowing and defining the Degrees of Freedom (along with other key parameters) allow for modeling the robotic system and implementation of AI algorithms to autonomously control the manipulator arm.Learn more about <a href="https://blueprintlab.com/blog/top-uses-for-underwater-manipulators/" target="_blank">Top Uses of Underwater ROV Manipulators</a>.<h3><style type="text/css" id="isPasted"></style><style type="text/css"></style><span data-sheets-formula="=PROPER(R[-1]C[0])" data-sheets-userformat='{"2":320,"9":2,"11":3}' data-sheets-value='{"1":2,"2":"What Do We Mean When We Talk About The Number Of ‘Functions’ Of A Robotic Arm?"}'>What do we mean when we talk about the Number of &lsquo;Functions&rsquo; of a Robotic Arm? </h3>Sometimes a &lsquo;Degree of freedom&rsquo; is coopted to be used for a function that does not result in &lsquo;freedom&rsquo;. In other words, it does not move the position or orientation of the end-effector/gripper/tool/sensor (the part of the robot that &lsquo;does stuff&rsquo;). For <a href="https://blueprintlab.com/products/manipulators/" target="_blank">Blueprint Lab manipulators</a>, we usually have a set of jaws at the end of the robotic arm. To open or close the jaws of the robotic arm, we use a prismatic actuator (a fancy word for a motor and gear set &ndash; a single joint).&nbsp;We define the reference point as a floating location in between the jaws of the manipulator. As the manipulator moves, it is this location that is being updated in terms of the &lsquo;position&rsquo; of the end-effector. If you want to grab something at position (x,y,z) with orientation (a,b,c), it is this position that is optimised in the<a href="https://robotacademy.net.au/masterclass/inverse-kinematics-and-robot-motion/" rel="noreferrer noopener" target="_blank">&nbsp;inverse kinematics algorithm</a>.Because of this, the movement of the linear actuator to open and close the manipulator&rsquo;s gripper does not change the reference point and thus it is not providing a &lsquo;degree-of-freedom.&nbsp;In this scenario, the prismatic actuator is providing a &lsquo;function&rsquo; but not a &lsquo;degree of freedom&rsquo;. As such, we may define a manipulator as having a different number of DoF and Functions; for example, the Bravo 7 is a 7-Function, 6 DoF manipulator, with one function being the open/close of the jaws.&nbsp;Why is all this important? One of the main things people are interested in when solving a complex robotic manipulator problem is the DoF and Functions. These two distinct pieces of terminology help to shortcut conversations and make sure everyone is talking on the same page!<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1649929989018-Article-Imagery-Infographic-01-2-2048x1152.jpg" style="width: 766px;" class="fr-fic fr-dib">

One of the main things people are interested in when solving a complex robotic manipulator problem is the DoF and Functions. These two distinct pieces of terminology help to shortcut conversations and make sure everyone is talking on the same page!

'Degrees of Freedom' vs 'Functions' of a Robotic Arm

This article was discussed in our <a data-saferedirecturl="https://www.google.com/url?q=https://www.wevolver.com/profile/the.next.byte&source=gmail&ust=1651619086659000&usg=AOvVaw31M1Y-wsRw4c0h8-at-VxZ" href="https://www.wevolver.com/profile/the.next.byte" id="isPasted" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/e2238814-9212-4010-afb6-ac48d637140f?dark=false" class="fr-draggable" data-gtm-yt-inspected-1_19="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true"></iframe>The full article will continue below.<hr>This article was first published on <a href="https://news.mit.edu/2022/robot-stroke-treatment-remote-0413" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>. &nbsp;<hr>MIT engineers have developed a telerobotic system to help surgeons quickly and remotely treat patients experiencing a stroke or aneurysm. With a modified joystick, surgeons in one hospital may control a robotic arm at another location to safely operate on a patient during a critical window of time that could save the patient&rsquo;s life and preserve their brain function.The robotic system, whose movement is controlled through magnets, is designed to remotely assist in endovascular intervention &mdash; a procedure performed in emergency situations to treat strokes caused by a blood clot. Such interventions normally require a surgeon to manually guide a thin wire to the clot, where it can physically clear the blockage or deliver drugs to break it up.One limitation of such procedures is accessibility: Neurovascular surgeons are often based at major medical institutions that are difficult to reach for patients in remote areas, particularly during the &ldquo;golden hour&rdquo; &mdash; the critical period after a stroke&rsquo;s onset, during which treatment should be administered to minimize any damage to the brain.The MIT team envisions that its robotic system could be installed at smaller hospitals and remotely guided by trained surgeons at larger medical centers. The system includes a medical-grade robotic arm with a magnet attached to its wrist. With a joystick and live imaging, an operator can adjust the magnet&rsquo;s orientation and manipulate the arm to guide a soft and thin magnetic wire through arteries and vessels.The researchers demonstrated the system in a &ldquo;phantom,&rdquo; a transparent model with vessels replicating complex arteries of the brain. With just an hour of training, neurosurgeons were able to remotely control the robot&rsquo;s arm to guide a wire through a maze of vessels to reach target locations in the model.&ldquo;We imagine, instead of transporting a patient from a rural area to a large city, they could go to a local hospital where nurses could set up this system. A neurosurgeon at a major medical center could watch live imaging of the patient and use the robot to operate in that golden hour. That&rsquo;s our future dream,&rdquo; says Xuanhe Zhao, a professor of mechanical engineering and of civil and environmental engineering at MIT.Zhao and his team have <a href="https://www.science.org/doi/10.1126/scirobotics.abg9907" target="_blank">published their findings</a> today in Science Robotics. MIT co-authors include lead author Yoonho Kim, Emily Genevriere, and Jaehun Choe, along with Pablo Harker, Robert Regenhardt, Justin Vranic, Adam Dmytriw, and Aman Patel at Massachusetts General Hospital (MGH), and Marcin Balicki of Philips Research North America.<iframe src="https://www.youtube.com/embed/IYlHl6h8lm4?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" style="width: 767px; height: 427px;" data-gtm-yt-inspected-1_19="true" id="391874016"></iframe><h2 id="isPasted">Tilt and twist</h2>Endovascular surgery is a specialized, minimally invasive procedure that involves carefully twisting and guiding a thin medical wire through the body&rsquo;s arteries and vessels to a target location, in a way that avoids damaging vessel walls. The procedure typically requires years of training for a surgeon to master.Robotic systems are being explored as assistive technologies in endovascular surgery. These systems mainly involve motor drives that advance and retract a wire while twisting it through the body&rsquo;s vasculature.&ldquo;But having a robot twist with the same level of sophistication [as a surgeon] is challenging,&rdquo; Kim notes. &ldquo;Our system is based on a fundamentally different mechanism.&rdquo;The team&rsquo;s new system builds on <a href="https://news.mit.edu/2019/robot-brain-blood-vessels-0828" target="_blank">work from 2019</a>, in which they demonstrated steering a magnetically controlled thread through a life-sized silicone model of the brain&rsquo;s blood vessels. They did so at the time using a handheld magnet, about the size of a soup can, that they manually manipulated.They have since affixed the magnet to the end of a medical-grade robotic arm, which can be steered using a small joystick knob on a mouse. By tilting the joystick, researchers can tilt the magnet in an orientation that a magnetic wire can follow. Buttons on the mouse control a set of motorized linear drives, which advance and retract the wire to make it move forward and back.The wire is as thin and flexible as a conventional neurovascular guidewire, with a soft, magnetically responsive tip that follows and bends in the direction of a magnetic field.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ5OTIzNDk1NTU1LU1JVC1Sb2JvLVN0cm9rZS0wMi1wcmVzcy5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">The MIT team envisions that its robotic system could be installed at smaller hospitals and remotely guided by trained surgeons at larger medical centers. Courtesy of the researchers<h2>Finding a path</h2>The team tested the robotic system in MGH&rsquo;s Catheter Lab &mdash; an operating room with standard medical imaging equipment used in endovascular procedures. The researchers installed the robotic arm in the lab, along with a life-sized silicone model of blood vessels. They set the joystick, along with a monitor displaying a live video of the model, in a control room. From there, an operator watched the video while using the joystick to remotely steer the wire through the vessels.The team trained a group of neurosurgeons to use the robotic system. After just one hour of training, each surgeon was able to successfully operate the system to guide the wire through complex vessels that are difficult to navigate with a manual guidewire.The team also used the robotic system to clear simulated clots in difficult-to-reach areas in the model. They steered the guidewire through vessels, and around sharp corners and turns, to reach regions where the researchers simulated clots. Once they guided the wire to the clot, the surgeons proceeded with standard endovascular methods to thread a microcatheter along the wire to the site of the clot. They retracted the wire, leaving the catheter, which they then applied to successfully remove the clot.&ldquo;The primary purpose of the magnetic guidewire is to get to the target location quickly and safely, so that standard devices like microcatheters can be used to deliver therapeutics,&rdquo; Kim says. &ldquo;Our system is like a pathfinder.&rdquo;He hopes that the teleoperated system can help more patients receive time-critical treatment. He also sees benefits for surgeons, who typically perform such vascular procedures in the same room as the patient, while being exposed to radiation from X-ray imaging.&ldquo;The neurosurgeons can operate the robot in another room or even in another city without repeated exposure to X-rays,&rdquo; Zhao says. &ldquo;We are truly excited about the potential impact of this technology on global health, given that stroke is one of the leading causes of death and long-term disability.&rdquo;<hr>&quot;Reprinted with permission of <a href="https://news.mit.edu/2022/robot-stroke-treatment-remote-0413" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>&quot;&nbsp;

MIT engineers developed a telerobotic system to help surgeons remotely treat patients experiencing stroke or aneurysm. With a modified joystick, surgeons may control a robotic arm at another hospital to operate on a patient. Courtesy of the researchers

The system could provide teleoperated endovascular treatment to patients during the critical time window after a stroke begins.

Joystick-operated robot could help surgeons treat stroke remotely

Doing things underwater has always been challenging. Human divers brave the pressures of the deep subsea environment, dealing with low light, poor visibility, and little room for error. Since the 1970s, technology developments gave rise to ROVs with robotic arms (aka &lsquo;<a href="https://blueprintlab.com/products/manipulators/" target="_blank">underwater manipulator arms&rsquo;</a>) to start accomplishing tasks underwater.Industries that use ROV manipulators include offshore energy, military, search and rescue, and marine science.Whilst not as dexterous as humans, these ROV manipulator systems are stronger and can go deeper than humans can dive. This ushered in a new era for offshore oil companies who could now install and maintain deeper installations.Originally, ROV manipulators were large and hydraulically powered. Today, whilst large hydraulic manipulators are still the workhorse of the ROV industry, electric systems have started to be released to the market. In particular, smaller electric ROV manipulators that are still highly dexterous have opened up new possibilities for the ROV community.Here are the top 9 uses of underwater ROV manipulators based on working with our clients here at Blueprint Lab.<h2>1. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Non-Destructive Testing (NDT)</h2><a href="https://en.wikipedia.org/wiki/Nondestructive_testing" rel="noreferrer noopener nofollow" target="_blank">Non-Destructive Testing</a> (NDT), and sometimes called NDE or NDI for examination and inspection respectively, is the process of using non-invasive means to inspect a component or structure to detect cracking, corrosion, or other defects within the material.Offshore oil rigs will sit in the water, braving the elements, salt corrosion, and marine growth for 20-30 years. To ensure that these structures and other water-based assets remain safe, there are regulations that govern their Inspection, Maintenance, and Repair (IMR). Disasters such as what happened to the<a href="https://www.offshore-technology.com/features/feature-the-worlds-deadliest-offshore-oil-rig-disasters-4149812/" rel="noreferrer noopener nofollow" target="_blank">&nbsp;Alexander L Kiellande oil platform in 1980</a> or more recent <a href="https://www.cbsnews.com/news/gulf-of-mexico-fire-ocean-burst-pipeline" rel="noreferrer noopener nofollow" target="_blank">near misses in the Gulf of Mexico</a> have been caused by cracking and corrosion of subsea structures left unchecked.Manipulators and human divers routinely carry out inspections of structures for cracking or corrosion using<a href="https://en.wikipedia.org/wiki/Ultrasonic_thickness_measurement" rel="noreferrer noopener nofollow" target="_blank">&nbsp;Ultrasonic Thickness</a> (UT),<a href="https://en.wikipedia.org/wiki/Cathodic_protection" rel="noreferrer noopener nofollow" target="_blank">&nbsp;Cathodic Protection</a> (CP), or<a href="https://en.wikipedia.org/wiki/Alternating_current_field_measurement" rel="noreferrer noopener nofollow" target="_blank">&nbsp;Alternating Current Field Measurement</a> instruments. ROV manipulators that are dexterous, more compact, and have advanced software control (including being able to precisely control the position and orientation of the instrument) have enabled small ROVs to <a href="https://blueprintlab.com/blog/degrees-of-freedom-vs-functions-of-a-robotic-arm/" target="_blank">carry out these tasks completely remotely</a>. Companies such as Fugro are<a href="https://www.fugro.com/about-fugro/our-expertise/remote-and-autonomous-solutions/remote-and-autonomous-vessels" rel="noreferrer noopener nofollow" target="_blank">&nbsp;pioneering remote operations</a> where an Unmanned Surface Vehicle (USV) hosting an ROV can deploy and inspect infrastructure using dexterous manipulators.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2Njk5OTc0LXBhc3RlZCBpbWFnZSAwLnBuZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 766px;" class="fr-fic fr-dib"><h2 id="isPasted">2. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Dexterous (Human-Like) Intervention&nbsp;</h2>Achieving the same (or better) level of dexterity as a human is the holy grail of dexterous robotic manipulation. Huge progress has been made in recent years in terms of the size and joint dexterity of robotic manipulators above and below the water. One current limitation is the ability to achieve precise, small-scale dexterity. Land robots have demonstrated the use of robotic hands with fingers; successfully manufacturing similar technologies underwater is far more difficult and yet to be commercially solved.Some dexterous tasks such as tying a knot, attaching a carabiner, or fastening a nut to a bolt have all been demonstrated using underwater manipulator technology. This has allowed industries to use robotic manipulators for net repair in aquaculture settings, and conduct complex military tasks.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2NzM2MTM1LUFscGhhLTUtQ2xpcHBpbmctQ2FyYWJpbmVyLTc2OHg1NzAuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 766px;" class="fr-fic fr-dib">Alpha 5 Manipulator attaching a carabiner underwater&nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2Nzg0NjE3LXBhc3RlZCBpbWFnZSAwICgxKS5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib"><h2 id="isPasted">3. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Construction And Repair</h2>With hydraulic and electric actuators able to exceed the capability of humans, underwater manipulator arms are used for moving large tools and instruments around to aid in the construction, maintenance, repair, and decommissioning of a whole range of subsea infrastructure. In the offshore energy industry, manipulators move large hooks attached to cables for deployment and recovery of subsea infrastructure and wield torque tools or welding torches.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2ODE1NTExLU1pY3JvLUlQLUNhbWVyYS1CYW5uZXItMi03Njh4NDMyLmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 766px;" class="fr-fic fr-dib"><h2 id="isPasted">4. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Close Visual Inspection</h2>Like NDT, Close Visual Inspection (CVI) is concerned with looking at infrastructure with <a href="https://blueprintlab.com/products/underwater-rov-camera/" target="_blank">HD subsea cameras</a> to detect any issues that need repair or follow up. Manipulators with good reach (length) and dexterity enable CVI in hard-to-reach areas such as inside pipe inlets and behind propellers.This ability for confined space access is a value-add offered by more modern, compact, electric manipulators like Blueprint Lab&rsquo;s Reach Alpha and Reach Bravo. Leveraging HD CVI allows for Underwater Inspection in Lieu of Dry-docking (UWILD). UWILD, as the name suggests, is the CVI/NDT of a ship&rsquo;s hull that avoids needing to take the vessel out of the water; a huge cost and efficiency saving.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2ODQ1NDc1LUJyYXZvLVdyaXN0LUNhbWVyYS03Njh4NDI4LnBuZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 766px;" class="fr-fic fr-dib"><h2 id="isPasted">5. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Cleaning/Anti-Fouling&nbsp;</h2>Over time, subsea infrastructure can become coated in marine growth (barnacles etc) and other biofouling substances. To properly inspect the condition of the infrastructure (using NDT or CVI methods), surfaces must be cleaned of any marine growth. This is generally done by using high-power water pressure, a cavitation blaster, or a rotary brush.In some scenarios, this will be done using a fixed system on the ROV. In other cases, the dexterity of a manipulator is required or beneficial to adequately reach all areas that need to be inspected. This is especially relevant where the geometry of the inspection area is more complex, such as at the weld nodes of a jack-up rig.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2ODc1MDg5LU9pbF9SaWctNzY4eDU3Ni5qcGVnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 766px;" class="fr-fic fr-dib">Subsea steel joints&nbsp;<h2 id="isPasted">6. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Sea Mine And UIED Intervention&nbsp;</h2>Military clearance divers carry out dangerous tasks including deploying a shaped charge to disarm a mine or examining and disrupting a Waterborne Improvised Explosive Device (WBIED). These tasks are still done by humans because they require high fidelity perception and dexterous intervention capabilities not previously available through a remote solution. Recently, with the release of more dexterous, compact manipulator arms like the Reach Alpha, military organisations are investigating ways for ROVs to start to do some of these more dangerous tasks.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2OTEzMTM1LTEwMDU1MzczMDc1XzIxNmRkZTc3NWFfYy5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">Image Source: Flickr<h2 id="isPasted">7. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Special Recovery Operations (e.g. Downed Aircraft, Drowning Victims)</h2>Special Recovery Operations include scenarios such as recovering a downed aircraft from the seafloor or drowning victims from a lakebed. These sensitive tasks have historically been conducted by highly skilled military or civilian diver teams. Recently ROVs have been able to assist and in some cases take-over, these high-risk tasks.Dexterous manipulators can be used to tie knots or attach carabiners to recover objects or for the recovery of forensic items without disturbing the lake/sea bed.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4NzE2OTYxMjYwLUhFQVJULXNpbXVsYXRpb24tNzY4eDQ4OS5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">Alpha Grabber during a simulated recovery mission &ndash; See the full video story below!&nbsp;<iframe src="https://www.youtube.com/embed/19V9YdC-ZOM?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" style="width: 768px; height: 430px;"></iframe><h2 id="isPasted">8. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Oceanography And Hydrography (Sampling And Measurement)</h2>Understanding the condition of our marine environment is critical for building a global picture of the Earth&rsquo;s ecosystem. Scientists regularly take samples from the sea bed for analysis and collect marine organisms for biological study. In some cases, sampling and organism collection requires precise positioning of a sampling device as well as the ability to retrieve a sample without stirring up sediment from the seafloor. Additionally, measuring devices (rulers and callipers) are often used to properly characterize an object of interest. In these cases, a dexterous manipulator allows for the ROV to sit on the seafloor and for confined areas to be reached (such as amongst a coral reef)<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1648717362455-EGM_5604_Credit_AIMS-EricMatson-2048x1367.jpeg" style="width: 766px;" class="fr-fic fr-dib">Image source: Scimex<h2 id="isPasted">9. <style type="text/css" id="isPasted"></style><style type="text/css"></style>Autonomy And Custom Control&nbsp;</h2>Robotics and Autonomous Systems researchers around the world are pioneering the use of underwater robots in a variety of autonomous applications. Some examples of this are using manipulators to autonomously interact with a subsea control panel or using multiple robots to lift, carry, and place an object, thereby utilising the lift capacity of more than one underwater vehicle.<h2 id="isPasted"><style type="text/css" id="isPasted"></style><style type="text/css"></style>Final Thoughts </h2>The uses of underwater ROV manipulators are varied and constantly expanding. As a company, Blueprint Lab is seeking not just to make incredible robotic arms, but to actually solve industry problems. We constantly discuss and explore the problems that our clients are trying to solve and have multiple projects in work regarding underwater manipulation, perception and control.

The aim of this article is to provide a high-level answer to the question: “What do people use underwater robotic arms for?” If you’ve worked with Remotely Operated Vehicles (ROVs) before, this article probably isn’t for you. For everyone else, let’s go.

Top Uses of Underwater ROV Manipulators

Electroadhesion, also known as electrostatic adhesion, is an electrically regulated mechanism, that creates attraction between two materials. Utilized in robotic handling, climbing, and active adhesion[1].&nbsp;This term was coined by Danish scientists Johnsen and Rahbek in 1923, while working with polished lithographic stone and metal surfaces to describe the physical phenomenon of significant adhesion that occurred when the highly resistive stone was placed on top of a metal plate and a high voltage was applied between them[2]. When a conductor and a semiconductor are in contact and a voltage is applied across the two materials, the conventional Johnsen&ndash;Rahbek (J-R) effect explains the attractive force experienced between the two materials.To date, a wide variety of other standard adhesion techniques have been used to stick objects or materials together temporarily. Chemical adhesion, synthetic gecko feet, suction cups, mechanical and magnetic gripper are some of these techniques. However, they are still not enough to cover all the challenges.Electroadhesion mainly takes its place where the standard solution creates damage and marks on the product or fails to stick it effectively and efficiently during the process.&nbsp;Although this technology has improved over the years, two major problems remain. It is extremely difficult to adjust and eliminate the attractive force created, in a fast and controlled way. These points assume special importance when applied in industrial applications.PoleAttraction&trade;,&nbsp;an <a href="https://engimotion.pt/" rel="noopener noreferrer" target="_blank">Engimotion</a> development and the ultimate evolution of electroadhesion, intends to solve these challenges. Especially focused on non-conductive materials, it promises a fast and controlled delivery of the handled part at the delivery point, as well as handling of product stacks, with the defined number of layers, reliably.&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1650009711065-image+5-01+%285%29.jpg" style="width: 768px;" class="fr-fic fr-dib">Figure 1: Before PoleAttractionTM (left). After PoleAttractionTM (right).&nbsp; How does PoleAttraction&trade; Work?PoleAttraction&trade; consists of an advanced electronic controller and a set of attraction pads. The controller is responsible for energizing each pad, generating a magnetic field that will polarize it and the non-conductive part or surface in contact, creating an attractive force between them[3], according the defined thresholds and orders received through the existent interfaces.The pad is based on a capacitor model, where the part to be handled is included, and normally depending on the application, it can have various sizes, shapes, and levels of rigidity[4]. PoleAttraction&trade; uses a proprietary design that ensures effective attraction with over 90% non-conductive materials and surfaces.Each PoleAttraction&trade; pad needs a specific combination of certified materials, applied through a very demanding and controlled manufacturing process, to ensure, beyond the good functioning, a fast and controlled attraction response.&nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ5NDAzNzQ4MDQ4LXBvbGUgYXR0cmFjdGlvbiAzLnBuZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 788px;" class="fr-fic fr-dib">Figure 2: Cross section of the PoleAttractionTM pad. Image credit: Engimotion.Nonetheless, to achieve really interesting and viable performance results, the PoleAttraction&trade; controller was developed with an integrated closed loop control, empowered by artificial intelligence, which manages the amount of attraction with the part or surface in real-time.<h2>Advantages of PoleAttraction&trade; Over Other Existing Adhesion</h2>PoleAttraction&trade; has a number of advantages over other standard adhesion techniques, such as pneumatic, mechanical, magnetic, and bioinspired, even if combined.The following are some of the main advantages that make PoleAttraction&trade; so interesting for certain areas, products, and applications:<ol start="1" type="1"><li>Delicate and Contamination free: By using suspension or soft pads, PoleAttraction&trade; endows the ability to handle delicate and valuable objects efficiently and safely, without creating damage, marks or even stains.</li></ol><ol start="2" type="1"><li>Adaptability: PoleAttraction&trade; empowers equipment to be independent of the material structure of the part to handled. So, porous and flexible parts are no longer a problem.</li></ol><ol start="3" type="1"><li>Versatility: The same PoleAttraction&trade; system can handle different materials or surfaces, with varying shapes and dimensions, single layer or multilayer.</li></ol><ol start="4" type="1"><li>Robustness: Even when PoleAttraction&trade; faces harsh situations such as rough surfaces, wet materials, dusty settings, low pressures and temperature conditions, the equipped system will maintain the task success level, with no wear.</li></ol><ol start="5" type="1"><li>Low Consumption: Despite the fact that a high voltage needs to be supplied, PoleAttraction&trade; endows systems with low energy consumption, because only a very small current (mA range) will travels through the pad.</li></ol><ol start="6" type="1"><li>Low weight and compact: PoleAttraction&trade; can be easily applied in a system using materials and structures that are mechanically simple and lightweight, reducing system complexity.</li></ol><ol start="7" type="1"><li>High forces: PoleAttraction&trade; is very efficient when comparing the attraction force generated per contact area (up to 1.1N per 10mm^2), keeping the rest of the advantages unchanged.</li></ol><ol start="8" type="1"><li>Fast response: One device empowered with PoleAttraction&trade; will be very independent of the part to be handled, achieving minimum pick and place waiting time of 0.2 seconds.</li></ol><ol start="9" type="1"><li>Silent: A device equipped with PoleAttraction&trade; will work without creating any additional noise, due to the fact that the generated sound will be out of hearing range.</li></ol><ol start="10" type="1"><li>Detection: PoleAttraction&trade; enable the system to have real-time feedback on the presence of part or surface. This feature offers the possibility of a closed loop control.</li></ol><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ5NDAzOTEwMzQ2LVBvbGVBdHRyYWN0aW9uXzEgKDEpLnBuZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 788px;" class="fr-fic fr-dib">The PoleAttractionTM&nbsp;Pad. Image credit: Engimotion.Applications of PoleAttraction&trade; in the Real World&nbsp;PoleAttraction&trade; can help in a wide range of applications, in different areas and equipment. As a disruptive solution that offers new capabilities, the most demanding situations are those where standards adhesion solutions fail to effectivity and efficiently solve the challenge. However, the recent focus on electrical efficiency opened the door to a wide range of applications, where standard adhesion solutions has been applied.In the next points we will present some particularly advantageous applications of PoleAttraction&trade; technology:<ol start="1" type="1"><li>End of arm tooling: It is the most important component in robotic solutions, the one that interacts directly with parts and components, whose functioning can be influenced by the environment. PoleAttraction&trade; is often used in EOAT solutions, mainly due to its soft touch, adaptability, versatility, and robustness, providing effective and more efficient solutions. Beyond that, other advantages such as fast response, energy efficiency, integrated closed-loop control, low weight, and noise, are in line with the latest requirements and needs of robotic and automation solutions.</li></ol><ol start="2" type="1"><li>Cleanroom: Cleanroom is one of the most demanding environments where zero contamination is mandatory. PoleAttraction&trade; as standard is 100% compliant with all requirements, keeping contact with sterilized parts, medical equipment, or even pharmaceutical products possible.</li></ol><ol start="3" type="1"><li>High incline conveyor: When transporting certain products, the conveyor system can only be tilted to a certain degree. The material will slip, turn or fall when the angle exceeds this limit. PoleAttraction&trade; mainly due to its high force and compact volume can be used in the conveyor system to solve this limitation. Since the material is grasped when it is driven, the angle may be significantly higher.</li></ol><ol start="4" type="1"><li>Biomedical: PoleAttraction&trade; enables biomedical devices to function like a clutch, to replicate exoskeleton actuation such us the ankle. Its low weight, consumption and wear make it a very suitable solution.</li></ol><ol start="5" type="1"><li>Climbing robots: A wide variety of technologies have been tested and implemented in climbing robots, such as magnetic grippers, suction cups, gecko feet, etc. PoleAttraction&trade;, due to its low weight, compact volume, robustness and low consumption provides additional arguments for this type of systems.</li></ol><h2>Conclusion</h2>Several major applications have been presented since the inception of electroadhesion, enabling technical improvements ranging from robotic gripping and climbing to active adhesion and biomedical applications. It has been determined that an increase in electroadhesion research is both foreseeable and necessary. To that purpose, this article provides a presentation and overview of the new and disruptive PoleAttraction&trade; approach, including how it works, its benefits, and its applications.With these in place, the industrial community has at its disposal a new technology capable of being applied in more sectors and applications, improving the efficiency of its processes. Some existing limitations are now solved with PoleAttraction&trade;, increasing the quality of products, processes, and working conditions.While it is unclear how near scientists and companies are to developing one efficient electroadhesive technology, one thing is certain: Engimotion&rsquo;s PoleAttraction&trade; has arrived.<h2>About the sponsor: Engimotion</h2>Engimotion is a Portuguese start-up based in Porto with an aim of making the cutting-edge world of robotics accessible to SME&rsquo;s. &nbsp;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ5NDA0MDYxNTYyLWVuZ2ltb3Rpb24gYm90dG9tIGJhbm5lci5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib"> References<ol start="1" type="1"><li>Guo, J., Jinsong, L., and Rossiter, J. (2019). Electroadhesion Technologies for Robotics: A Comprehensive Review. IEEE Transactions on Robotics PP(99):1-15. DOI:10.1109/TRO.2019.2956869</li><li>Johnsen, A., and Rahbek, K. (1923). A physical phenomenon and its applications to telegraphy, telephony, etc. J. Inst. Electr. Eng. 61, 713&ndash;725. doi: 10.1049/jiee-1.1923.0092</li><li>Alpha Lab Inc (2018). Common static electricity problems and remedies: a series of brief articles. Available at: <a href="https://www.alphalabinc.com/common-static-problems/" target="_blank">https://www.alphalabinc.com/common-static-problems/</a> (Accessed January 4, 2022).</li><li>Cao, C., Sun, X., Fang, Y., and Qin, Q. (2016). Theoretical model and design of electroadhesive pad with interdigitated electrodes. Materials and Design 89:485-491 DOI:10.1016/j.matdes.2015.09.162</li></ol>&nbsp;

PoleAttraction™ is an advanced stage of electroadhesion technology, developed by Engimotion which promises to revolutionize industrial automation.

Understanding the Fundamentals of PoleAttraction™ Technology

<a href="https://sites.google.com/site/tapomayukh/home" target="_blank">Tapomayukh Bhattacharjee</a> has been working on assistive robotics for approximately a decade, and in speaking to the people who would benefit from new technologies, he’s come to a few realizations.“I started chatting a lot with the stakeholders – people with mobility limitations, the caregivers who are helping them, and occupational therapists – and I felt like robotics can truly make a difference in their lives, when it’s ready to be deployed,” said Bhattacharjee, hired in July 2021 as an assistant professor of computer science in the Cornell Ann S. Bowers College of Computing and Information Science.<iframe src="https://www.youtube.com/embed/f-NboRkoTDs?&amp;wmode=opaque&amp;rel=0" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 768px; height: 439px;"></iframe>Tapomayukh Bhattacharjee received a National Robotics Initiative collaborative grant for a project that aims to address the way people with mobility issues are given a chance for improved control and independence over their environments, especially how they are fed.&nbsp;Among the basic activities of daily living that robotics could impact, Bhattacharjee is currently focused on eating. And a&nbsp;<a href="https://www.nsf.gov/awardsearch/showAward?AWD_ID=2132846&HistoricalAwards=false" target="_blank">four-year, $1.5 million grant</a> from the National Science Foundation’s National Robotics Initiative will help him and his&nbsp;<a href="https://emprise.cs.cornell.edu/" target="_blank">EmPRISE Lab</a> develop assistive robotics for people with physical disabilities and their caregivers.“Feeding is one of the most basic activities,” he said. “Imagine yourself asking someone else to feed you every morsel of food in your day-to-day life. It just completely takes away the sense of independence. And so, if we could solve this feeding challenge, if a person could perceive this robot as an extension of their own body, then they will feel much more independent. That’s why I am so passionate about solving this.”Bhattacharjee – who received his Ph.D. in 2017 from the Georgia Institute of Technology, and developed a prototype robot during his postdoctoral work at the University of Washington prior to joining the Cornell Bowers CIS faculty – fully understands the nature of the challenge in front of him.“Despite great strides taken toward sustainable solutions in controlled environments,” he wrote in his grant proposal, “robots are far from ready for adoption in real-home environments as long-term caregiving solutions.”To address the eating challenge, Bhattacharjee will focus on three key elements:<ul><li>Bite acquisition: His team will derive algorithms that learn by obtaining human feedback – which they refer to as human-in-the-loop manipulation – to perform difficult tasks related to eating, particularly with different forms of food;</li><li>Bite transfer: The goal is to develop safe control and learning algorithms for bite transfer – that is, the robot actually placing the food safely in a person’s mouth, particularly if the person has profound physical limitations and cannot move to take the food; and</li><li>Feeding with user preferences: The team will develop active learning and shared autonomy algorithms that capture, over time, human preferences of bite transfer trajectories.</li></ul>“The main lessons we learned in our experiments [at Washington] was that every user is different,” he said. “Everybody has their personal preferences. And if we really want a long-term caregiving solution, the solution needs to be personalized to the user. And just like a patient and a caregiver need time to get used to each other, it’s the same with a patient and a robot.”The main target population Bhattacharjee is focusing on with his assistive technology is people with spinal cord injuries – those who are limited physically but not necessarily cognitively, so they would be able to help train the robot.One key element of the work will be leveraging the idea of human feedback – specifically by embracing the inevitable physical contact between the robot and human, such as when placing the utensil inside the mouth.“If you think about robots in airports, self-driving cars, robots in grocery stores, it’s all about avoiding obstacles,” Bhattacharjee said. “But realistically, if I’m grabbing for something, my arm might touch something else, right? The whole point is, can we leverage this contact, while being safe and efficient at the same time?”The grant period starts Jan. 1, 2022, and runs through 2025.

Doctoral student Rajat Kumar Jenamani, a member of Tapomayukh Bhattacharjee’s EmPRISE Lab, prepares to take a piece of a banana from an assistive robot prototype. Ryan Young/Cornell University

Tapomayukh Bhattacharjee has been working on assistive robotics for approximately a decade, and in speaking to the people who would benefit from new technologies, he’s come to a few realizations.

Robot-assisted feeding the focus of 1.5M USD NSF grant

This article was first published on <a href="https://news.mit.edu/2021/robot-finds-items-camera-antenna-1005" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>. &nbsp;<hr>A busy commuter is ready to walk out the door, only to realize they’ve misplaced their keys and must search through piles of stuff to find them. Rapidly sifting through clutter, they wish they could figure out which pile was hiding the keys.Researchers at MIT have created a robotic system that can do just that. The system, RFusion, is a robotic arm with a camera and radio frequency (RF) antenna attached to its gripper. It fuses signals from the antenna with visual input from the camera to locate and retrieve an item, even if the item is buried under a pile and completely out of view.The RFusion prototype the researchers developed relies on RFID tags, which are cheap, battery-less tags that can be stuck to an item and reflect signals sent by an antenna. Because RF signals can travel through most surfaces (like the mound of dirty laundry that may be obscuring the keys), RFusion is able to locate a tagged item within a pile.Using machine learning, the robotic arm automatically zeroes-in on the object’s exact location, moves the items on top of it, grasps the object, and verifies that it picked up the right thing. The camera, antenna, robotic arm, and AI are fully integrated, so RFusion can work in any environment without requiring a special set up.While finding lost keys is helpful, RFusion could have many broader applications in the future, like sorting through piles to fulfill orders in a warehouse, identifying and installing components in an auto manufacturing plant, or helping an elderly individual perform daily tasks in the home, though the current prototype isn’t quite fast enough yet for these uses.“This idea of being able to find items in a chaotic world is an open problem that we’ve been working on for a few years. Having robots that are able to search for things under a pile is a growing need in industry today. Right now, you can think of this as a Roomba on steroids, but in the near term, this could have a lot of applications in manufacturing and warehouse environments,” said senior author Fadel Adib, associate professor in the Department of Electrical Engineering and Computer Science and director of the Signal Kinetics group in the MIT Media Lab.Co-authors include research assistant Tara Boroushaki, the lead author; electrical engineering and computer science graduate student Isaac Perper; research associate Mergen Nachin; and Alberto Rodriguez, the Class of 1957 Associate Professor in the Department of Mechanical Engineering. The research will be presented at the Association for Computing Machinery Conference on Embedded Networked Senor Systems next month.<iframe src="https://www.youtube.com/embed/iqehzw_aLc0?&amp;wmode=opaque&amp;rel=0" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 767px; height: 433px;"></iframe><h2 id="isPasted">Sending signals</h2>RFusion begins searching for an object using its antenna, which bounces signals off the RFID tag (like sunlight being reflected off a mirror) to identify a spherical area in which the tag is located. It combines that sphere with the camera input, which narrows down the object’s location. For instance, the item can’t be located on an area of a table that is empty.But once the robot has a general idea of where the item is, it would need to swing its arm widely around the room taking additional measurements to come up with the exact location, which is slow and inefficient.The researchers used reinforcement learning to train a neural network that can optimize the robot’s trajectory to the object. In reinforcement learning, the algorithm is trained through trial and error with a reward system.“This is also how our brain learns. We get rewarded from our teachers, from our parents, from a computer game, etc. The same thing happens in reinforcement learning. We let the agent make mistakes or do something right and then we punish or reward the network. This is how the network learns something that is really hard for it to model,” Boroushaki explains.In the case of RFusion, the optimization algorithm was rewarded when it limited the number of moves it had to make to localize the item and the distance it had to travel to pick it up.Once the system identifies the exact right spot, the neural network uses combined RF and visual information to predict how the robotic arm should grasp the object, including the angle of the hand and the width of the gripper, and whether it must remove other items first. It also scans the item’s tag one last time to make sure it picked up the right object.<h2>Cutting through clutter</h2>The researchers tested RFusion in several different environments. They buried a keychain in a box full of clutter and hid a remote control under a pile of items on a couch.But if they fed all the camera data and RF measurements to the reinforcement learning algorithm, it would have overwhelmed the system. So, drawing on the method a GPS uses to consolidate data from satellites, they summarized the RF measurements and limited the visual data to the area right in front of the robot.Their approach worked well — RFusion had a 96 percent success rate when retrieving objects that were fully hidden under a pile.“Sometimes, if you only rely on RF measurements, there is going to be an outlier, and if you rely only on vision, there is sometimes going to be a mistake from the camera. But if you combine them, they are going to correct each other. That is what made the system so robust,” Boroushaki says.In the future, the researchers hope to increase the speed of the system so it can move smoothly, rather than stopping periodically to take measurements. This would enable RFusion to be deployed in a fast-paced manufacturing or warehouse setting.Beyond its potential industrial uses, a system like this could even be incorporated into future smart homes to assist people with any number of household tasks, Boroushaki says.“Every year, billions of RFID tags are used to identify objects in today’s complex supply chains, including clothing and lots of other consumer goods. The RFusion approach points the way to autonomous robots that can dig through a pile of mixed items and sort them out using the data stored in the RFID tags, much more efficiently than having to inspect each item individually, especially when the items look similar to a computer vision system,” says Matthew S. Reynolds, CoMotion Presidential Innovation Fellow and associate professor of electrical and computer engineering at the University of Washington, who was not involved in the research. “The RFusion approach is a great step forward for robotics operating in complex supply chains where identifying and ‘picking’ the right item quickly and accurately is the key to getting orders fulfilled on time and keeping demanding customers happy.”<hr>"Reprinted with permission of&nbsp;<a href="https://news.mit.edu/2021/robot-finds-items-camera-antenna-1005" id="isPasted" rel="noopener noreferrer" target="_blank">MIT News</a>"

Researchers at MIT have developed a fully-integrated robotic arm that fuses visual data from a camera and radio frequency (RF) information from an antenna to find and retrieve objects, even when they are buried under a pile and fully out of view. Credits: Courtesy of the researchers

This robotic arm fuses data from a camera and antenna to locate and retrieve items, even if they are buried under a pile.

A robot that finds lost items

Welding has never been an easy job to perform. It’s repetitive, exhausting, and pretty much dangerous for the people involved. With all the ins and outs, no wonder there is a shortage of qualified welders–the one that’s only about to increase due to the expected wave of retirements and lack of younger talent.To address the skills gap, Rozum Robotics developed an automated welding system for Tungsten Inert Gas (TIG) welding with argon gas. The scope of application was the welding of towel rail warmers from stainless steel.<iframe width="640" height="360" src="https://www.youtube.com/embed/pj0I8NjtJv0?&amp;wmode=opaque&amp;rel=0" frameborder="0" allowfullscreen="" class="fr-draggable"></iframe>The robotic system consists of two manipulators PULSE 75.&nbsp;PULSE is a 6-axis robotic arm suitable for applications that need high positioning precision and steady performance. They can be used for various repetitive tasks and are pretty lightweight making it easy to integrate them even into a compact work environment. The characteristics of PULSE 75 are as follows:&nbsp;<div align="left" dir="ltr"><table><tbody><tr><td>Payload</td><td>6 kg</td></tr><tr><td>Reach</td><td>750 mm</td></tr><tr><td>Degrees of Freedom</td><td>6</td></tr><tr><td>Position Repeatability</td><td>+/- 0.1 mm</td></tr><tr><td>Ambient Temperature</td><td>0...35 °С</td></tr><tr><td>Weight</td><td>12.6 kg</td></tr><tr><td>Non-Stop Lifetime Cycle&nbsp;</td><td>20 000+ hours</td></tr><tr><td>TCP Velocity (max)</td><td>2 m/s</td></tr><tr><td>End-Effector Mounting Flange</td><td>ISO 9409-1-50-4-M6</td></tr><tr><td>Footprint</td><td>120 mm</td></tr><tr><td>Platform</td><td>Web interface. Any device</td></tr><tr><td>Programming&nbsp;</td><td>Hand-guiding. REST API. UI</td></tr></tbody></table></div>Here’s a short brief on how the robotic welding system works:An operator places the soon-to-be-welded towel rail warmer into the fixture. After the workpiece is fixed and a short calibration is performed, the electrode reaches the required position. Then the welding head walks along the preset pathway resulting in neatly welded seams.The robotic welding system is completely safe for humans. The operators aren’t exposed to possible hard typically associated with the welding job. If a person accidentally moves too close to the robotic welders, they’ll shut down immediately.The solution keeps humans out of harm's way and allows enterprises to improve both productivity and the final product appearance.

With the number of skilled welders decreasing and the job being rather dangerous, implementing a robotic welding system is the next step for the industry. Here's an example of such a system.

Robotic Welding System to Save the Day For Welding 

3D printed sand casting molds and cores are changing the way high-performance, large metal parts are manufactured today. Additive manufacturing is enabling modern foundries to produce complex metal parts in rapid lead times. This article explains the benefits of coupling advanced design tools with 3D printed sand molds using, as an example, the redesign and manufacture of a 3-foot long robotic arm.<h2>Sand Casting &amp; Industrial 3D printing&nbsp;</h2>Metal casting is a common and well-proven manufacturing method used to produce goods that we incorporate into our daily lives. 90% of all manufactured products and machinery today include components made using casting. The most popular metal casting process is sand casting; over 70% of all metal parts are manufactured using this production process.&nbsp;The sand casting process begins by creating a sacrificial mold that consists of compacted sand mixed with a binder. The mold’s cavity is then filled with molten metal through a gating system before the mold is destroyed to release the cast part.&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1622627739519-ntop-humtown-mold-cleaning-2-1024x575.png" style="width: 788px;" class="fr-fic fr-dib">Large sand casting mold ready for use after 3D printing and cleaning.&nbsp;&nbsp;Sand casting dates back to the 1st century BC. Over the centuries, it has evolved into the industrial process we know. Yet, foundries today are further enabled by the advent of digital manufacturing and 3D printing technologies.Sand casting using 3D printed molds and cores is emerging as a key industrial application of additive manufacturing. Until recently, design engineers and casting foundries used this hybrid manufacturing technology primarily for prototyping. Today, more and more foundries in the US and overseas are adopting this manufacturing technology to augment their internal processes.&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1622627772915-ntop-humtown-mold-3d-printing-1-1024x573.png" style="width: 788px;" class="fr-fic fr-dib">3D printed sand molds and core are manufactured layer-by-layer directly from a digital file in an industrial 3D printing system. The print head jets droplets of binder material over thin layers of sand to create each cross-section.&nbsp;&nbsp;<h3>Benefits of Sand Casting with 3D Printed Molds &amp; Cores</h3>Here are some of the ways that 3D printing can benefit a casting foundry:<ul><li>3D printed sand casts and cores facilitate the creation of gating systems and risers that result in high-performance metal parts with fewer internal defects and up to 15% higher material strength. </li><li>Additive manufacturing eliminates the need for hard tooling and casting patterns and the associated geometry restrictions. This benefit facilitates the production of high-performance, optimized parts with complex geometry. </li><li>3D printing and other digital manufacturing technologies help transform the image of the traditional foundry, attracting young talent and new workforce to the field.</li></ul><h3>Limitations&nbsp;of Sand Casting with 3D Printed Molds &amp; Cores</h3>However, 3D printing is only a tool. The limitations of this new technology in regards to sand casting include:<ul><li>Part design should still follow the restrictions imposed by the casting process and the 3D sand printing systems. These design considerations include wall thickness, changes in part cross-section, and wall-to-wall thickness. </li><li>The current availability of industrial sand 3D printers is limited, and the cost of manufacturing 3D printed molds are relatively high. For reference, sand 3D printing costs approximately $0.1 per cubic inch, while a traditional foundry usually charges between $10-20k for a mold. </li><li>As with every new technology, access to knowledge and design expertise is still limited. Elusive best practices and design guidelines stop engineers and manufacturers from getting the most out of this new technology.</li></ul>The following case study directly addresses the last point. By documenting the design method and practical considerations that went into each decision, we hope to make this technology more accessible to manufacturers, designers, and engineers.<h2>Case study: Topology Optimized Robot Arm</h2>To demonstrate the benefits of sand casting with 3D printed molds and cores, the engineers of <a href="http://ntopology.com/" target="_blank">nTopology</a>, <a href="https://sites.psu.edu/shapelab/" rel="noopener" target="_blank">Penn State University</a>, <a href="https://www.flow3d.com/" rel="noopener" target="_blank">Flow 3D</a>, and <a href="https://www.humtown.com/" rel="noopener" target="_blank">Humtown</a> joined forces to redesign a meter-long robotic arm. Together they created an end-to-end digital casting workflow — from part optimization to design for manufacturability and, finally, manufacturing.The team combined cutting-edge design techniques, like topology optimization, with advanced casting features that can only be manufactured additively (including the sprue, gates, and risers). Using this method, the team managed to:<ul><li>Reduce the weight of the part by 40%</li><li>Avoid common casting defects</li><li>Directly 3D print the entire sand mold</li><li>Manufacture the part in less than a week</li></ul>&nbsp;<h3>Generating a Lightweight Robotic Arm&nbsp;</h3>The first step in this project was to optimize the geometry of the robotic arm. Using <a href="https://ntopology.com/topology-optimization-software/" target="_blank">topology optimization software</a>, the team reduced the weight of the part by 40% — from 240 lbs down to 165 lbs — while still fulfilling the functional requirements of the defined loading conditions.&nbsp;Topology optimization is a simulation-driven design technique used to maximize stiffness and minimize weight in aerospace and automotive engineering applications. The automated smoothening and reconstruction capabilities of nTopology enabled the team to make design changes quickly and with little effort.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1622627995487-ntop-humtown-topology-optimization-process.png" style="width: 788px;" class="fr-fic fr-dib">Overview of the topology optimization process in nTopology — from original design to final export as a CAD body.&nbsp;Of course, the engineering team considered the manufacturability of the part during the design phase. The final metal part weighs 165 lbs (or approximately 75 kg) when cast in aluminum and has bounding box dimensions of 39” by 16” by 16” (or 1.0 m by 0.4 m by 0.4 m). The robotic arm’s size limited the options available to the team to produce this huge part.<blockquote>“The only way to make a part this big and this complex is to leverage advanced manufacturing. Direct additive manufacturing techniques, such as SLM or EBM, were not an option due to the size of the part. For this reason, we decided to couple additive manufacturing with a sand casting mold.”<cite>Dr. Ryan O’Hara, Director of Aerospace Engineering at nTopology</cite></blockquote>Following the traditional mold-making method (using a master pattern) would introduce several complications. Due to the complexity of the geometry, the design team would have to make many compromises, reducing the performance of the part.<h3>Optimizing the Design of the Cast</h3>To demonstrate the capabilities of the technology, the team decided to directly 3D print the entire mold. A more common production scenario would be to 3D print only parts of the mold, like the mold’s cores or other critical-for-quality systems.This decision enables the team to optimize other critical features of the mold, like geometry and location of the sprues, gates, and risers. This process ensured the metal cast would have minimal internal porosity and high-performance material properties.The mold was designed through a collaborative effort between Penn State University and Flow3D. The team took two main design requirements into account during this step:<ol><li>The molten metal must fill the cavity as smoothly as possible. Research has shown that flow rates below 0.5 m/s are necessary to minimize turbulence and reduce the possibility of material defects due to oxide layer detachment and porosity.</li><li>The risers must solidify after the part.&nbsp;Uneven solidification is another common cause of internal defects, shrinkage, cracking, and part deformation. For this reason, the sections that will be machined off the part after casting must solidify last.</li></ol> <div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1622628033164-ntop-humtown-mold-assembly-2-1024x576.png" style="width: 788px;" class="fr-fic fr-dib">The mold was manufactured in parts and then assembled before pouring the molten metal. This design of the spiral helix sprue could not be manufactured with traditional patterns.&nbsp;&nbsp;To ensure that the material would fill the mold without introducing turbulence, the team reimagined the design of the gating system and the risers. Instead of a down sprue, they used a spiral helix probe. Instead of cylindrical risers, they opted for risers with a spherical or hemispherical shape.This optimized sprue and riser geometry ensured that the flow speed of the molten metal is below the desired threshold and that the molten metal would solidify evenly. Moreover, these features could only be made using direct additive manufacturing technologies, as it is impossible to create such tooling using a traditional casting pattern-making process.To determine the best part orientation and the optimal position of the runner, gates, and risers, the team ran multiple design iterations using casting simulation software. The goal of the simulations was to optimize riser performance, minimize porosity, and verify gate flow velocities. The simulation stage ensured that the part would be manufactured first-time-right and reduce the development time from months to weeks.<blockquote>“In this project, we applied all the sand casting knowledge that we have developed in the lab. We were able to incorporate theoretically optimal sprue and riser designs that cannot be manufactured using traditional methods. That was very effective in reducing the overall defects and was further validated using simulations.”<cite>Dr. Guha Manogharan, Assist. Professor, Penn State University</cite></blockquote>The unique direct production capabilities of the 3D printing process enable the production of these advanced mold design methodologies. They are also proven to yield significant performance improvement. Research has shown that, compared to traditional methods, cast parts produced using this model have:<ul><li>99% lower defects for a total of 0.02% internal non-metallic inclusions</li><li>8 to 15% higher strength when cast using the same materials</li></ul>The improved performance of the as-casted materials makes this process most relevant for foundries that create high-performance or custom parts.<h3>Streamlining the Manufacturing Process</h3>The ability to quickly produce the desired complex shapes and structures necessary in sand was fundamental to the part’s manufacturing to meeting the project’s goals.&nbsp;Humtown used one of their four ExOne SMax sand binder jetting 3D printing systems to the mold. Once the engineers of Humtown received the final mold design, they were able to print the mold in less than 24 hours. Due to their close partnership with Humtown, Trumbull Foundry was able to cast the mold within one day. <div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1622628146434-ntop-humtown-mold-release-3-1024x612.png" style="width: 788px;" class="fr-fic fr-dib">The process of pouring the molten metal into the 3D printed mold is identical to the sand casting process that takes place in any traditional foundry.&nbsp;&nbsp; &nbsp;&nbsp;Humtown is one of the leading solution providers of 3D printed sand casts in the US. They have embraced new technologies and they now encourage other foundries to adopt new casting methods to create a lean and agile supply chain ecosystem.&nbsp;<blockquote>“We need to start pushing casting to its limits. The biggest threat is staying the same — doing what we’ve always done. We need innovators who take advantage of new software to remove barriers in part and casting design. We also need foundries in the US to embrace new technologies to remain relevant on a global level.”<cite>Brandon Lamoncha, Director of Additive Manufacturing, Humtown</cite></blockquote></div>&nbsp;</div><div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1622628189833-ntop-humtown-mold-release-3-1-1024x768.jpg" style="width: 788px;" class="fr-fic fr-dib">The mold was destroyed after casting to release the metal part which is now ready for post-processing operations&nbsp;<h2 class="fr-img-space-wrap2">Key takeaways</h2>3D printing technologies are changing the scenery of metal casting. 3D sand printing enables design and manufacturing engineers to:<ol><li>Produce optimized large parts with complex geometries</li><li>Design casting molds that minimize internal material defects</li><li>Build leaner and more agile manufacturing supply chains</li></ol><h3>List of Additional Resources</h3><ul><li><a href="https://ntopology.com/videos/video/simulation-series-mold-design-and-casting-fluid-simulation-of-an-advanced-robot-arm-design-in-ntopology/" target="_blank">A technical webinar on part optimization, mold design, and simulation.</a></li><li><a href="https://sites.psu.edu/shapelab/" rel="noopener" target="_blank">Dr. Guha Manogharan’s research lab at Penn State University.</a></li><li><a href="https://www.sciencedirect.com/science/article/pii/S2214860418308960#fig0005" rel="noopener" target="_blank">Open-source whitepaper on the spiral helix sprue design.</a></li></ul><hr>This article was first published on the&nbsp;<a href="https://ntopology.com/blog/2021/05/04/design-brief-3d-printed-casting-of-3-foot-long-robot-arm/" rel="noopener noreferrer" target="_blank">nTopology blog</a>. </div>

3D printed sand casting molds and cores are changing the way high-performance, large metal parts are manufactured today. Additive manufacturing is enabling modern foundries to produce complex metal parts in rapid lead times.

Design Brief: 3D Printed Casting of 3-Foot Long Robot Arm

Bin picking, i.e. robotic picking of objects with random poses from a bin, is one of the most common robotic tasks yet also one that poses some of the greatest technological challenges. A robot needs to be equipped with exceptional vision and robotic intelligence to be able to localize each part in a bin, navigate to it without colliding with its environment or other parts, then pick it, and safely place it to another location in an aligned position.There are two ways to mount a 3D vision system in the robotic cell, each having its advantages and each being more suitable for certain applications:A. Extrinsic calibrationB. Hand-eye calibration <h2>Extrinsic calibration</h2>Extrinsic calibration is used in setups where the scanner is mounted in a fixed, stationary position in the robotic cell, usually above the bin. The scanner must not be moved in relation to the robot after the system has been calibrated but it does not need to be stationary in relation to the robotic cell.&nbsp;Photoneo offers five models of the <a href="https://www.photoneo.com/phoxi-3d-scanner/" target="_blank">PhoXi 3D Scanner</a> (XS – XL), each providing a different scanning volume ranging from 16 centimeters up to 4 meters. As a rule of thumb, the more room is required for the bin picking application – including the space for robot movement, the size of the bin and parts, etc. – the larger model of the PhoXi 3D Scanner is required.Extrinsic calibration&nbsp;is done with any suitable ball&nbsp;attached to the endpoint of the robotic arm or to the gripper. The ball needs to be made of a material that is appropriate for scanning, that means smooth and not too reflective.<div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1621588982478-Photoneo_Extrinsic+calibration.png" style="width: 700px;" class="fr-fic fr-dib">Extrinsic calibration: The 3D scanner is mounted in a stationary position.&nbsp;&nbsp;</div><h2>Hand-eye picking</h2>Hand-eye calibration allows you to mount the 3D vision system directly onto the robotic arm. For a successful calibration, the scanner must be mounted behind the very last joint (e.g. on the gripper). Any changes made to the scanner’s position after the calibration renders the calibration matrix invalid and the whole calibration procedure must be carried out again. <iframe width="640" height="360" src="https://www.youtube.com/embed/hu9RHfuUwW0?&amp;wmode=opaque&amp;rel=0" frameborder="0" allowfullscreen="" class="fr-draggable"></iframe> Hand-eye calibration&nbsp;is done with a marker pattern – a flat sheet of paper (or another material) with a special pattern recognized by Photoneo PhoXi 3D scanners. <div class="fr-img-space-wrap"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1621589161916-Photoneo_Hand-eye+calibration.png" style="width: 700px;" class="fr-fic fr-dib">Hand-eye calibration: The 3D scanner is mounted on the robotic arm.&nbsp;&nbsp;</div><h3>Advantages of hand-eye picking</h3>Hand-eye picking offers a number of advantages over the traditional setup. If you have a large bin&nbsp;and a scanner mounted above it with a fixed viewpoint, you will not be able to scan the bin with a&nbsp;small scanner. If you mount a small scanner directly onto the robotic arm, you can come closer to the contents&nbsp;of the bin with the scanner and choose which part of the bin to scan.Another advantage of hand-eye bin picking comes in case you have two bins. One scanner mounted firmly in a fixed position will not be able to make scans of both bins – this would require two scanners at least. In contrast to this, a scanner mounted on the robotic arm will move from one bin to another&nbsp;and make scans of their contents from appropriate distance and angle. It is thus able to cover a larger area than extrinsic calibration.Hand-eye bin picking may also eliminate the need to darken the room where the robotic cell is placed. The ambient light coming from a window might pose serious challenges to the deployed 3D vision system and often requires special effort to darken the whole room. A scanner attached to the robot can make scans of a bin from one side first and then from another, minimizing the need to make any special adjustments to the environment.It can also happen that the 3D vision system itself casts shadows on the bin and inhibits a high-quality acquisition of the scene. This problem is usually solved by making a compromise and finding the most optimal position for the scanner in relation to the bin or by manually rearranging the parts within the bin so that the vision system captures them all in the end. Hand-eye bin picking eliminates this problem as it enables the scanner to “look” at the scene from any angle and from any position.Similarly, the hand-eye approach is an optimal solution for picking&nbsp;parts that are placed close to the walls of the bin. The walls – and even the parts themselves – may cast shadows and inhibit the recognition of the parts so mounting the vision system onto the robotic arm will allow you to approach and pick the parts from an appropriate angle.&nbsp;While hand-eye bin picking provides numerous advantages over extrinsic calibration, it is also fair to say that a scanner attached to the robotic arm may restrict the robot’s movements. Bearing this limitation in mind, it is advisable to choose a smaller scanner. In the case of Photoneo PhoXi 3D Scanner family, the appropriate models are XS, S, M, and L, covering a scanning range from 16 cm up to 2 m.Another important fact is that the robot needs to stay still during scan acquisition, which may prolong the cycle time. Therefore, the hand-eye approach is not suitable for time-critical applications.If you want to automate your application but are not sure what type of bin picking solution would be best suited for your project, <a href="https://www.photoneo.com/contact-us/" rel="noopener noreferrer" target="_blank">contact Photoneo</a> and let’s discuss it. We will be happy to assist you.

There are two ways to mount a 3D vision system in the robotic cell, each having its advantages and each being more suitable for certain applications. However, there are many cases where hand-eye calibration surpasses the more traditional setup in a number of respects.

Hand-eye bin picking

Picking an electric drive for robotic applications is a delicate matter—and a real headache. Sometimes it’s easier to order a custom motor for your robot instead of buying a standard one.&nbsp;Of course, you can always obtain a conventional drive model from a well-known manufacturer and ask for modifications. However, here comes the downside: such changes are typically expensive, and you’ll probably have to wait longer for them to be made. For a hardware startup building a prototype, long delays can be a dealbreaker.&nbsp;Meanwhile, a custom electric motor can save you lots of your time, money, and nerves. What is more, a made-to-order engine is a better fit for an advanced product with peculiar dimensions and specifications. Such a solution may have extra protection to endure specific environmental hazards.However, when you have no clear picture of what you should get, ordering a custom motor may seem too complicated. To ease your worries, we at Rozum Robotics have come up with a list of recommendations to consider before filling out a custom motor request.&nbsp;<h2 dir="ltr">What You Should Know About Custom Motor Specifications</h2> <div class="fr-img-space-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjIwOTg0OTU1NDUwLUlNR180NzAyICgxKS5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib">FMI Drive by Rozum Robotics&nbsp;If you want to get a custom electric motor, you’ll have to review some technical specifications for your product first.&nbsp;</div> Here's what we suggest paying attention to and put down in a checklist for a tailored drive (you may not know all of them, but that’s no problem—even identifying some of them can be of huge help):<ul><li dir="ltr">Power Supply</li></ul>Check out your power supply parameters first. Are we talking about single-phase electric power, three-phase one, or DC?<ul><li dir="ltr">Nominal Supply Voltage</li></ul>Do you know the intended nominal supply voltage of your system? If yes, inform the manufacturer about it.<ul><li dir="ltr">Overall Dimensions</li></ul>Before ordering a custom engine, you have to think about how it’s going to fit. Take all the necessary measurements, such as height, width, depth, and weight. If known, add to these parameters the diameter and length of the output shaft end.<ul><li dir="ltr">Housing</li></ul>There are at least three things to consider: the material of your application housing, the insulation class of your stator windings, and the Ingress Protection Rating of the electric motor you want to have. The rating is used to define the protection level against water and dust.<ul><li dir="ltr">Motor Characteristics</li></ul>One of the most important steps is to identify required motor ratings. To do so, answer the questions below:<ol><li dir="ltr">How should motor windings be connected?</li><li dir="ltr">What should the nominal and maximum engine torque be?</li><li dir="ltr">What should the nominal and maximum voltage be?</li><li dir="ltr">What should the nominal and maximum rotation speed be?</li><li dir="ltr">What should the nominal motor power be?</li><li dir="ltr">What should the rotor moment of inertia be?</li><li dir="ltr">What is your expected efficiency output?</li><li dir="ltr">What is your operation mode, S1, S3, or something else?</li></ol><ul><li dir="ltr">Environment</li></ul>The environmental impact determines the life cycle of a drive, so it’s crucial to have a clear understanding of the conditions your drive will operate under. Have you established the operating temperature range? What about humidity? Is the environment corrosive or explosive? All these things matter when developing a reliable custom motor.<ul><li dir="ltr">Control System</li></ul>When it comes to the control system, you need to take a closer look at your controller. Is it an in-house solution or a purchased product from a third-party provider? If yes, who is the manufacturer? What is the model of this controller? Do you need feedback control?&nbsp;Another important thing is to define the commutation type of the motor. Is it trapezoidal or sinusoidal?&nbsp;<ul><li dir="ltr">Temperature Sensors</li></ul>Do you require inbuilt sensors to detect temperature changes so that the motor can shut off power and prevent overheating from happening?<ul><li dir="ltr">Additional Requirements</li></ul>The needs of hardware startups vary. Your custom motor may need some additional features not mentioned in this article. If you’re pressed for time or on a shoestring budget, you may also want to include these facts in the list of demands.<h2 dir="ltr">What You Should Check About a Custom Motor Manufacturer</h2> <div class="fr-img-space-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjIwOTg0ODExNjYxLUlNR180NzE5LmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 300px;" class="fr-fic fr-dib">FMI Drives by Rozum RoboticsIt’s always challenging to find a credible custom motor manufacturer able to deliver engines on cue.</div>To avoid pitfalls, we recommend having a detailed conversation with a potential partner and focusing attention on the following points:<ol><li dir="ltr">Production: Make sure your partner has in-house production and doesn’t outsource projects to unknown third parties. Working with a direct manufacturer gives you more control over the process—and makes it transparent;</li><li dir="ltr">Expertise: It’s safer to order custom motors from a vendor who has a proven track record of successful products;</li><li dir="ltr">Pricing:&nbsp;Finding a producer with a reasonable price-quality ratio is an entire quest—we at Rozum Robotics went through this themselves when we were looking for a customized solution. Eventually, we decided to produce motors all by ourselves.&nbsp;</li></ol>Don’t hesitate to verify all the possible information about prospective suppliers—the precaution will save you from unnecessary trouble down the road.<h2 dir="ltr">The Bottom Line</h2>If you’re a startupper trying to take the world by storm, you know how important it is to get a personalized engine for a prototype. In this case, ordering a custom motor can provide you with many benefits since you’re getting a solution adapted for your application. Although it requires some preliminary fieldwork, such a step can help you get ahead of competitors and build something awesome along the way.&nbsp;

robotic arms

Profiles