Research Robots

<h2>Akira Science AB, a start-up based in Stockholm, is betting on the combination of two revolutionary disciplines: tissue engineering and 3D printing.&nbsp;</h2>These two disciplines used to belong to two different stories that are now deeply interconnected. During the last fifty years scientists and surgeons have combined the concepts of life sciences, biology and biocompatible materials to construct functional tissues and open the way to innovative and less invasive techniques respect to traditional surgical transplants. They have been looking for new materials to substitute classical treatments to improve medical treatments where autograph or allograph of explanted tissues are required due to disease or trauma. In parallel to this story, 3D printing technologies also known as Additive Manufacturing (AM) were born in the 1980s and initially intended to quickly produce prototypes within industrial applications. When 3D printing technologies later met tissue engineering, a powerful combination consolidated to create structures with controlled geometry and high rate of reproducibility. Tissue engineers have been seeking for structures &ndash; scaffolds&nbsp;&ndash; that can provide structural and mechanical support to a damaged tissue while promoting its regeneration and allowing nutrients&rsquo; supply to the cells.The 3D printing market has been growing fast during the last decade releasing innovative technologies and materials, especially for the medical sector. 3D printing is transforming the way we manufacture objects from a centralized to a decentralized, customized production onsite.Akira Science is projected to have an active role in these future landscapes of smart and innovative manufacturing technologies applied to degradable materials for medical applications. The business potential arises from the ever-increasing need of patient-specific medical devices and of timely laboratory biological studies to test drugs and new clinical strategies - never so evident like in this pandemic period.&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1590050859860-1590050859859.png" style="width: 655px;" class="fr-fic fr-dib">A cutting-edge new material and a smart scaffold design are the complementary and revolutionary points of force of Akira&rsquo;s strategy. The newly developed polymer (AKIMed-c12) has exceptional thermal stability, ensuring control of the material properties while printing, presenting a faster degradation time in the body environment than the current utilized materials (from 3-5 years to 9-10 months). Although newly formulated, AKIMed-c12 is made starting from well-established building blocks for the synthesis of approved biomedical materials, ensuring biocompatibility and non-toxicity in the physiological environment. While the printed scaffolds are not hard as the current available ones, but soft and pliable proving comfort to the patient (AKIMed-c12: 3D printed scaffolds).<iframe width="640" height="360" src="https://www.youtube.com/embed/GdgRqw2ZHjw?&wmode=opaque" frameborder="0" allowfullscreen="" class="fr-draggable"></iframe> The new material will be the workhorse for the 3D printing of degradable medical devices, while the smart design opens the way to new applications in tissue regeneration that were not possible until today utilizing the materials available on the market. Akira team is confident that such a combination has the potential to expand the scope of degradable 3D printed scaffolds from hard, for example bone, to soft tissue regeneration, such as breast reconstruction after mastectomy.Akira Science is providing both filaments for 3D printing and scaffolds with an architecture that satisfies customers&rsquo; need. Researchers and clinicians can buy the filament (AKIMed-c12: filament) and print the desired shape in their own facilities or can decide to ask Akira for printing their customized devices. Akira also provides support and consulting to collaborators and customers with material selection, design and simulation of the mechanical behavior of the desired scaffolds.The company continues to invest in open innovation through a continuous dialogue with customers and by setting new strategies to map future needs in tissue engineering and 3D printing opportunities.<hr>&Aacute;lvaro Morales and Tiziana Fuoco (AKIRA Science AB)

“The nexus between two revolutionary disciplines is inspiring us towards a future improved society”

Tissue Engineering and 3D Printing: Two Revolutionary Disciplines Now Fused Into One

Henrik Christensen shares his views on the impact of the robot revolution and stories from his life in European and US robotics research.

The impact of the robot revolution with roboticist Henrik Christensen

<h1>Executive Summary</h1><h2>Intro</h2>Wevolver is a platform &amp; community providing engineers informative content to help them innovate. Wevolver reaches millions of engineers every month in a very specific demographic: over 41% of them are between 25 and 34 years old, and less than 10% are older than 44.&nbsp;Geographically, European countries represent 28% percent of the audience, the USA 26%, and beyond India&#39;s 10%, the audience is spread widely across the globe.This provides a unique opportunity to learn about this engineering generation&#39;s interests, concerns, and points of view. Previously other interesting reports have been published by engineering organizations: For example, Hackster.io reported in 2016 on the maker community, Fictiv holds a yearly survey among mechanical engineers (primarily in the US), and IEEE conducts their &#39;Pulse of Engineering&#39; report. We think that Wevolver&#39;s &#39;Engineering State of Mind&#39; research complements those because of the specific demographics of its audience, as well as the report&#39;s specific focus on how this cohort views the world.(The report is also available as a download. Click <a href="http://bit.ly/33dSx64" rel="noopener noreferrer" target="_blank">here</a> to access the PDF)<h2>About the People</h2><ul type="disc"><li>+200 people respondents who were notified through Wevolver&#39;s newsletter and social media posts and responded between July 15th and August 31st, 2019.</li><li>Represent a wide range of industries.</li><li>60% were professional engineers, working at a wide range of company sizes; from sole proprietors to +100.000 people.</li><li>82% of students are at undergraduate level or higher.</li></ul><h2>Main Outcomes</h2>1. Engineers are extremely worried about climate change. 2. Engineers think A.I. is strongly under-appreciated. 3. Engineers are strongly interested in the field of robotics.<hr><h1>All Results</h1><h2>Demographics</h2>Now let&#39;s dive deeper into the results of the survey. Starting with the demographics:<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995166383-Slide4.JPG" style="width: 1114px;" class="fr-fic fr-dib"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995206862-Slide5.JPG" style="width: 1097px;" class="fr-fic fr-dib">Only 1% of survey respondents label themselves as a Hobbyist Maker. At the same time, we know from conversations we&#39;ve had that many professionals do perform &#39;Maker&#39; activities in their spare time: Examples range from developing electric motorbikes to tinkering with 3D printing.Among the professionals the majority has a role in engineering; beyond the most represented roles such as Mechanical Engineer, Electrical engineer, and Software engineer, there is a whole range of disciplines; Chemical Engineer, Civil Engineer, Biomedical Engineer, etc. There is also a significant amount with a pure leadership role, many of which who have been trained as an engineer, and 9.9% works as a researcher. Other roles that were expressed include education, analyst, and helicopter pilot. Among students disciplines include Mechanical and Electrical Engineering, Robotics, Aerospace, and Computer Science.These roles are applied in a wide range of industries, as we&#39;ll see next:<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995345594-Slide6.JPG" style="width: 1102px;" class="fr-fic fr-dib">Sixteen percent of respondents are active in the Industrial Robotics &amp; Automation industry (interestingly, as you&rsquo;ll see later, a much larger group (over 66%) of all respondents actually lists robotics as the topic they are most interested in).&nbsp;Services, ranging from manufacturing to engineering and design services, are also strongly represented, and software is a third runner up. Beyond those, our respondents&rsquo; industries cover a wide range. Other industries mentioned include VR, Art &amp; Design, Chemical, Naval, and Aeronautics.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995265581-Slide7.JPG" style="width: 1114px;" class="fr-fic fr-dib">It appears that engineers have a voice: The majority is involved in day to day engineering decisions, and many are involved in determining the direction of their company&#39;s R&amp;D. When we zoom in, we see that the percentage of engineers being involved in setting R&amp;D directions is significantly higher at small and medium size companies (64% versus 44% at companies over 500 employees).Engineers are involved in purchase decisions, especially when we zoom in on smaller companies. While the total percentage of being either involved in or making purchase decisions is roughly equal for all types of companies (around 47%), when looking at small companies the amount of people who actually make purchase decisions themselves (17%) is more than double that of large companies.<h2>Insights</h2>We could label this cohort as relatively young (with 91% being below 44), well educated, and representing quite a wide range of industries and company types. These people work in the most innovative companies in the world and are responsible for developing the products and technologies we&#39;ll use. Furthermore, the influence of this cohort is likely to increase as they progress in their careers and continue to grow their skills, experience, and knowledge.Therefore, we think the perspective of this community matters and that&rsquo;s what we&rsquo;ll dive into now.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995456957-Slide8.JPG" style="width: 1114px;" class="fr-fic fr-dib">We inquired which topics these engineers are most interested in to learn about. The results from the survey correlate with what we see are the most popular content topics on the Wevolver platform.Robotics &amp; Automation dwarf other topics of interest. This is interesting as only 16% of respondents are actually active in the industrial robotics and automation industry. Clean Energy is a good runner up which is not surprising given the concerns engineers have about climate change and environmental issues. In that light, Clean Energy could have scored even higher. One explanation might be that engineers think sustainability challenges need to be tackled on many facets, as we&#39;ll see later in the survey (for example, one respondent commented how advances in quantum computing could help solve complex environmental issues). The strong interest in A.I. and other computing advancements (including big data and quantum computing) is in line with the rapid developments in this field, as well as with the point of view from engineers that A.I. as a technology is strongly under-appreciated. Worth noting is that A.I. forms an essential component of the topic of robotics as well as of autonomous vehicles (autonomous vehicles sits among the top 3 topics for over 21% of the survey respondents as well). Respondents also mentioned their interest in the ethics involved in A.I. We consider the relatively low interest in AR/VR surprising compared to the size of the interest (or hype) in media and venture capital. &nbsp;Engineers have many interests, and other topics mentioned include medical technology, astrophysics, and; &quot;literally everything.&quot;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995505356-Slide10.JPG" style="width: 1114px;" class="fr-fic fr-dib">Given the sizable interest in Robotics we zoomed in on the people interested in this topic and explore which subdomain they are focused on. In this instance we enquired specifically which fields engineers wanted to grow expertise in. Our view is that this question reveals being active or an interest to become active in the chosen domain, beyond being purely interested an sich. This gives an indication of the importance engineers deem the domain to have in the future.Both Collaborative Robots (&#39;cobots&#39;) and Human-Robot Interaction are the big standouts here. These two topics also overlap and are related: Collaborate Robots are defined as &ldquo;robots intended to interact with humans in a shared space or to work safely in close proximity. Cobots stand in contrast to traditional industrial robots, which are designed to work autonomously with safety assured by isolation from human contact.Human-Robot Interaction (HRI) describes the studying or designing of robotic systems for use by or with humans. Developing collaborative robots requires designing how humans engage with these machines and through which interfaces. Apart from its application to collaborative robots, HRI applies to many (if not all) fields in robotics, especially with the growing cognitive capabilities of robots this field has seen significant growth.Cobots and HRI stand out, which can be expected given the growth and size of both fields. In our eyes, the most remarkable result is the significant interest in the domain of bio robotics. At the moment this field is tiny from a commercial perspective but apparently expected to grow in importance.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995563949-Slide12.JPG" style="width: 1114px;" class="fr-fic fr-dib">This question reflects the impact engineers think a given technology will make in comparison to the attention the technology receives from society. Here engineers point to a clear conclusion: &quot;A.I. &nbsp;will be huge, and society doesn&#39;t see how big its impact will be.&quot; We found this result striking because, at first glance, there doesn&#39;t seem to be a lack of attention to A.I. in media and within companies. However, engineers think the impact of A.I. will be orders of magnitudes bigger than reflected by that amount of attention. Secondly, people we spoke with indicated that their perspective is most of us don&rsquo;t conceive how much of our lives and society will change because of implementations of Artificial Intelligent systems&nbsp;<blockquote><blockquote><blockquote><blockquote>Engineers point out that the implications and impact of A.I. are significantly bigger than what people generally expect.</blockquote></blockquote></blockquote></blockquote>Up to this point, the survey uncovered unexpecting insights. On top of that, the one that completely stopped us in our tracks was the absolutely unanimous answer to our question about challenges the world faces:<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1571995582131-Slide13.JPG" style="width: 1114px;" class="fr-fic fr-dib">Take note: The smartest minds on our planet are deeply worried about the health of our environment. This topic overshadows seemingly high impact challenges as poverty and healthcare, and even the potential negative aspects of A.I. are seen as a significantly impactful challenge. As one said, &quot;Without a healthy habitable planet, nothing else matters.&quot;Respondents had to answer this question in an open-ended way. After the survey, we classified all responses. Climate change, environment, and clean energy were so often mentioned in a single answer and used interchangeably that we decided to classify them under a single banner. Note that the survey was held over the summer, before the current global climate crisis strikes and relatively heightened attention to the topic.We had expected a wider distribution of challenges, and for example expected a higher attribution to robotization and employment. At the same time, high concerns about our environment correspond with the activity we see happening in Wevolver&#39;s community: discussion threads about the topic consistently generate a high level of engagement, and any knowledge share on the topic is likely to spark a high amount of interactions.<blockquote><blockquote><blockquote><blockquote>&quot;Without a healthy habitable planet, nothing else matters.&quot;</blockquote></blockquote></blockquote></blockquote> <h1>Conclusion</h1>We perceive this cohort of engineers being relatively strongly socially engaged. Socio-economic issues and the ability to contribute matter to them. This is reflected in the results of our inquiries into these engineers&#39; concerns, interests, and world view. You cloud also label them as relatively &#39;techno-optimistic:&#39; Many think technological advancements can solve current challenges, or at least need to play an essential role in solutions.Engineers ride an interesting balance. Generally optimistic about the role that technology plays, they also are more clearly aware of its current state and limitations. &nbsp;For us, the research&#39;s insight into engineers&#39; concern about our environment has been the most striking and we think it&rsquo;s a telltale sign. Based on this research, we have increased the informative content we share about this topic, as well have started more discussion threads and Q&amp;A sessions to grow the available knowledge and engagement.A.I. and robotics are the two big other topics that engineers pay attention to. According to engineers, our society underappreciates the impact of A.I. Besides this, we think that the research also points to a discrepancy between the interest of engineers in robotics, and the level of attention the subject gets from the general public, media, and politicians. We recommend leaders to take note of this, and increasingly opening up the conversation with the people who are developing today&#39;s and tomorrow&#39;s technologies. Ultimately, engineers are the ones who can most clearly see both capabilities and limitations of technology, as well as its future directions.&nbsp;We&#39;d like to thank all survey participants, as well as our community members who helped spread the survey.&nbsp; Please share your feedback and questions, we&#39;re looking forward to hearing from you. &nbsp;On behalf of team Wevolver; Bram Geenen,&nbsp; CEO Wevolver.(The report is also available as a download. Click <a href="http://bit.ly/33dSx64" rel="noopener noreferrer" target="_blank">here</a> to access the PDF)<hr><h2>About Wevolver</h2>Wevolver is a platform &amp; community providing engineers informative content to help them innovate. Wevolver reaches millions of engineers with articles, project descriptions, videos, and engaging conversations about state of the art technology that enable to keep up to date and find knowledge when engineering. The information on Wevolver&#39;s platform is created by a community of engineers, Wevolver&#39;s network of academic researchers, and editorial staff. Companies can sponsor content on the platform. For this work Wevolver won the SXSW Innovation Award, the Accenture Innovation Award, and the Top Most Innovative Web Platforms by Fast Company. Wevolver is how today&#39;s engineers stay cutting edge.

Research reveals the concerns, interests, and visions of the people who develop our future technologies.

2019 Engineering State of Mind Report

Scanning Electron Microscope (SEM) Machine in Laboratory

This article delves into the fundamental principles of SEM, various imaging modes and techniques, sample preparation methods, and the applications of SEM in different fields.

Scanning Electron Microscopy: A Comprehensive Guide

This is the 3rd and final article in a 3 part series featuring the applications of tinyML. The series introduces the concept of tinyML and explains some selected applications of the technology in various fields like sustainability, healthcare, and education.Education is the first step towards innovation. It is an integral part of personal development and equips the learners with the tools necessary to go ahead and solve the challenges faced by humanity. While tinyML is a great tool to develop pedagogical interventions for improving the quality of education in different streams, it is in itself a vast subject that every science and technology student must be familiar with.In our <a href="https://www.wevolver.com/article/applications-of-tinyml-in-healthcare-for-a-safer-future" target="_blank">previous article</a> about the applications of tinyML, we explained how it aids medical research and improves healthcare. This article continues the series by showcasing two more applications of tinyML for education.<h2 dir="ltr">Using tinyML for Neuroscience in K12 education: tinyML4STEM</h2>Anything and everything concerned with the central nervous system is a part of neuroscience. It is a multidisciplinary field that involves a scientific study of how the brain coordinates with the body and makes various body functions possible. The study is not just limited to humans but can also be extended to animals and even plants.Roughly 20% of the world’s population has suffered from a neurological disorder at some point in their lives, and none of the disorders have a cure yet. The only way to make new discoveries in the domain is by promoting research and education.It is also interesting to note that the most fundamental unit of Machine Learning (ML) is called a neuron and the whole concept and modelling of Artificial Intelligence (AI) based systems came from neuroscience. This makes it essential to talk about the specialised subject with the students of computer science to make them understand the underlying principles of the technology.But the problem with neuroscience education has always been the affordability and availability of experiment kits. Unlike many other Science Technology Engineering Management (STEM) fields, the apparatus for performing neuroscience experiments can not be acquired easily by schools and colleges. Graduate students opting for a specialisation in the area are the only ones to get their hands on these experiment kits.Greg Gage and Tim Marzullo realised this problem back in 2008 when they were pursuing PhD at the University of Michigan. The duo tried explaining neuroscience concepts to school children but couldn’t do so without showcasing practicals. There was no way to bring expensive graduate college equipment to schools. To solve this issue and make neuro-science kits affordable and readily available, Greg and Tim founded Backyard Brains.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkwNDUyMjI0LWltYWdlNy5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="EMG-signals-backyard-brains">Illustrations like these can help kids grasp even complex concepts easily. Source: Backyard BrainsThe organisation today makes low-cost neuroscience trainers, DIY kits, tools, software, conducts workshops and a lot more to democratise neuroscience education.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkwNTI1MDYyLWltYWdlMS5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="neuroscience-experiment-kits-backyard-brains">Neuroscience trainer kits by Backyard Brains are great alternatives for schools to introduce the students to the field. Source: Backyard BrainsNeuroscience signals like Electromyogram (EMG), Electrooculogram (EOG), Electrocardiogram (EKG), etc., can be used to get various cues about what is going on inside the body.When neurons fire electrical impulses from the motor cortex, the signals flow through the spinal cord to the parts of the body involved in the action. By putting small electrodes on the skin near the areas where the signals can be picked up, it is possible to observe them via an EMG. The impulses being electrical in nature can be amplified as a single-dimensional signal and visualised easily. These single-dimensional signals are beautiful for ML and are also quite easy to be analysed.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkwNjI0MDcwLWltYWdlNC5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="visualising-neuroscience">A snapshot from tinyML talks where Greg demonstrates how EMG signals can be visualised with a low-cost training kit. Source: tinyML YouTubeThe patterns in these signals might not be as apparent to humans as they are to the tinyML algorithms, which can classify and map them with different human behaviours. An implementation of such a technique can be used to develop a brain-machine interface that can help make neuroprosthetics.&nbsp;EOG is another example of a neuro signal that measures the corneo-retinal standing potential of the eye. In other words, it helps understand eye movements. A trained TinyML system can be used to accurately detect eye blinking and movements by feeding the signal to the input.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkwNjYzNTM5LWltYWdlOC5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="EOG-signals-detect-eye-blinking">The spikes that appear on the EOG are due to eye blinking. Source: tinyML YouTubeThen there’s EKG generated by the electrical impulses from the heart. For different people, the patterns of EKG are observed to be similar when looking at the same object. This can be used to predict if the person is telling the truth. In medical applications, signals can be used to check the functioning of the brain. A sample tone is played to the patient, and electric potential signals are observed. When the tone being played changes, the subconscious mind should ideally change the way it reacts, which should be evident in the electric potential signals.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkxNTU2NjQ2LWltYWdlMy5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="hackerhand-copies-gestures-EKG-signals">‘Hackerhand’, a robotic arm mimicking hand movements based on EKG signals. Source: tinyML YouTubeIt is also interesting to note that the signals are generated slightly before someone is about to take action, making it possible for tinyML systems to be able to predict the behaviour in advance. A similar fun project has been developed at Backyard Brains.Readers can participate in many more such projects or share ideas by visiting <a href="https://backyardbrains.com/" target="_blank">Backyard Brains</a>.<h2 dir="ltr">TinyML Open Education Initiative: tinyMLedu</h2>Over the past two decades, ML has been through a journey from a purely academic and theoretical discipline to a widely spread technology in use. It won’t be an understatement to say that technology has touched almost every industry and is now ubiquitous technology. It is expected that the interest in the field will only grow from here, at least in the near foreseeable future. Given its amazing potential in solving some of the greatest challenges faced by humanity, it is important that more people are introduced to technology in a systematic way.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkxNTk4OTQ2LWltYWdlNS5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="instructors-tinyML-harvard-google-edx">Instructors of the tinyML specialisationUnlike traditional ML, it is possible to run tinyML algorithms on low-cost and low-power embedded systems, which solves a major problem related to the unavailability of powerful hardware for learners. But the shortage of ML educators is still something that needs to be addressed.A joint initiative by Harvard and Google, developed as an academic and industry collaboration, aims to address the challenges by introducing tinyML to the masses with a Massive Open Online Course (MOOC) on edX.&nbsp;The courses that are a part of the tinyML specialisation go beyond teaching the students about the subject by diving deeper into the practical applications and industrial product development lifecycle. The next generation of students needs to understand the end-to-end full-stack development of tinyML projects to be able to gain a complete understanding of the subject.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkxNjIwMzE4LWltYWdlOS5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib" alt="tinyML-specialisation-course-structure">A diagram providing an overview of topics explored in tinyML specialisation. Source: [3]The tinyML specialisation, jointly developed by Harvard and Google, is a set of self-paced learning modules that can be taken from anywhere. The specialisation includes four courses:<ol><li dir="ltr">Introduction to tinyML:&nbsp;The first course covers the basics of ML and embedded systems. Everything from the concept to gathering data and training the algorithms is explained.</li><li dir="ltr">Applications of tinyML: The second course builds on the foundation by explaining some parts of the code behind the most widely used tinyML applications. It also introduces the learners to the principles of keyword spotting, visual wake words, anomaly detection, and dataset engineering.</li><li dir="ltr">Deploying tinyML: The third course teaches how code is written, optimised, and deployed for embedded systems. This is where microcontrollers are introduced, and students can purchase a kit for a nominal price (US$49.99) to get hands-on experience.</li><li dir="ltr">Scaling tinyML [Optional]: Once the learners are familiar with the design, development and deployment of tinyML, the final course covers the more advanced aspects related to producing tinyML solutions for the masses.</li></ol>Each course includes several activities such as collabs, hands-on labs, quizzes, readings, assignments, tests, and discussion-forum participation.The key challenges for students taking up the tinyML specialisation can be limited hardware accessibility and the requirement of being familiar with programming. To address the challenges associated with hardware accessibility, open-source emulation platforms like <a href="https://renode.io/" target="_blank">renode.io</a> from Antmicro are being tested to allow learners to try out their code without the hardware. The other challenge can be solved by platforms like <a href="https://www.wevolver.com/profile/edge.impulse" target="_blank">Edge Impulse</a>, which are lowering the barriers to enable people with little to no programming knowledge to implement tinyML solutions.Anyone with interest in tinyML can visit <a href="https://www.edx.org/professional-certificate/harvardx-tiny-machine-learning" target="_blank">tinyML Professional Certificate | edX</a> and enrol for the course for free. The course material is available on <a href="https://github.com/tinyMLx/courseware" target="_blank">GitHub</a>.<h2 dir="ltr" id="isPasted">Conclusion</h2>Though the project kits or MOOCs are not a complete solution to train professional neuroscience researchers or tinyML solution architects, they offer a great place for beginners to start. The kits and courses are designed in such a way that the students can engage in fun activities while they experiment and learn new stuff. This makes the experience memorable and develops an interest in the subject, which could lead more people to choose the specialised fields and make new discoveries.&nbsp;This article concludes our tinyML applications series.About tinyML FoundationWith its workshops, webinars, expert talks, research conferences, competitions, and a plethora of other events, tinyML Foundation enables students, researchers, and industry personnel to come together and share their experiences about the technology. It is the incredibly collaborative nature of the community that allows it to advance rapidly.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQzMjkxNjYyNjY4LWltYWdlMi5wbmciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 300px;" class="fr-fic fr-dib">The <a href="https://www.wevolver.com/article/tinyml-for-good-where-machine-learning-meets-edge-computing" target="_blank">introductory article</a> familiarised the readers with the concept of tinyML.The <a href="https://www.wevolver.com/article/tinyml" target="_blank">first article</a> explained some possibilities of tinyML applications in sustainable technologies.The <a href="https://www.wevolver.com/article/applications-of-tinyml-in-healthcare-for-a-safer-future/" target="_blank">second article</a> is about tinyML applications aiding healthcare and medical research.The <a href="https://www.wevolver.com/article/applications-of-tinyml-making-specialised-education-more-accessible" rel="noopener noreferrer" target="_blank">third and final article</a> shall cover the tinyML applications in pedagogy and education.<h2 dir="ltr">References</h2>[1] Marzullo TC, Gage GJ (2012) The SpikerBox: A Low Cost, Open-Source BioAmplifier for Increasing Public Participation in Neuroscience Inquiry. PLOS ONE 7(3): e30837. <a href="https://doi.org/10.1371/journal.pone.0030837" target="_blank">https://doi.org/10.1371/journal.pone.0030837</a>.[2] Gregory J. Gage, The Case for Neuroscience Research in the Classroom, Neuron, Volume 102, Issue 5, 2019, Pages 914-917, ISSN 0896-6273, <a href="https://doi.org/10.1016/j.neuron.2019.04.007" target="_blank">https://doi.org/10.1016/j.neuron.2019.04.007</a>.[3] Vijay J. Reddi et. al., Widening Access to Applied Machine Learning with TinyML, arXiv:2106.04008v2 [cs.LG], Jun 2021, [Online], Available from: <a href="https://arxiv.org/abs/2106.04008" target="_blank">https://arxiv.org/abs/2106.04008</a>.

In this article, we look at two tinyML projects for education. We show how Backyard Brains uses low-cost experiment kits to make neuroscience education more accessible. We also introduce our readers to a specialisation offered by Harvard & Google to help students learn tinyML like never before.

Applications of TinyML making specialised education more accessible

<h2 id="isPasted">Introduction</h2>The growing complexity of electronic systems is reshaping how engineers ensure reliability and compliance. Faster switching speeds and denser integration have made electromagnetic compatibility (EMC) one of the most critical design concerns, as noise issues discovered late in development often force costly redesigns. In addition, system-level demands, such as energy efficiency and accurate prediction of thermal behavior, are linked to EMC performance. To address these interrelated challenges, ROHM has established an end-to-end validation ecosystem. By combining accredited EMC measurement chambers, advanced motor bench systems, and web-based simulation tools, ROHM enables customers worldwide to implement effective countermeasures early, achieving greater design confidence, compliance, and efficiency.<h2>EMC Validation with In-House Anechoic Chambers</h2>Electromagnetic noise is one of the most pervasive risks in modern electronics. When left unchecked, it can lead to malfunction, system instability, and even regulatory non-compliance. For IC designers and system engineers, tackling noise at an early stage is critical.To support this, ROHM operates its own accredited EMC measurement facilities. Located at the Yokohama Technology Center, Japan, these facilities include:<ul><li>3-meter anechoic chamber for precision emissions measurements.</li><li>Automotive EMC chamber, which replicates real vehicle wiring harnesses and mounting conditions to test immunity and emissions in application-relevant environments.</li></ul><iframe width="640" height="360" src="https://www.youtube.com/embed/AoAEFJefN3s?&amp;wmode=opaque&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0">      </iframe>This in-house capability works strongly to the customer’s  advantage. With ROHM’s process, EMC countermeasures are designed during the IC development stage, allowing the customer to proceed with their designs with greater confidence. This significantly reduces the risk of late-stage redesigns and is one of the key advantages of ROHM’s robust EMC validation ecosystem.Table 1: Key EMC tests at ROHM<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1759849924697-image7.png" style="width:100%px" class="fr-fic fr-dib" alt="emc-test-rohm" />A notable example is the development of <a href="https://www.rohm.com/emarmour" target="_blank">ROHM’s EMARMOUR™</a> operational amplifiers, which achieved industry-leading immunity to electromagnetic interference (EMI). This success came from iterative testing in the anechoic chambers, where circuit proposals were measured, refined, and validated until breakthrough performance was achieved.<h2>Motor Bench Evaluation for Efficiency Testing</h2>While EMC focuses on noise and compliance, efficiency must also be evaluated for a reliable system design. In electric vehicles (EVs) and industrial drives, energy savings translate directly into reduced operating costs, longer range, and higher overall performance. Yet validating efficiency is complex because it requires testing not just individual devices, but entire drive systems.ROHM addresses this challenge with its motor bench evaluation environment, which reproduces real-world conditions for motors, gate drivers, and power devices. The setup includes a test motor and load motor configuration, regenerative converters, precision current and voltage sensors, and a dedicated control PC. This allows engineers to monitor efficiency and potential behavior under real operating conditions across a wide range of varying torque and rotational speed sequences.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1759850934678-image6.jpg" style="width:100%px" class="fr-fic fr-dib" alt="rohm-motor-efficiency-test" />Fig. 1: ROHM Motor Test Configuration DiagramIn comparative tests under <a href="https://en.wikipedia.org/wiki/Worldwide_Harmonised_Light_Vehicles_Test_Procedure" target="_blank">Worldwide Harmonized Light Vehicle Test Cycle (WLTC) Class 3b conditions</a>, inverters equipped with <a href="https://www.rohm.com/products/sic-power-devices/sic-mosfet#supportInfo" target="_blank">ROHM’s 4th Generation SiC MOSFETs</a> achieved up to 10% lower electricity consumption compared to those using conventional IGBTs. This confirms that high-efficiency operation can be achieved while  ensuring performance gains do not introduce excessive noise.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1759849963549-image2.jpg" style="width:100%px" class="fr-fic fr-dib" alt="rohm-motor-evaluation-test" />Fig. 2: ROHM Motor Evaluation Test Facilities<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1759849955110-image1.jpg" style="width:100%px" class="fr-fic fr-dib" alt="rohm-motor-bench-inverter-efficiency-comparision" />Fig. 3: ROHM’s motor bench demonstrates up to 10% higher efficiency with 4th Gen SiC MOSFETs versus IGBTs.By enabling these detailed system-level measurements, customers gain early insight into energy savings, and overall reliability before moving to costly prototyping or large-scale production.<h2>Simulation Tools for Virtual Validation</h2>Even with advanced EMC facilities and motor bench testing, designers often need to validate performance much earlier in the development cycle. Prototyping is expensive, and datasheets alone cannot capture the complex thermal and electrical interactions that occur in real-world systems. To help with this, ROHM offers the <a href="https://www.rohm.com/solution-simulator" target="_blank">ROHM Solution Simulator</a>, a free, web-based tool that enables engineers to evaluate devices and circuits under realistic application conditions. This tool is unique in the way it allows not only ICs but also entire circuits including discrete components such as transistors, diodes, resistors, and LEDs, and it also supports thermal design.Another key feature is its electrical-thermal coupled analysis. What once required a full day of modelling and computation can now be completed in under ten minutes, making it approximately 100 times faster than conventional methods. Designers can quickly examine junction temperatures, pin-level heating, and thermal interference between components, gaining insights before hardware is even built.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1759850012454-image4.png" style="width:100%px" class="fr-fic fr-dib" alt="rohm-solution-simulator-thermal-analysis" />Fig. 4: ROHM Solution Simulator reduces thermal validation time from a day to minutes.The simulator also fits seamlessly into existing workflows. Engineers can select a solution circuit, choose specific ROHM devices, run simulations, and even order samples directly. For more advanced system-level validation, results can be exported into the <a href="https://eda.sw.siemens.com/en-US/pcb/partquest/" target="_blank">Siemens EDA PartQuest</a> environment.<h2>Strengthening Competitiveness Through Validation</h2>When viewed together, ROHM’s validation facilities form a comprehensive ecosystem. Each contributes to a different but equally critical dimension of design reliability:<ul><li>State-of-the-art anechoic chambers ensure compliance with global EMC standards and protect against system malfunctions caused by noise.</li><li>Motor bench testing validates real-world efficiency and performance of drive systems in automotive and industrial applications.</li><li>Simulation tools accelerate development of the entire electrical circuit by identifying thermal, electrical, and heat-related issues before hardware prototyping.</li></ul>For customers, the combined benefits are clear: development cycles become shorter, reducing time-to-market. Risk is lowered because potential issues are identified earlier, preventing costly redesigns. Compliance confidence is strengthened across international markets, ensuring smoother certification processes. And system-level performance is optimized, translating into energy savings, safety, and reliability.Comprehensive design measures significantly enhance product reliability and safety while meeting customer expectations. This approach delivers exceptional value through both technical expertise and support systems, strengthening competitiveness in the global market.<h2>ROHM’s Application and Technical Solution Center in Europe</h2>While the tools and facilities discussed in this article are based at ROHM’s R&amp;D center in Japan, customers in Europe also benefit from local expertise through the European Application and Technical Solution Center (ATSC) in Willich, Germany. To support users in their development efforts, the EU support team offers services that contribute to the quality of the customer's end product. The facilities in Germany are not only meant for low-voltage IC products: Through a modern lab ROHM also provides support for power devices (IGBTs, SiC MOSFETs) with voltage classes up to 2 kV since 2018.     <img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1759850018173-image3.jpg" style="width:100%px" class="fr-fic fr-dib" alt="rohm-atsc-europe-engineers" />Fig. 5: At ROHM’s ATSC in Europe, engineers collaborate directly with customers on circuit evaluation and design-in support.The ATSC focuses on supporting engineers during their design-in phase, providing application boards, reference designs, and hands-on technical collaboration. By working closely with local development teams, the ATSC ensures that European customers receive support for integrating ROHM’s analog ICs, power devices, and system solutions. This way, ROHM combines cutting-edge R&amp;D infrastructure with regional engineering support, delivering a balanced approach that strengthens customer competitiveness worldwide.<h2>Conclusion</h2>EMI, energy efficiency, and thermal management are often invisible yet decisive for reliable, compliant electronics. If overlooked, they can cause redesigns, certification delays, and performance losses. ROHM’s R&amp;D facilities employ anechoic chambers, motor bench evaluation, and simulation tools as part of a preventive validation ecosystem that helps customers detect issues early, apply effective countermeasures, and deliver designs that are globally compliant, efficient, safe, and reliable.Explore further: <a href="https://www.rohm.com/company/about/stories-of-manufacturing/emc" target="_blank">Endless Struggle Against Invisible Noise | ROHM</a>

ROHM's R&D facilities integrate EMC testing, motor bench evaluation, and advanced simulation to tackle electromagnetic noise, efficiency, and thermal challenges. Together, they create a preventive validation ecosystem that accelerates development and ensures reliable, compliant electronic systems.

Ensuring EMC Through A Validation Ecosystem: Anechoic Chambers, Motor Bench, and Advanced Simulation

To celebrate Global Engineering Day, we’re looking at what it’s like to work as a truly global engineer, collaborating with international colleagues from all over the world to advance software development.Read on to learn about the career paths of Claire Dross, Head of Static Analysis at AdaCore, based in our Toulouse office in France, and Tõnu Näks, Deputy Head of Toolchain and Managing Director of AdaCore’s Estonia branch in Tallinn.<h3 dir="ltr">What's your educational background?</h3>Claire: I studied Computer Science at the Ecole Polytechnique, a French Engineering School. The degree there is equivalent to a Master's elsewhere.In my last year of Engineering School, we each chose a specialization. I was studying part-time at a university in Paris for a technology research degree called MPRI -&nbsp;Master Parisien de Recherche en Informatique. Someone from AdaCore had posted an internship proposal on a board at the university and I found it unique because this university is a research university, so usually you wouldn’t see internships posted there. I interviewed both for this internship which included the opportunity to do a PhD, and for another opportunity with Dassault Systèmes. AdaCore sounded like the most interesting one with complex, challenging research to work on with very smart people.During my first three years at AdaCore, I completed my PhD on Generic Decision Procedures for Axiomatic First-Order Theories, which was a subject that was relevant to my work here. After finishing my PhD in April 2014, I continued at AdaCore as a software engineer.Tonu: I studied at the Tallinn University of Technology, graduating with an MSc in Systems and Software Engineering in 1998.My research topic was modeling time constraints using UML/SysML models. I was fascinated by the idea of mixing the models of real-world objects with system requirements and then doing some magic to get a computer program out of it. This got me involved in model-based development.I worked alongside my studies, starting out as a C/C++ programmer in an industrial automation startup in 1990, and later becoming a project manager at the university. While working on my master’s thesis in 1997, I was assigned a research project to create a UML tool for describing system behavior with time constraints and doing formal analysis on the consistency of those constraints. This led to me and two of my colleagues founding a startup called IB Krates to commercialize this tool.<h3 dir="ltr">How has your career progressed at AdaCore?</h3>Claire: When I was doing my PhD, I was naturally very focused on its subject, which was really technical. Gradually over time, I began to look at SPARK as not just a technology but as a product, and my work shifted to involve much more development than research.As the years passed, I was given more responsibility, working on projects like the SPARK roadmap. Thanks to this experience, I was offered the role of Team Lead for SPARK. This was my first experience with management.I had also been building my skills in this area and had attended AdaCore’s internal management training course, so all this contributed to me becoming the right person to lead the team. I really enjoy being a manager, it’s fantastic. I never get bored with helping people prioritize their workload, listening to their ideas, and generally just being present to support them when projects become challenging.In July 2024, I was promoted to Head of the Static Analysis Unit. By this time, I had been working in SPARK for over 10 years. It felt like a good time to broaden my understanding of our technologies to learn more about our activities in other Static Analysis sub-teams. I’m enjoying learning more about our work with Dynamic Analysis and have just started a project in the Dynamic Analysis Unit. I’m always able to find a new intellectual challenge here.Tonu: I started working with AdaCore as a partner in 2009 when AdaCore joined the GeneAuto research project. GeneAuto was a consortium led by Continental and driven by requirements from Airbus, Thales, and Barco. The initial GeneAuto project ended up with a prototype of a Simulink → C translator written in Java. Our first joint project with AdaCore was the development of an Ada printer for this prototype as a proof of concept. This was also my first real encounter with the Ada language.Following a series of joint projects, the software tools group from IB Krates joined AdaCore in 2018. I became the head of the company’s Estonian branch and a member of our joint tool’s Lead Team, responsible for coordinating its development and defining its architecture.Joining AdaCore felt like a natural transition. We had good synergy practically working as one team years before the merger. When we formally joined the company, the reception was warm and people were extremely welcoming.Following this project, I moved to the Toolchain unit and became Deputy Head of Toolchain. Looking to apply my extensive experience in project management and keep my engineering skills fresh, I took the position of Front-end Team Lead at the beginning of 2024 and became Rust Team Lead later that year.<h3 dir="ltr">Can you tell us about your work with SPARK at AdaCore and how your work with the language has evolved over time?</h3>Claire: When I first joined AdaCore, SPARK was still a really novel technology and certainly more research-focused than development-focused. Over the years, this has changed a lot - the technology is now much more efficient and user-friendly. As customer demand has increased, it has grown into one of our core products. When we talk about Ada technology, we talk about SPARK too.<h3 dir="ltr">Can you tell us about the Static Analysis Unit, your current projects and its plans for the future?</h3>Claire: The Static Analysis Unit is made up of several subteams - the Libadalang team, the GNAT Static Analysis team, and the SPARK team:<ul><li dir="ltr">The Libadalang team is creating a frontend to analyse source code in Ada which is used by our internal IDE and GNATcheck teams to check conformance and compliance, for instance. Our Libadalang engineers are working on a way to reformat Ada code automatically and add “quick fixes” to tool messages to correct elements in the code.</li><li dir="ltr">The GNAT Static Analysis team is working to improve static analysis with a focus on security, for example detecting CWEs (Common Weakness Enumerations). They are also working on integrating static analysis tools developed at AdaCore in a single analysis suite. This year, they are integrating gnatmetric, which is a tool for computing various program metrics.</li><li dir="ltr">We are always working to improve SPARK's usability. This includes increasing the subset of language features it supports and adding brand-new features. We integrate support for our customers’ features within SPARK. Finally, we create new materials and resources to help programmers learn SPARK on&nbsp;<a href="http://learn.adacore.com/">learn.adacore.com</a> and to make it easier for them to annotate their code.</li></ul><h3>Can you tell us about the Toolchain Unit, your current projects and its plans for the future?</h3>Tonu: The toolchain unit provides Adacore's core technologies: compilers, debuggers, various helper tools and libraries. The unit consists of 9 teams and over 45 teammates.<ul><li dir="ltr">Our bread and butter is the Ada compiler and its ports for specific processors.</li><li dir="ltr">We’re always working on new developments for the Ada language, defining its scope and future roadmap.</li><li dir="ltr">We also provide dedicated ports for other languages – C/C++, Rust and tools for interfacing those languages with Ada.</li><li dir="ltr">Rust has been a new addition to our product offering within the last few years. It’s exciting to see how this new product is evolving and taking off.</li></ul>Personally, what motivates me at work is ensuring team members work on tasks they know best and keep processes effective. I find it really fulfilling to work on new developments in our technology and deliver the final product to our customers.<h3 dir="ltr">How do you collaborate with teams based in different locations at AdaCore?</h3>Claire: Across the Static Analysis Unit, we have representatives in many different locations. Several can be found in our offices in Paris, Grenoble, or Toulouse where I am based. But others are very dispersed including members based across vastly different timezones such as Korea and the USA.Though we try to remain connected to Slack throughout our working days to make it easier to chat and come up with technical solutions together when we need to, we also find it important to prioritize having a few regular meetings for the team. We have a weekly standup for regular updates on what everyone is working on, a monthly call for general alignment on technical goals and around 2 - 4 other meetings to share knowledge on specific topics or insights gathered from research conferences. These updates are really important to help the team work well together.Tonu: In the Toolchain Unit, we have team members from all over the world across multiple time zones, including Estonia, France, the UK, and both the West coast and East coast of the US.We organize meetings so that everyone can attend as close as possible to their normal working hours. The ten-hour time difference between the farthest time zones makes finding a reasonable time difficult, so we stick to one full team meeting per week. Most of the time we rely on Google Meetings in smaller groups, email, Gitlab messages, and Slack to collaborate. It’s not easy to organize face-to-face meetings, but we aim to get the whole team together at least once a year.<h3 dir="ltr">What would you say to someone interested in joining AdaCore?</h3>Claire: We are doing interesting work in technology and research at AdaCore. There are always technical challenges to solve to improve our products, and there is the opportunity to interact with really smart people. Collaboration is really important here — everyone wants to see the team succeed, and we all get on well together. I would say that the team and the technology we work on are the two main attractions for me of working at AdaCore.Tonu: Even if we are not a big company, we have expertise in many different fields. We have a mix of top language experts - some of whom come from the original teams who developed the Ada language - as well as experts in compiler technology, formal analysis, and processor architectures.Here, people are always willing to share their knowledge and you can speak to anyone directly, regardless of seniority. It is rewarding to hear what people are doing and, from a cultural viewpoint, I enjoy working with people from different countries.<h3 dir="ltr">What do you value most about working at AdaCore?</h3>Claire: My colleagues' expertise and the quality of work here are really high. This is important to me, and it motivates many people to work at AdaCore.Another thing worth mentioning is that while working at AdaCore, I have never felt singled out for being a woman - it has never been a topic of conversation.Career development and the freedom to create your own path are valued more here than at other companies. You never feel replaceable like you might at another company, and that’s a good thing. Each person is valued for what they can achieve, and not everybody is the same.Tonu: The first thing that struck me when I started working with AdaCore was the openness. I enjoyed seeing how the mindset of sharing knowledge simplifies working processes. Being able to book the President’s office as a meeting room in Paris shows how little emphasis there is on hierarchy here.I came from a very small company before, where it often happened that only one person had knowledge on a problem at hand. Since joining AdaCore, I have never had another occasion where I was stuck on such a specific problem and there was no one to ask for help. Here, you can always depend on somebody to ask who can give you some pointers.

To celebrate Global Engineering Day, we're looking at what it's like to work as a truly global engineer, collaborating with international colleagues from all over the world to advance software development.

Building the Future: My Path from Software Research to Leadership

There’s been a lot of buzz over bipedal robots in recent years.Companies like Boston Dynamics, Agility Robotics, Unitree and others have developed powerful algorithms and leading edge hardware to make what was once science fiction a reality. There are now an increasing number of walking (and sometimes talking) upright robots that get around on two legs. These tend to be humanoids, but they are bipedal.There’s a certain cool factor to seeing robots that walk like people. But the push for bipedal robots is also driven by infrastructure: Factories and other settings where such devices might be deployed have been built for people. So robots that can walk and are roughly human size can work in such spaces without infrastructure changes.“With the automobile, we had to build roads,” said Jonathan Hurst, Chief Technology Officer of Agility Robotics, in an explanatory video. “With legged robots we’ve already built the infrastructure. Legged robots are going to change the world as much as the automobile did.”As the saying goes, time will tell. But before we proceed, it’s worth mentioning that bipedal doesn’t necessarily mean humanoid.“A humanoid typically mimics the human form – so it has a head, torso, arms and legs,” explains Luke Corbeth, InDro’s Head of R&amp;D Sales.“Bipedal simply means it walks on two legs, but it doesn’t need to look human. So while most humanoids are bipedal, not all bipedal robots are humanoids.”Below: Agility’s Cassie – a bipedal, non-humanoid robot. Immense R&amp;D went into developing this machine, with many of the lessons learned applied to its current Digit humanoid<iframe width="640" height="360" src="https://www.youtube.com/embed/DdojWYOK0Nc??si=WL0wpUwIkrD8hMN2&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</iframe><h3 id="isPasted">The Bipedal-Humanoid Connection</h3>As the video illustrated, bipedal robots aren’t necessarily humanoid (though they can be). But since the non-humanoid versions don’t have arms or manipulators, what are the use-cases?First off, they’re critical tools in the R&amp;D space. Before any company attempts a full-blown humanoid, it needs to perfect locomotion, balance and gait. That, of course, requires intensive hardware and software development. Many in the research space don’t have the time or resources to build from scratch. By starting with an existing bipedal robot they can rapidly start working on improving algorithms, adding autonomy stacks, machine vision, etc.“Achieving stable and efficient bipedal locomotion is really the first critical milestone – so it involves doing things like balancing the gait, being very energy efficient and knowing how to recover from various disturbances,” says Corbeth. “But once that’s dialed in, you can build advanced capabilities on top of it, things like manipulation or autonomous navigation. So starting with a bipedal platform can help clients achieve their ultimate goals much sooner”Not surprisingly, clients for bipedal, non-humanoid platforms are often in the R&amp;D space.“For anyone specifically researching bipedal locomotion, these devices make sense,” he adds. “It allows them to really focus on research and control, computer vision and AI applications. It’s an accessible platform for labs to really accelerate their work on humanoids.”In other words, perfecting a bipedal platform is critical in the development of full humanoid robots.&nbsp;<h3>Rise of the Humanoids</h3>We recently took a dive into humanoids <a href="https://indrorobotics.ca/the-rise-of-the-humanoid-robots/" target="_blank">here</a>.To recap briefly, humanoids are on the rise because their form factor allows them to integrate with existing infrastructure. With arms and manipulators/end effectors, they can carry out many of the tasks that humans perform. Bipedal design means they can climb stairs or navigate other obstacles. Even humanoids with wheels or tracks can now carry out these manoeuvres.“Humanoid robots have become one of the most frontier topics in the field of robot research [<a href="https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cim2.12080#cim212080-bib-0001" data-tab="pane-pcw-references" target="_blank">1</a>],” states <a href="https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cim2.12080" target="_blank">this research paper</a>. “Owing to the human-like structures and strong environmental adaptability [<a href="https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cim2.12080#cim212080-bib-0002" data-tab="pane-pcw-references" target="_blank">2</a>], biped robots can directly operate the tools and vehicles used by humans, showing wide application prospects in fields such as home service, industrial manufacturing and environmental detection [<a href="https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cim2.12080#cim212080-bib-0003" data-tab="pane-pcw-references" target="_blank">3</a>]…Ongoing research…shows great potential in human–robot collaboration and autonomous operation [<a href="https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cim2.12080#cim212080-bib-0006" data-tab="pane-pcw-references" target="_blank">6</a>].”Many of the tasks bipedal robots will eventually carry out aren’t even fully known yet, as these new commercial products are very much – despite some really impressive machines – in the early stages of adoption and deployment. It’s a safe bet that every company currently selling bipedal or humanoid robots is hard at work in the lab on the next generation. There’s a lot of development in the pipeline.“Better battery life is kind of on everyone’s wishlist – the runtime of a humanoid or bipedal robot simply isn’t as long as some of the traditional wheeled or track systems. There are also other things like faster and safer locomotion and, of course, dexterous hands,” says Corbeth.We hit up AI for some thoughts on where these machines are going. It concurs that the full benefits of bipedal robots have yet to be realised.“While bipedal robots offer unique advantages, it’s worth noting that they are still under development, and their efficiency and practicality in certain applications are still being evaluated.&nbsp;For example, wheeled robots might be more energy-efficient for certain tasks on flat surfaces.&nbsp;However, for navigating complex, unstructured environments and interacting with human-scale tools and spaces, bipedal robots offer a promising solution.”In addition to humanoids, InDro now offers a strictly bipedal, non-humanoid platform primarily for R&amp;D. As with most platforms, our engineers are currently working on expanding its capabilities to enable it more fully for R&amp;D and industrial clients. We will soon be integrating <a href="https://indrorobotics.ca/the-new-indro-command-module-amazing-power-in-a-tiny-package/" target="_blank">InDro Cortex</a>, a brain-box that enables everything from remote teleoperation and sensor integration to fully autonomous and/or easily programmable missions.“We’re looking to add our Cortex solution – the hardware and the software and the autonomy – to our humanoids and bipedal robots,” says Corbeth. “We see opportunities to integrate advanced autonomy, teleoperation and perception pipelines into this equipment…making them a turnkey solution for advanced humanoid development and real-world testing.”Below: A great video explanation of the bipedal advantage, followed by the bipedal robot InDro now has available<iframe width="640" height="360" src="https://www.youtube.com/embed/mHmmySGdaoM??si=_YUtIonJpOBhBYy3&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&nbsp;&nbsp;</iframe><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1752856176771-Biped+6.jpg" style="width: 100%px;" class="fr-fic fr-dib" alt="Biped Robot"><h3 id="isPasted">InDro's Take</h3>Bipedal robots are the precursor to full-blown humanoids. Not only does the humanoid form factor work well in existing infrastructure, they’re seen by many as the ideal collaborative robots, or co-bots. People seem more at ease with something that looks vaguely human (with the notable exception of Terminator’s T800).“The human form factor is just intuitive for people to interact with – and the similar size helps them use human tools and really fit in well in workspaces,” says Corbeth. “Some may argue as well they also kind of build trust, which is crucial for collaborative robots operating around or with people.”And for those in the R&amp;D space looking for a bipedal-only platform, we’ve got you covered.We look forward to sharing more about our bipedal and humanoid robots in future, particularly once we’ve supercharged them with InDro Cortex. If you’re curious to learn more, <a href="https://indrorobotics.ca/thebiped/" target="_blank" rel="noopener noreferrer">checkout the biped platform here</a>.

Exploring the Impact of Advanced Bipedal Robotics

Bipedal Robots Step Into The Scene

Research and Development product leaders like you and me drive innovation. We turn ideas and problems into safe and manufacturable products by exploring new technologies, materials, and processes to meet technical needs and customer expectations.

Research Robots

Engineers Wiki.

Most Asked Questions.

Scanning Electron Microscopy: A Comprehensive Guide

Applications of TinyML making specialised education more accessible

ORGANIZATIONS.

SHAPING THE INDUSTRY.

University of Cambridge

Technical University of Munich

Rensselaer Polytechnic Institute

AKIRA Science

Trossen Robotics

TAGGED WITH research platforms