When ChatGPT or Gemini give what seems to be an expert response to your burning questions, you may not realize how much information it relies on to give that reply. Like other popular generative artificial intelligence (AI) models, these chatbots rely on backbone systems called foundation models that train on billions, or even trillions, of data points.In a similar vein, engineers are hoping to build foundation models that train a range of robots on new skills like picking up, moving, and putting down objects in places like homes and factories. The problem is that it’s difficult to collect and transfer instructional data across robotic systems. You could teach your system by teleoperating the hardware step-by-step using technology like virtual reality (VR), but that can be time-consuming. Training on videos from the internet is less instructive, since the clips don’t provide a step-by-step, specialized task walk-through for particular robots. A simulation-driven approach called “PhysicsGen” from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Robotics and AI Institute customizes robot training data to help robots find the most efficient movements for a task. The system can multiply a few dozen VR demonstrations into nearly 3,000 simulations per machine. These high-quality instructions are then mapped to the precise configurations of mechanical companions like robotic arms and hands.&nbsp;PhysicsGen creates data that generalize to specific robots and condition via a three-step process. First, a VR headset tracks how humans manipulate objects like blocks using their hands. These interactions are mapped in a 3D physics simulator at the same time, visualizing the key points of our hands as small spheres that mirror our gestures. For example, if you flipped a toy over, you’d see 3D shapes representing different parts of your hands rotating a virtual version of that object. The pipeline then remaps these points to a 3D model of the setup of a specific machine (like a robotic arm), moving them to the precise “joints” where a system twists and turns. Finally, PhysicsGen uses trajectory optimization — essentially simulating the most efficient motions to complete a task — so the robot knows the best ways to do things like repositioning a box.Each simulation is a detailed training data point that walks a robot through potential ways to handle objects. When implemented into a policy (or the action plan that the robot follows), the machine has a variety of ways to approach a task, and can try out different motions if one doesn’t work.“We’re creating robot-specific data without needing humans to re-record specialized demonstrations for each machine,” says Lujie Yang, an MIT PhD student in electrical engineering and computer science and CSAIL affiliate who is the lead author of a new&nbsp;<a href="https://arxiv.org/abs/2502.20382">paper</a> introducing the project. “We’re scaling up the data in an autonomous and efficient way, making task instructions useful to a wider range of machines.” Generating so many instructional trajectories for robots could eventually help engineers build a massive dataset to guide machines like robotic arms and dexterous hands. For example, the pipeline might help two robotic arms collaborate on picking up warehouse items and placing them in the right boxes for deliveries. The system may also guide two robots to work together in a household on tasks like putting away cups. PhysicsGen’s potential also extends to converting data designed for older robots or different environments into useful instructions for new machines. “Despite being collected for a specific type of robot, we can revive these prior datasets to make them more generally useful,” adds Yang.<h2 dir="ltr">Addition by multiplication</h2>PhysicsGen turned just 24 human demonstrations into thousands of simulated ones, helping both digital and real-world robots reorient objects. Yang and her colleagues first tested their pipeline in a virtual experiment where a floating robotic hand needed to rotate a block into a target position. The digital robot executed the task at a rate of 81 percent accuracy by training on PhysicGen’s massive dataset, a 60 percent improvement from a baseline that only learned from human demonstrations. The researchers also found that PhysicsGen could improve how virtual robotic arms collaborate to manipulate objects. Their system created extra training data that helped two pairs of robots successfully accomplish tasks as much as 30 percent more often than a purely human-taught baseline.In an experiment with a pair of real-world robotic arms, the researchers observed similar improvements as the machines teamed up to flip a large box into its designated position. When the robots deviated from the intended trajectory or mishandled the object, they were able to recover mid-task by referencing alternative trajectories from their library of instructional data. Senior author Russ Tedrake, who is the Toyota Professor of Electrical Engineering and Computer Science, Aeronautics and Astronautics, and Mechanical Engineering at MIT, adds that this imitation-guided data generation technique combines the strengths of human demonstration with the power of robot motion planning algorithms. “Even a single demonstration from a human can make the motion planning problem much easier,” says Tedrake, who is also a senior vice president of large behavior models at the Toyota Research Institute and CSAIL principal investigator. “In the future, perhaps the foundation models will be able to provide this information, and this type of data generation technique will provide a type of post-training recipe for that model.”<h2 dir="ltr">The future of PhysicsGen</h2>Soon, PhysicsGen may be extended to a new frontier: diversifying the tasks a machine can execute.“We’d like to use PhysicsGen to teach a robot to pour water when it’s only been trained to put away dishes, for example,” says Yang. “Our pipeline doesn’t just generate dynamically feasible motions for familiar tasks; it also has the potential of creating a diverse library of physical interactions that we believe can serve as building blocks for accomplishing entirely new tasks a human hasn’t demonstrated.”Creating lots of widely applicable training data may eventually help build a foundation model for robots, though MIT researchers caution that this is a somewhat distant goal. The CSAIL-led team is investigating how PhysicsGen can harness vast, unstructured resources&nbsp;— like internet videos — as seeds for simulation. The goal: transform everyday visual content into rich, robot-ready data that could teach machines to perform tasks no one explicitly showed them.Yang and her colleagues also aim to make PhysicsGen even more useful for robots with diverse shapes and configurations in the future. To make that happen, they plan to leverage datasets with demonstrations of real robots, capturing how robotic joints move instead of human ones.The researchers also plan to incorporate reinforcement learning, where an AI system learns by trial and error, to make PhysicsGen expand its dataset beyond human-provided examples. They may augment their pipeline with advanced perception techniques to help a robot perceive and interpret their environment visually, allowing the machine to analyze and adapt to the complexities of the physical world.For now, PhysicsGen shows how AI can help us teach different robots to manipulate objects within the same category, particularly rigid ones. The pipeline may soon help robots find the best ways to handle soft items (like fruits) and deformable ones (like clay), but those interactions aren’t easy to simulate yet.Yang and Tedrake wrote the paper with two CSAIL colleagues: co-lead author and MIT PhD student Hyung Ju “Terry” Suh SM ’22 and MIT PhD student Bernhard Paus Græsdal. Robotics and AI Institute researchers Tong Zhao ’22, MEng ’23, Tarik Kelestemur, Jiuguang Wang, and Tao Pang PhD ’23 are also authors. Their work was supported by the Robotics and AI Institute and Amazon.

PhysicsGen can multiply a few dozen virtual reality demonstrations into nearly 3,000 simulations per machine for mechanical companions like robotic arms and hands. Image designed by Alex Shipps/MIT CSAIL, using photos from the researchers.

The PhysicsGen system, developed by MIT researchers, helps robots handle items in homes and factories by tailoring training data to a particular machine.

Simulation-based pipeline tailors training data for dexterous robots

In order to advance the convenience of data collection for humanoid robots, we refer to other solutions to do the adaptation development and open source.Github：<a tabindex="0" href="https://www.youtube.com/redirect?event=video_description&redir_token=QUFFLUhqbGEtVm9yOHhmdlZEVFpnUTNSUEdLdzJCZG9XUXxBQ3Jtc0tsTmEweUk5aWQ4LWFvVTRQcGdUb182R2F2dFM3cENCb1lUREJSbnhwTlgwN2ptR1pSRlAwakxBM284QWZYc01JTWhYektEYUZ3ZGhXenlEbVAwWkgtXzN6c1QybV9xNkNlS2tfS3JqbzhjYWJ2UGtDVQ&q=https%3A%2F%2Fgithub.com%2Funitreerobotics%2Favp_teleoperate&v=pNjr2f_XHoo" rel="nofollow" target="_blank" data-immersive-translate-walked="d184844b-18ce-4d8f-9392-ad8f851f3836">https://github.com/unitreerobotics/av...</a>Kinect：<a tabindex="0" href="https://www.youtube.com/redirect?event=video_description&redir_token=QUFFLUhqa25pczNWM3NDT2RoaXpVb3o3MWFfVTBtS2lnUXxBQ3Jtc0trN0JLVlg5ZVRxZXdpcUhPXzFkTzZXNlp4SEtkTms2aTRCZUZhc2o5cGVONzFNdHVRemd5SUFDSVhWUlgwbzlXaTlwVDF3c1p0SE5nQXBnYy1hd3NuamxlYzM1TW1NSGdVMThjXzIxZlRKeEF3cXJUNA&q=https%3A%2F%2Fgithub.com%2Funitreerobotics%2Fkinect_teleoperate&v=pNjr2f_XHoo" rel="nofollow" target="_blank" data-immersive-translate-walked="d184844b-18ce-4d8f-9392-ad8f851f3836">https://github.com/unitreerobotics/ki...</a> Official Website: www.unitree.com&nbsp;Twitter: twitter.com/UnitreeRobotics&nbsp;LinkedIn: www.linkedin.com/company/unitreerobotics

In order to advance the convenience of data collection for humanoid robots, we refer to other solutions to do the adaptation development and open source.

Open Source Unitree First View Teleoperation for Humanoid Robots

Photoneo, now part of Zebra Technologies and a global leader in high-resolution 3D vision systems, today announced the launch of its best-in-class <a href="https://ai.photoneo.com/best-3d-scanner" target="_blank" rel="noopener noreferrer">PhoXi 3D Scanner Gen3</a>.&nbsp;Engineered for the most accuracy-critical applications across various industries, this top-of-the-line 3D scanner introduces a powerful Blue Laser technology along its integrated color camera, delivering unparalleled precision and reliability in a durable, feather-light carbon body.The PhoXi 3D Scanner Gen3 represents the new generation of the world’s most robust 3D scanner with advanced capabilities that allow for the detection of hairline cracks, micro-edges, and subtle assembly flaws with&nbsp;60% more 3D data points,&nbsp;without compromising its robust scanning range. Gen3 also provides ultra-clear scans, empowering AI-powered inspection, tighter quality control and high-accuracy VGR applications."The PhoXi 3D Scanner Gen3 defines new standards in 3D scanning accuracy,"&nbsp;said Svorad Stolc, CTO of Photoneo.&nbsp;"We've listened to our customers' needs for higher accuracy, better material handling, and unmatched reliability, and this new scanner delivers on all fronts. Its blue laser technology, integrated color capture, and autonomous maintenance features will redefine how businesses approach quality control, logistics, and automation."Key Innovations and Benefits:<ul><li>Top-Notch Color Data:&nbsp;Featuring an&nbsp;integrated RGB camera, the Gen3 captures both&nbsp;3D data and color texture simultaneously, simplifying tasks like verifying labels, finishes, or material blends for enhanced quality assurance, sorting, and texture analysis.</li><li>Unrivaled Surface Versatility:&nbsp;This scanner effortlessly handles challenging surfaces, including black plastics, reflective metals, rubber, and matte finishes, achieving up to&nbsp;2.5 times better 3D data completeness&nbsp;on complex materials, eliminating wasted time and rescans.</li><li>Exceptional Range and Detail:&nbsp;Gen3 is fully calibrated for distances up to 4 meters, with&nbsp;robust accuracy up to 6 meters for larger logistics tasks, ensuring trustworthy 3D vision for both close-up inspections and long-range object detection.</li><li>Double the Speed, No Trade-Offs:&nbsp;The Gen3 supports&nbsp;advanced parallel scanning&nbsp;using both blue and red laser variants concurrently, with no interference between wavelengths. This dual-channel architecture dramatically&nbsp;increases scanning throughput and data density&nbsp;without compromise.</li><li>Zero Maintenance:&nbsp;With autonomous maintenance capabilities, the Gen3 eliminates the need for special marker patterns, physical access, or service calls. Users can&nbsp;auto-maintain the device with a single click, ensuring submillimeter accuracy that doesn’t drift over time and keeping production lines always running.</li></ul>Dependable, High-Precision Results:<ul><li>5.1 MP 3D resolution</li><li>60% more 3D points</li><li>8 MP RGB data</li><li>Operates in any lighting conditions, even direct sunlight</li><li>Up to 2.5× better scan completeness&nbsp;on difficult materials</li><li>20 dB higher dynamic range</li><li>Any distance from 0.3 m to 6 m</li><li>Autonomous Maintenance:&nbsp;No marker patterns, no tuning, no hassle</li></ul>For press inquiries, interviews, or to schedule a private demo session, please contact: Inna Imas, <a href="mailto:Inna.imas@zebra.com" target="_blank">Inna.imas@zebra.com</a>, <a href="mailto:Photoneo-marketing@zebra.com" target="_blank">Photoneo-marketing@zebra.com</a> About PhotoneoPhotoneo, now part of Zebra Technologies, is redefining industrial automation with advanced 3D vision and robotic intelligence. Our industry-leading technology empowers businesses in automotive, logistics, e-commerce and other sectors to achieve fully intelligent dynamic automation, with precision, efficiency, and scalability. Photoneo is a leading provider of industrial 3D vision, AI-powered automation solutions, and robotic intelligence software. Since its foundation in 2013, the company’s mission has been to give vision and intelligence to robots all over the world so that they can see and understand. The goal is to automate monotonous and risky tasks by deploying vision-guided robots. Based on a patented 3D technology, Photoneo developed the world’s highest-resolution and highest-accuracy 3D camera, opening up new perspectives on automation. <a href="http://www.photoneo.com/" target="_blank">www.photoneo.com</a>

Setting a New Standard for High-Resolution Industrial 3D Scanning

Photoneo Launches PhoXi 3D Scanner Gen3

The collaboration between AI and robotics enables robots to implement tasks more effectively and handle complications previously beyond their capacities.

Empowering Robotics with Axelera AI: Intelligent Solutions for Advanced Automation

In this episode, we explore two cutting-edge environmental robots developed by ETH Zurich students: MONKEE, a tree-climbing robot for canopy research, and ReefRanger, an autonomous underwater robot that feeds and monitors corals.

Podcast: Tree-Climbing and Reef-Restoring Robots

<h2 dir="ltr" id="isPasted">Introduction</h2>Service robotics is a fast-growing field, with intelligent, adaptive, and autonomous systems becoming increasingly prevalent across industries. As these robots become more sophisticated, engineers face more complex challenges when it comes to achieving real-time perception, precise motion control, and environmental awareness. TDK Corporation, a leading Japanese electronics company, has developed a comprehensive sensor ecosystem to address these challenges. The result is a modular and scalable platform for next-generation robots.TDK’s sensor ecosystem is integrated with the ROS 1 and ROS 2 framework, and is a unified solution for robotic developers. Drawing inspiration from the sensory capabilities often imagined in anime and manga, this technology brings us closer to creating robots that are highly perceptive and responsive. By combining cutting-edge sensor technologies and flexible algorithms, TDK is leading the way for a new era of intelligent robotics that can interact with humans and their environment. &nbsp;<h2 dir="ltr">The TDK Sensor Ecosystem: A Comprehensive Robotics Solution</h2>The core of TDK’s ecosystem is a collection of modular sensors. Each sensor is engineered to perform a specific function, yet they are designed to work together to improve robot performance.Motion sensing is handled by 6-axis and 9-axis MEMS-based Inertial Measurement Units (IMUs), like the ICM-42688P. These units provide the high-precision tracking necessary for balance, navigation, and posture correction. Environmental factors are monitored through gas, humidity, and barometric pressure sensors. For example, the IPC-10111 capacitive barometric pressure sensor detects changes in air quality and altitude, which is particularly valuable in industrial contexts.Robots also gain a sense of touch and proximity through capacitive and piezoelectric touch sensors. These components allow machines to detect objects and interact safely with humans by responding with tactile feedback that makes interactions more intuitive. Additionally, a layer of acoustic and spatial awareness is provided by digital microphones (like the ICS-43434) and ultrasonic Time-of-Flight sensors (including CH101 and CH201). These components enable functions like obstacle avoidance and voice interaction.1This comprehensive sensor suite enables flexible hardware configurations, which allows developers to customize robots for specific tasks. The plug-and-play integration with ROS also reduces development time and improves cross-compatibility between components. TDK's multi-sensor fusion techniques merge data from different types of sensors to give robots a holistic perception of their environment, like the multi-sensory awareness often portrayed in the futuristic robots of pop culture.<h2 dir="ltr">Motion Sensing and Adaptive Locomotion</h2>TDK’s IMUs play a very important role in robotic motion control by enabling precise movement and posture management. These sensors allow robots to move smoothly, maintain balance, and even prevent falls, particularly in humanoid designs.When IMUs are integrated with other sensing technology, like LiDAR and vision-based SLAM (Simultaneous Localization and Mapping), it improves robotic positioning and mapping. This sensor fusion approach allows robots to navigate complex environments with greater accuracy and adaptability.Robotic systems benefit from advanced algorithms like Kalman filtering, which compensates for sensor drift and ensures fluid transitions between movements. In AI-enhanced applications, IMUs also support predictive trajectory planning, so that robots can adapt to chaning environments in real time. These capabilities are demonstrated in robots like ANYmal, developed by ANYbotics (a TDK Ventures portfolio company), which uses TDK sensor tech to operate autonomously in industrial settings and cluttered environments.2These capabilities are especially apparent in robots like ANYmal, developed by ANYbotics, a company backed by TDK Ventures. ANYmal demonstrates advanced locomotion and navigation in industrial environments and is a real-world application for TDK’s sensor technologies.<h2 dir="ltr">Environmental Awareness: Enhancing Robot Sensing Capabilities</h2>TDK’s environmental sensors also have real-world applications. These sensors significantly enhance robots’ ability to detect and interact with their surroundings and operate safely around humans. TDK’s environmental sensors support this by providing real-time data on air quality, humidity and atmospheric pressure:<ul><li dir="ltr">Gas Sensors&nbsp;— The TCE-11101 MEMS-based CO2 gas sensor detects harmful substances with high accuracy, which is important in industrial and healthcare environments.</li><li dir="ltr">Humidity Sensors — TDK's humidity sensors, featuring ±5% RH accuracy, enable adaptive climate control in smart homes and workplaces.</li><li dir="ltr">Pressure Sensors — The ICP-10111 capacitive barometric pressure sensor, integrated into TDK's RoboKit1, allows for altitude detection and atmospheric pressure monitoring.</li></ul>Beyond atmospheric sensing, TDK sensors enhance object detection and give robots a reliable, non-contact method for navigation and interaction:<ul><li dir="ltr">Object Detection — TDK's SmartSonic ultrasonic Time-of-Flight (ToF) sensors, such as the ICU-20201, provide non-contact object detection and navigation up to 5 meters in any lighting condition.</li><li dir="ltr">Voice Detection&nbsp;— The ICS-43434 digital I²S microphones enhance spatial awareness in voice-activated robots.3</li></ul>With these advanced sensing capabilities, robots can better adapt to their environment and interact with humans in a more intuitive way.<h2 dir="ltr">Intelligent Human-Robot Interaction with TDK’s Sensor Fusion</h2>Human-machine interaction is more engaging with sensors that understand gestures, proximity, and touch. TDK’s sensor fusion technology also facilitates more natural and intuitive robot-human interactions. Touch and proximity sensing is especially relevant for consumer-facing robotics, where intuitive feedback helps build using trust:<ul><li dir="ltr">Haptic Touch Sensors — TDK's piezoelectric actuators provide high-definition haptic feedback for enhanced touch interactions in robotic applications.</li><li dir="ltr">Gesture-Based Control — The CH101-00ABR ultrasonic ToF sensor enables gesture-based control and user input recognition with a configurable 180° field of view.</li></ul>Through TDK’s RobotKit 1 development platform, integrated with ROS and TDK’s adaptive learning models, robots can tailor their responses over time, learning from repeated interactions. This personalized behavior improves functionality and provides more dynamic human-machine interaction:<ul><li dir="ltr">Holistic Awareness — The ICM-42688-P 6-axis IMU, combined with other sensors in the RoboKit1, provides real-time situational awareness.</li><li dir="ltr">Adaptive Learning&nbsp;— TDK's RoboKit software, integrated with ROS, enables personalized interactions using adaptive learning models.</li><li dir="ltr">Social Applications&nbsp;— The combination of IMUs, microphones, and ToF sensors in the RoboKit1 platform enhances social robotics applications.</li></ul>These advancements bring us closer to the kind of seamless human-robot interactions often portrayed in science fiction, where robots can understand gestures, emotions, and intentions with remarkable accuracy.<h2 dir="ltr">ROS 1 and ROS 2: The Software Framework Unifying TDK’s Sensor Ecosystem</h2>The Robot Operating System (ROS) is a critical standardized platform for robotic perception, planning, and control. TDK’s ROS 1 and ROS 2 extension includes pre-configured sensor libraries and real-time data synchronization, streamlining development and performance.This software foundation supports critical functions like real-time sensor processing, AI-enhanced decision-making, and cross-platform compatibility. Developers can use the same ecosystem to build robots for very different applications, from smart retail kiosks to autonomous healthcare aides, without having to reinvent the platform for each use case.<h2 dir="ltr">Real-World Applications of TDK’s Robotics Sensor Platform</h2>As highlighted throughout this series, TDK’s sensor platform is already making a big impact in the real world. Its technologies are used in robotics systems for healthcare, retail, personal assistance, and more. The investment by TDK Ventures in companies like ANYbotics further underlines the company’s commitment to driving innovation in robotics.By enabling smarter, safer, and more adaptable machines, TDK is solving today’s engineering problems and laying the groundwork for human-robot coexistence.<h2 dir="ltr">Conclusion</h2>TDK's sensor ecosystem is more than just a set of components—it's a modular, scalable, and AI-driven solution that is already shaping real-world robotics. As innovation continues and ethical considerations evolve, we are closer than ever to a future where intelligent, responsive robots integrate seamlessly into our daily lives—much like the imagined robotic companions of anime and manga.Learn more about TDK’s innovative advancements at <a href="https://www.tdk.com/en/index.html">https://www.tdk.com/en/index.html</a>.<hr>Resources:<ol><li>Qualcomm Robotics RB3 Development Kit. Accessed from <a href="https://invensense.tdk.com/technology/robotics/" id="isPasted">https://invensense.tdk.com/technology/robotics/</a></li><li>TDK IMU Product Page. Accessed from <a href="https://product.tdk.com/en/products/sensor/mortion-inertial/imu/index.html" target="_blank" rel="noopener noreferrer">https://product.tdk.com/en/products/sensor/mortion-inertial/imu/index.html</a></li><li>“Sensor solutions that enable advanced control of service robots”. Accessed from <a href="https://product.tdk.com/en/techlibrary/solutionguide/sensor-for-service-robots.html" id="isPasted">https://product.tdk.com/en/techlibrary/solutionguide/sensor-for-service-robots.html</a></li></ol>

This article is part 4 of a 4-part article series on TDK's advanced robotics.

A Platform for Smarter Robots: How TDK's Sensor Ecosystem Powers Next-Gen Robotics

<h1 data-immersive-translate-walked="96540da1-b11f-43db-91ca-401597307f25" id="isPasted">Unitree Go2 New Upgrade</h1>The evolution of intelligent robots is full of surprises and exciting moments every day. Let's have fun together. 🥳🥳🥳Official Website: www.unitree.com&nbsp;Twitter: twitter.com/UnitreeRobotics&nbsp;Youtube: @unitreerobotics &nbsp;&nbsp;&nbsp;LinkedIn: www.linkedin.com/company/unitreerobotics

The evolution of intelligent robots is full of surprises and exciting moments every day.
Let's have fun together.

Unitree Go2 New Upgrade

<h3 id="isPasted">Introduction</h3>The demand for robotics in utility sectors, ranging from infrastructure inspection to port logistics, is growing quickly as industries seek to automate labor-intensive and hazardous tasks. Reliable and precise navigation is a must for these robots, especially those that operate in cluttered, dynamic environments where there are obstacles, moving vehicles, and complex layouts. However, Global Navigation Satellite Systems (GNSS) alone is often insufficient for this type of complex navigation due to signal loss in urban canyons, near power lines, or indoors.Some robotic navigation systems rely on detailed 3D maps built in advance using techniques like SLAM (Simultaneous Localization and Mapping). While powerful in theory, these solutions also face major limitations in real-world large-scale applications because environments change constantly and maps quickly become obsolete. Additionally, these methods often require high-end LiDAR sensors and GPU-intensive processing, which increases costs and complexity, making it difficult to scale across large fleets. Fixposition, a Zurich-based company, is at the forefront of solving this challenge with high-precision global positioning solutions for autonomous machines. Rather than relying solely on GNSS or pre-built maps, Fixposition combines multiple sensor modalities: GNSS, computer vision, inertial sensors, and, optionally, vehicle data, into a unified solution. Its Vision-RTK 2 sensor demonstrates how intelligent sensor fusion effectively enables real-time localization in complex environments.This article explores the core navigation challenges for utility robotics and how Fixposition’s sensor fusion technology offers a scalable, adaptable, and cost-effective alternative to traditional approaches.<h2>Challenges Utility Robots Face in Complex Environments</h2>Before diving into the solution, it’s important to understand the problem. Utility robots face unpredictable terrain, both physical and electromagnetic. Their success depends on precise navigation in areas where GNSS falls short, and where adaptability and scalability are key to deployment at scale.<h3>GNSS Limitations</h3>Utility robots often operate in environments where GNSS signals are unreliable. Tall buildings, bridges, dense foliage, and power infrastructure can block or reflect satellite signals, which can lead to signal loss or degradation. Multipath interference, where signals bounce off surfaces before reaching the receiver, is especially problematic in urban and industrial settings, and causes significant positioning errors.<h3>Demand for Versatility and Scalability</h3>Modern utility robots are expected to perform across many different environments, from city streets, to orchards, and mines. This versatility requires navigation solutions that can adapt to different conditions and robot types. Scalability is also important, as organizations look to deploy fleets of robots for diverse applications without the need for excessive customization or integration overhead.<h3>Cost and Integration</h3>Traditional high-precision positioning systems, such as RTK/INS (Real-Time Kinematic / Inertial Navigation Systems) are often prohibitively expensive and require complex integration and software customization. These factors contribute to high development costs and lengthy time-to-market, which can hinder the adoption of robotics in utility sectors.<h2>Fixposition’s GNSS-Vision Fusion Technology</h2>Rather than filling the gaps left by GNSS, Fixposition’s approach changes how robotic systems can achieve reliable navigation in complex environments. The company’s sensor fusion engine combines GNSS, camera-based vision, inertial measurements, and optional vehicle kinematics, which enables consistent, real-time localization, even when satellite signals are intermittent or unavailable. This approach removes the need for pre-mapped environments and highly customized deployments, providing greater flexibility and reduced operational overhead.<h3>How It Works</h3>Fixposition’s deep sensor fusion engine, called xFusion, is at the center of the solution. This software component blends inputs from GNSS, vision (camera), inertial measurement units (IMUs), and vehicle data for centimeter-level accuracy. In GNSS-denied zones, like tunnels, dense foliage, or reflective surfaces, Fixposition’s visual-inertial odometry maintains a low drift rate (less than 0.75%), which enables continuous positioning in dynamic environments.Fixposition’s Vision-RTK 2 sensor demonstrates this approach. It delivers real-time, globally-referenced position with RTK-level accuracy (1 cm + 1 ppm), in a form factor that is compact, lightweight, IP66-rated, and suitable for outdoor and industrial environments. This system is designed for ease of integration with common robotics platforms through interfaces like  ROS, PX4, CAN, and UART.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1750159405844-fixpoastion.jpg" style="width:100%px" class="fr-fic fr-dib" />Fixposition’s Vision-RTK 2 | Source: Fixposition.<h2>Key Advantages</h2>Affordability: Using advanced sensor fusion, Fixposition offers performance comparable to high-end RTK/INS systems, while significantly reducing hardware and integration costs. The company’s pre-built, cost-effective solutions help robotics engineers reduce development and integration expenses.Fast Integration: Vision-RTK 2 is designed for quick testing and deployment. It is compatible with common robotics middleware (ROS, PX4) and standard interfaces (CAN, UART), meaning that time to integration and deployment is minimized. The modular design allows for adaptation to various sensors and robot platforms, including drones, ground robots, and industrial vehicles.Scalability: Fixposition’s solutions are tailored for different customer needs and operational environments, from urban to rural, industrial to agricultural. The hardware is forward-looking, and continuous software updates ensure that equipment provides long-term value and adaptability as requirements change.Accelerated Time-to-Market: Time-to market and technical risk for robotics teams are reduced with Fixposition’s ready-made solutions, expert support, and evaluation/demo platforms.<h2>Real-World Use Cases in Utility Operations</h2>Fixposition’s positioning solutions are field-proven in some of the most demanding operational environments. Here are a few examples of how utility robots leverage deep sensor fusion for consistent, real-time localization:<h3>Citywide Street Sweeping: Reduced Downtime by 90%</h3>A customer has deployed over 500 autonomous street-sweeping robots across a major metropolitan area, including downtown cores with high-rise buildings. With Fixposition’s positioning engine, robots transitioned seamlessly between GNSS-available and GNSS-denied areas. Navigation-related manual interventions dropped by 90%, dramatically improving operational uptime.<h3>Fully Automated Port Logistics: +40% Productivity</h3>In a major shipping port, a customer integrated Fixposition’s Vision-RTK 2 to enable autonomous truck navigation among dense metal containers and under bridges. Without relying on pre-built maps, the vehicle maintained consistent performance. This resulted in a 40% increase in productivity and helped address labor shortages.<h3>Expanding Security Patrol Coverage – 4x Customer Growth</h3>A provider of security robots expanded their reach into underground and dense urban facilities using Fixposition’s technology. Over the following year, the company quadrupled its customer base and improved teleoperation efficiency from one operator per four robots to one per twenty.<h3>Adaptability</h3>Each deployment is optimized for the specific environment and robot form factor, maintaining robust performance whether on the ground, in the air, or in industrial settings.<h1>Integration and Evaluation</h1>Fixposition takes a collaborative approach to integration and works closely with customers to define requirements, select the optimal sensor stack, and design the system architecture In addition to hardware like the Vision-RTK 2, Fixposition offers software integration and customization services to meet specific operational goals..Evaluation typically starts with onsite demonstrations, including installation, data collection, and calibration. The data is then benchmarked against ground truth, with post-demo analysis providing actionable insights for further optimization. Fixposition’s flexible integration software architecture supports integration with existing sensor payloads and perception stacks, keeping disruption minimal while accelerating deployment.<h2>Conclusion: Enabling Scalable, Reliable Utility Robotics</h2>Fixposition’s GNSS-vision fusion technology addresses the core challenges of utility robotics: delivering navigation accuracy, robust operation in GNSS-challenged environments, and cost-effective, rapid integration. Its combination of tightly integrated hardware, adaptive algorithms, and software customization positions it as a strong partner for developers building the next generation of autonomous systems. As industries push for safer, more efficient robotics, robust positioning technology like Fixposition’s will continue to play a pivotal role.For more information about Fixposition’s solutions, visit <a href="https://www.fixposition.com/">www.fixposition.com</a>.

Utility robots can't always count on GNSS, especially in dynamic, busy environments like cities or industrial settings. By combining data from multiple sensors, Fixposition shows how sensor fusion can help robots stay on track and work reliably in the real world.

Fixing Positioning: Why GNSS Alone Fails Utility Robots — And How Sensor Fusion Bridges the Gap

<h1 id="isPasted">Unitree Combat Competition Highlights May 25, 2025</h1>A historic moment in human history: The first-ever humanoid robot combat competition(Livestream)

A historic moment in human history: The first-ever humanoid robot combat competition(Livestream)

Unitree Combat Competition Highlights May 25, 2025

This is Part 3 of a four-part series. See Part 1: <a href="https://www.wevolver.com/article/mastering-multitasking-exploring-the-distributed-processing-capabilities-of-tdks-advanced-robotics" target="_blank" rel="noopener noreferrer">Mastering Multitasking: Exploring the Distributed Processing Capabilities of TDKs Advanced Robotics</a> and Part 2: <a href="https://www.wevolver.com/article/sensing-the-world-how-tdks-multi-sensor-fusion-improves-perception-in-industrial-and-service-robots" target="_blank" rel="noopener noreferrer">Sensing the World: How TDK’s Multi-Sensor Fusion Improves Perception in Industrial and Service Robots. </a><h2>Introduction</h2>Humanoid robotics have seen remarkable growth in recent years, with applications expanding across healthcare, home assistance, and industrial sectors. The global market for humanoid robots is expected to grow from USD $2.03 billion in 2024 to USD 13.25 billion by 2030.[1] However, this growth has been accompanied by significant challenges, notably in motion control and stability. The key to addressing these issues is the Inertial Measurement Unit (IMU), an important component for replicating human-like movements in humanoid robots. IMUs track orientation, acceleration, and movement, so that humanoid robots can replicate human-like movements effectively.  TDK Corporation, a leader in electronic components and systems, has developed a unique MEMS-based 6-axis IMU technology that is transforming motion control in humanoid robotics. This advanced IMU integrates accelerometer and gyroscope data to provide real-time motion tracking, which enables precise limb control, dynamic stability, and fall detection in humanoid robots.[2]By combining high-precision sensors with sophisticated algorithms, TDK’s 6-axis IMU sets a new standard for motion control in the field of service robotics.<h2>The Need for Precision in Humanoid Robots</h2>Humanoid robots face unique motion challenges that require exacting solutions:<ul><li>Balance and Stability — Robots working in unpredictable environments near humans must stay upright on uneven terrain.</li><li>Real-Time Motion Tracking — Robots need instant data processing and coordination to move naturally and respond to external stimuli.</li><li>Fall Detection and Recovery — Preventing and recovering from falls is critical for safe operation, especially in spaces designed for humans.</li></ul>Traditional motion sensors often struggle to keep up, and basic IMUs often fail to compensate for sudden disturbances. This leads to small errors that add up over time. Additionally, although optical and LiDAR-based systems are extremely accurate, they are computationally demanding and can introduce delays, which makes them less ideal for fast, responsive movement.[3]The limitations of conventional sensors show that there is a need for more advanced solutions in humanoid robotics. TDK’s 6-axis IMU addresses these shortcomings by providing high-precision, low-latency motion data. This responsive IMU helps humanoid robots move with greater agility and stability, bringing them a step closer to human-like motion. <h2>How TDK’s 6-Axis IMU Solves These Challenges</h2><h3>Advanced Motion Tracking Through Sensor Fusion</h3>TDK’s 6-axis IMU combines accelerometers and gyroscopes to gather precise motion data. The working mechanism involves these components:<ul><li>Accelerometers measure linear acceleration in three axes.</li><li>Gyroscopes detect angular velocity around three axes.</li><li>Sensor fusion algorithms integrate both of these data streams to predict movement with accuracy.</li></ul>Quantified performance indicators for TDK’s ICM-42688-P IMU:<ul><li>TDK’s ICM-42688-P IMU achieves a 40% lower noise figure compared to traditional consumer-grade IMUs.</li><li>Temperature stability is improved by 2x, keeping data accurate across environmental conditions.</li><li>The device features a high-resolution analog-to-digital converter that provides an 8x increase in gyroscope resolution and a 4x increase in accelerometer resolution.</li><li>Rapid data processing and a 100% accurate clock eliminate timing errors for near-instantaneous motion tracking.[4]</li></ul>This fusion technology has several benefits:<ul><li>Drift Compensation — Advanced algorithms correct sensor drift, which keeps data accurate long term.</li><li>Kalman Filtering — This technique refines and enhances motion estimates by combining sensor data with predictive models.</li><li>Ultra-Low Latency — The rapid data processing results in near-instantaneous motion tracking.[5]</li><li>AI-Powered Motion Predictions — IMU data can be used for AI/ML predictive models for more human-like movement.  </li></ul><h3>Enhancing Dynamic Stability in Humanoid Robots</h3>Dynamic stability is critical for humanoid robots, and TDK’s ICM-42688-P IMU helps maintain this with:<ul><li>Real-Time Posture Correction — The IMU detects imbalances and triggers adjustments to the robot’s stance. It reaches a heading accuracy of ≤10° per hour and operates at a data rate of up to 1000 Hz, enabling fast detection and correction of imbalances. </li><li>Adaptive Gait Optimization — The IMU’s high-frequency (up to 1000 Hz) keeps the robot walking smoothly on uneven terrain by continuous adjustment of leg movements.</li><li>Multi-Sensor Integration — IMU data is fused with force sensor feedback and geometric models using Extended Kalman Filters (EKF). This fusion reduces contact force estimation errors to within 5 N·m and maintains balance stability above 95% in dynamic environments. When IMU and force sensor data are combined, interference errors are reduced by about 20%, and overall pose estimation accuracy improves by up to 30%</li></ul><h3>Fall Detection and Recovery</h3>Safety is a priority in robotics, especially in assistive applications. The 6-axis IMU helps prevent falls by:<ul><li>Detecting sudden acceleration changes that might signal a potential fall.</li><li>Analyzing body tilt and weight shifts to predict instability.</li><li>Triggering corrective actions before impact, reducing the risk of falls.</li></ul>These capabilities make TDK’s IMU valuable in applications like assistive robotics, where fall prevention is required for user safety.[6]<h2>Real-World Applications of TDK’s 6-Axis IMU</h2><h3>Assistive Robotics in Healthcare</h3>TDK’s IMU technology finds significant applications in healthcare robotics:<ul><li>Exoskeletons for Rehabilitation — Helps impaired patients regain movement with precise motion control and balance support.</li><li>Elderly Support Robots — Improves stability for home care robotic assistants by providing safe navigation and facilitating interaction in domestic environments. [7]</li></ul><h3>Home Service Robots</h3>The 6-axis IMU also has applications in domestic settings, where there are opportunities to improve robotic efficiency:<ul><li>Autonomous Navigation — Enables smooth movement for cleaning, delivery, and household assistance.</li><li>Precision in Object Handling — Provides stability and control for AI-powered robotic arms, which allows for safe handling of household items.</li></ul><h3>Industrial and Inspection Robotics: ANYbotics Case Study</h3>TDK Ventures has partnered with ANYbotics, a leader in autonomous industrial inspection robots. Their ANYmal robot integrates TDK’s IMU technology to enhance performance in:<ul><li>Harsh Environments — Enables stable movement on uneven surfaces and improves obstacle avoidance in industrial settings. The IMU ensures that the robot maintains balance even in hazardous areas such as offshore platforms, underground tunnels, and power plants.</li><li>Factory Automation — Supports self-balancing robotic arms for precise manufacturing tasks, increasing efficiency in automated production lines. The IMU's real-time motion tracking allows robots to detect micro-vibrations and adjust accordingly, reducing errors in delicate assembly processes.[8]</li></ul>ANYmal’s ability to navigate complex environments with high stability demonstrates how TDK’s IMU complements robotic autonomy. By improving movement precision and safety, this technology provides industries with a way to reduce human risk exposure while maintaining high operational efficiency.<h2>TDK’s Competitive Edge in IMU Technology</h2><h3>TDK's 6-axis IMU has several advantages that make it stand out from conventional IMUs:</h3><ul><li>High Precision — Delivers more accurate motion data with minimal drift.</li><li>Robust Noise Filtering — Maintains clean data even in noisy environments.</li><li>Compact Design — MEMS-based miniaturization helps keep robot designs lightweight and power-efficient.[9]</li></ul>TDK’s MEMS-based IMU is unique because it can provide micro-scale motion tracking with high precision, which is key to replicating human-like movements in robots. The compact size of the technology also makes way for the development of more agile and energy-efficient robotic systems.Looking ahead, TDK is exploring AI and machine learning integration:<ul><li>AI-powered motion predictions can refine IMU tracking for even greater accuracy.</li><li>Adaptive learning algorithms could enable humanoid robots to improve movement by learning about the environment over time.</li></ul><h2>Conclusion</h2>TDK’s 6-axis IMU is positioned to shape the future of humanoid robotics with industry-leading precision, robust noise filtering, and ultra-compact MEMS design. Devices like the ICM-42688-P offer precise, real-time motion data and unparalleled performance metrics that enable more stable, agile, and safe robotic systems. These advancements position TDK at the forefront of robotic motion tracking for replicating human-like movement.As TDK continues to innovate in MEMS-based IMU technology, we can anticipate even more advanced and capable robotic systems in years to come. Learn more about TDK’s innovative advancements at <a href="https://www.tdk.com/en/index.html">https://www.tdk.com/en/index.html</a>.<hr /><h3>Reference</h3>[1] Markets and Markets. “Humanoid Robot Market Size, Share &amp; Growth”. Accessed from <a href="https://www.marketsandmarkets.com/Market-Reports/humanoid-robot-market-99567653.html" id="isPasted">https://www.marketsandmarkets.com/Market-Reports/humanoid-robot-market-99567653.html</a>[2] TDK IMU Product Page. Accessed from <a href="https://product.tdk.com/en/products/sensor/mortion-inertial/imu/index.html" id="isPasted">https://product.tdk.com/en/products/sensor/mortion-inertial/imu/index.html</a> [3] Ohidul Islam. “Challenges in Humanoid Robotics and How to Overcome Them”. Accessed from <a href="https://robozaps.com/challenges-in-humanoid-robotics/" id="isPasted">https://robozaps.com/challenges-in-humanoid-robotics/</a> [4] Shannon Davis. “TDK Launches High-Performance 6-axis IMU with Industry-Leading Motion Sensor Performance”. Semiconductor Digest. Accessed from <a href="https://www.semiconductor-digest.com/tdk-launches-high-performance-6-axis-imu-with-industry-leading-motion-sensor-performance/" id="isPasted">https://www.semiconductor-digest.com/tdk-launches-high-performance-6-axis-imu-with-industry-leading-motion-sensor-performance/</a> [5] TDK IMU Product Page.[6] “TDK launches high-performance 6-axis IMU with industry-leading motion sensor performance for IoT, robotics, AR/VR and wearable applications”. Industry EMA. Accessed from <a href="https://www.industryemea.com/news/27191-tdk-launches-high-performance-6-axis-imu-with-industry-leading-motion-sensor-performance-for-iot,-robotics,-ar-vr-and-wearable-applications" id="isPasted">https://www.industryemea.com/news/27191-tdk-launches-high-performance-6-axis-imu-with-industry-leading-motion-sensor-performance-for-iot,-robotics,-ar-vr-and-wearable-applications</a> [7] Rika Melissa. “Service Robot Market: Trends, Growth, and Future Outlook” (22 May 2024). Sateton. Accessd from <a href="https://statzon.com/insights/humanoid-helpers-and-beyond-service-robot-market-expansion" id="isPasted">https://statzon.com/insights/humanoid-helpers-and-beyond-service-robot-market-expansion</a>[8] “TDK Ventures Invests in ANYbotics, a World Leader in Industrial Inspection Autonomous Robots” (11 Dec. 2024). Accessed from <a href="https://tdk-ventures.com/news/announcements/tdk-ventures-invests-in-anybotics-a-world-leader-in-industrial-inspection-autonomous-robots/" id="isPasted">https://tdk-ventures.com/news/announcements/tdk-ventures-invests-in-anybotics-a-world-leader-in-industrial-inspection-autonomous-robots/</a>[9] TDK IMU Product Page.

Photo by Possessed Photography on Unsplash

By combining high-precision sensors with sophisticated algorithms, TDK's 6-axis IMU sets a new standard for motion control in the field of service robotics.

Innovation in Motion: How TDK's 6-Axis IMU Enables Precise Movement in Humanoid Robots

Smart manufacturing utilizes integrated, intelligent technologies like the Internet of Things (IoT), artificial intelligence (AI), and robotics to optimize manufacturing processes through automation and real-time data analytics. At the heart of these cutting-edge advancements are photonics technologies, which utilize light-based mechanisms to advance manufacturing capabilities. Essential to modern production environments, photonics enhances sensing, processing, and inspection tasks.According to the Fortune Business Insights report titled “Photonics Market Size, Share &amp; COVID-19 Impact Analysis,” the global photonics market size is projected to grow from USD 983.51 billion in 2024 to USD 1,642.61 billion by 2032 at a CAGR of 6.7% [1]. This growth underscores the expanding role of photonic components in modern industrial systems. A critical innovation within this domain is the development of compact Light Detection and Ranging (LiDAR) systems. These systems, particularly those powered by low-profile pulse laser diodes, are pivotal in areas requiring high precision and responsiveness such as robotics, quality control, and autonomous material handling. Compact LiDAR systems are prized for their ability to offer miniaturization, reduced power consumption, and superior accuracy—qualities that are indispensable for the advancement of manufacturing automation.This article explores the transformative influence of photonics in smart manufacturing, focusing on the deployment of compact LiDAR systems. It details their pivotal applications, delineates their competitive advantages, addresses implementation challenges, and forecasts future trends that will shape the industry.<h2>Photonics in Smart Manufacturing</h2>Photonics refers to generating, manipulating, and detecting photons, particularly in the visible and near-infrared spectrum, to perform various functions of utmost importance in smart manufacturing. These advanced optical systems enable high-speed real-time monitoring through optical sensors while facilitating precision material processing applications, including cutting, welding, and engraving. Among the most impactful implementations is LiDAR technology, which provides essential 3D mapping and quality inspection capabilities. Compact LiDAR systems utilizing low-profile pulse laser diodes offer advantages, delivering high-accuracy depth perception even in space-constrained industrial environments. Their combination of high-frequency operation and minimal power requirements makes these systems exceptionally well-suited for integration into automated production lines, where they enhance both precision and efficiency. These capabilities are integral to the design of cyber-physical production systems, one of the core components of Industry 4.0. <img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1747924156324-hama+2.jpg" style="width:100%px" class="fr-fic fr-dib" /><h2 id="isPasted">Applications of Compact LiDAR Systems in Smart Manufacturing </h2>Compact LiDAR systems have enabled various photonics applications to become more accessible, mobile, and adaptable. Their incorporation into various segments of the manufacturing process illustrates their versatile utility.<h3>Sensing and Data Acquisition</h3>The compact LiDAR system's most impactful application is in real-time, high-resolution sensing. LiDAR technology works by emitting short laser pulses and measuring the time it takes for these pulses to reflect off surfaces and return to the detector. Low-profile pulse laser diodes in such systems enable high pulse repetition rates, compact form factors, and reduced energy consumption.In smart manufacturing, these systems are used extensively in robotic navigation, object detection, and production line mapping. Their compactness ensures they can be mounted on mobile platforms such as autonomous guided vehicles (AGVs), enabling dynamic mapping and obstacle avoidance in factory environments. The high spatial resolution provided by LiDAR improves feedback accuracy for closed-loop control, resulting in enhanced system responsiveness.<h3>Laser-Based Processing</h3>While LiDAR is primarily a sensing technology, its laser foundation aligns with broader laser-based processing techniques in manufacturing. Compact LiDAR systems, integrated alongside laser machining tools, contribute to real-time monitoring and adaptive control of material processing tasks such as micro-welding or additive manufacturing.Overlaying a LiDAR-based spatial map with the target surface enables the processing laser to adapt to real-time topographical changes, ensuring consistent processing even when the material or workpiece exhibits irregularities. This approach reduces defects and supports inline adjustments, ultimately contributing to higher process reliability.<h3>Imaging and Quality Control</h3>Compact LiDAR systems also enhance machine vision and quality assurance protocols, combining depth mapping with conventional 2D imaging to enable comprehensive inspections that consider surface geometry alongside texture and colour.For example, in the automotive and electronics industries, compact LiDAR facilitates micro-warping detection in printed circuit boards or misalignment in component assemblies. Using pulse laser diodes ensures fast data acquisition, thereby maintaining throughput without sacrificing accuracy.<h2>Advantages of Compact LiDAR Over Traditional Systems</h2>Integrating compact LiDAR systems into photonics-driven manufacturing environments provides several strategic advantages:<h3>Enhanced Spatial Precision: </h3>LiDAR systems provide centimetre to millimetre-level resolution, essential for high-precision applications such as electronic component assembly or semiconductor inspection.<h3>Scalability:</h3>The low-profile design of compact LiDAR modules enhances their scalability, allowing for seamless integration into various applications, from compact robotic joints to larger metrology systems. This flexibility offers a significant advantage over traditional, bulky equipment, enabling LiDAR systems to be scaled up or down based on the specific requirements of the task or environment.<h3>Real-Time Monitoring and Adaptability: </h3>LiDAR systems can dynamically track object movement and surface variations, unlike static sensors. Their use in adaptive systems ensures consistency despite variability in manufacturing conditions.<h3>Reduced Maintenance and Operational Downtime:</h3>Compact LiDAR modules have few moving parts and can be sealed against dust and contaminants. This durability contributes to extended operational lifespans and lower total cost of ownership compared to traditional optical or mechanical sensing tools.<h3>Energy and Resource Efficiency: </h3>Pulse laser diodes operate with high electrical-to-optical conversion efficiency. This translates to lower power requirements, which are especially crucial in distributed systems and mobile robotic units.<h2>Challenges and Solutions</h2>Despite their potential, compact LiDAR systems face several implementation challenges. Addressing these is key to unlocking their full value in smart manufacturing.<h3>Environmental Robustness</h3>Manufacturing environments are often harsh, involving dust, vibration, and thermal fluctuations. Compact LiDAR systems, although inherently robust due to fewer mechanical parts, must be further optimized through hermetic sealing, vibration damping, and temperature compensation mechanisms. Research into ruggedized optical materials and integrated thermal regulation continues to address this limitation.<h3>System Integration</h3>Compact LiDAR into existing factory infrastructure requires alignment with industrial communication protocols (e.g., OPC UA, Modbus) and compatibility with manufacturing execution systems (MES). Vendors increasingly offer LiDAR modules with built-in interfaces and APIs to ease integration challenges. Further, plug-and-play capabilities and modular architectures are facilitating retrofitting into legacy systems.<h3>Technology Integration and Optimization</h3>Compact LiDAR performance depends on precision components, primarily Pulse Laser Diodes (PLDs) and optical sensors:Pulse Laser Diodes emit nanosecond-range light pulses, providing the core signal for time-of-flight measurements. Their characteristics (peak power, repetition rate, and jitter) directly influence range and spatial resolution. Newer low-profile PLDs, like those from Hamamatsu, deliver high peak power (100W) with reduced form factor and energy demand ideal for embedded industrial systems.Optical Sensors such as avalanche photodiodes (APDs) and single-photon avalanche diodes (SPADs) are used to detect returned pulses. These advanced photodetectors offer superior sensitivity and timing precision, essential for high-resolution depth mapping in dynamic manufacturing environments.These technologies not only ensure reliable object detection and mapping but also enhance adaptability across varying surface textures and ambient lighting conditions. Improvements in packaging, thermal stability, and signal amplification further contribute to durability and accuracy.<h3>Data Volume and Processing</h3>High-frequency LiDAR scanning generates large volumes of spatial data. Efficient data handling and fusion with other sensor modalities (e.g., vision systems and tactile sensors) remain key concerns. Integration with edge computing hardware and real-time data processing algorithms, including machine learning for feature extraction, can alleviate computational bottlenecks and support intelligent decision-making.<h3>Initial Capital Costs</h3>While the cost of LiDAR has declined significantly in recent years due to advancements in diode and packaging technologies, initial procurement can still be substantial. However, the long-term return on investment through improved process efficiency, defect reduction, and automation scalability often justifies the expenditure.<h2>Advances in High-Speed Laser Diodes</h2>The trajectory of compact LiDAR systems indicates their increasing role as essential components within intelligent manufacturing and robotics platforms. As the demand for precision, efficiency, and adaptability grows, several key technological trends are anticipated to shape the next development phase, areas in which Hamamatsu Photonics’ optoelectronic innovations can offer enabling value.The continued refinement of pulsed laser diodes with high peak power, low jitter, and nanosecond-range pulse widths is central to enhancing the responsiveness of LiDAR systems. Such characteristics facilitate precise time-of-flight measurements and support integration with motion control frameworks in advanced robotics. Hamamatsu’s portfolio of pulsed laser diodes is well-suited for such time-critical applications, providing core components for the next generation of compact sensing modules.<h3>Photonics-Integrated Miniaturization:</h3>The photonic integration trend enables LiDAR systems to become smaller, more robust, and cost-effective. While full photonic integrated circuits (PICs) are evolving in parallel domains, Hamamatsu’s work on compact packaging of photonic components such as semiconductor laser modules and detectors supports the miniaturization efforts needed in space-constrained or embedded industrial applications[8].<h3>System Readiness for Intelligent Platforms:</h3>Emerging LiDAR modules are increasingly expected to interface seamlessly with intelligent systems for real-time monitoring, data fusion, and adaptive decision-making. Although system integrators often handle the interpretative layer, the stability and precision of Hamamatsu’s light sources and photodetectors make them suitable for deployment in AI-augmented platforms, requiring reliable data acquisition and temporal consistency[9].<h3>Sustainability in Manufacturing:</h3>Compact, energy-efficient LiDAR components contribute to the overarching goals of green manufacturing by enabling fine-grained monitoring, resource optimization, and predictive maintenance. Hamamatsu’s emphasis on component durability, thermal efficiency, and low power consumption aligns well with the principles of sustainable system design[10].<h3>Global Standardisation and Interoperability:</h3>International efforts to develop interoperability frameworks for LiDAR deployment in industrial environments pave the way for broader adoption. Hamamatsu's optoelectronic components' design consistency and signal reliability make them viable candidates for inclusion in modular, standards-aligned architectures that demand repeatability and cross-platform integration[9].<h2>Key technologies: The advantages of PLD in compact LiDAR systems</h2>Low-profile pulse laser diodes (PLDs) offer several advantages for compact LiDAR systems:High Peak Power: These PLDs can achieve peak powers exceeding 100W,sufficient for precise distance measurement in industrial environments .Energy Efficiency: Their design enables low power consumption, supporting extended operation in compact and battery-powered platforms.  Compact Design: The low-profile SMD format enables the creation of smaller, more compact LiDAR systems, which are easier to integrate into various applications.Mass Production: The compatibility with wafer-level manufacturing allows for large-volume production, reducing costs and improving scalability.Durability: These PLDs are resin-embedded for enhanced durability and longer lifetimes.High Photon Detection Efficiency: Improved photon detection efficiency ensures better performance in detecting and mapping objects.These advantages make low-profile PLDs ideal for applications requiring precise, efficient, and compact LiDAR systems.<h2 id="isPasted">Conclusion</h2>Fusing compact LiDAR systems, especially those utilizing low-profile pulse laser diodes with photonics technologies, transforms smart manufacturing. These systems deliver unprecedented accuracy, real-time adaptability, and spatial awareness, which are critical for achieving the responsiveness and efficiency demanded by Industry 4.0 paradigms.While challenges persist regarding integration, robustness, and data processing, recent advancements in pulse laser diode (PLD) efficiency, high-sensitivity photodetectors (such as APDs and SPADs), and miniaturized optical packaging continue to mitigate these hurdles. Furthermore, the adoption of edge computing modules, standardized industrial communication interfaces, and modular sensor architectures supports seamless deployment.These enabling technologies pave the way for the widespread integration of compact LiDAR as a standard tool in intelligent factories—empowering agile production lines, self-aware machines, and high-quality outputs with reduced environmental impact.<h3>Call to Action</h3>Stakeholders in industrial automation must recognize the strategic advantage of compact LiDAR technologies. Organizations can position themselves at the forefront of smart manufacturing innovation by investing in research, fostering partnerships, and staying current with technological developments. Active engagement with standards bodies, educational initiatives, and pilot deployments will accelerate the effective deployment of photonics-enabled manufacturing solutions.Manufacturers and technology providers such as Hamamatsu Photonics, known for developing pulsed laser diodes, offer components that may be considered when designing and implementing compact LiDAR systems. Staying informed about commercially available technologies can support more informed decision-making and system design.<h2>References and further reading</h2>[1] Fortune Business Insights, "Photonics Market Size, Share &amp; COVID-19 Impact Analysis," [Online]. Available: <a href="https://www.fortunebusinessinsights.com/photonics-market-106525">https://www.fortunebusinessinsights.com/photonics-market-106525</a>.[2] B. E. A. Saleh and M. C. Teich, Fundamentals of Photonics, 3rd ed. Wiley-Interscience, 2007.[3] J. Zhang and S. Singh, "LOAM: Lidar Odometry and Mapping in Real-time," Robotics: Science and systems. Vol. 2. No. 9. 2014.[4] P. Rainbow, "High-power pulsed laser diodes take on new industrial and commercial applications," Photonics Spectra, vol. 38, pp. 105–108, 2004.[5] Hamamatsu Photonics, "Pulsed Laser Diodes," [Online]. Available: <a href="https://www.hamamatsu.com/jp/en/product/lasers/semiconductor-lasers/plds.html">https://www.hamamatsu.com/jp/en/product/lasers/semiconductor-lasers/plds.html</a>[6]. M. P. Mollah et al., "Efficient compression method for roadside LiDAR data," in Proc. 31st ACM Int. Conf. on Information &amp; Knowledge Management (CIKM), 2022, pp. 3726–3730.[7] M. Smit et al., "An introduction to InP-based generic integration technology," Semiconductor Science and Technology, vol. 29, no. 8, 2012.[8] Photodiodes. Hamamatsu Photonics K.K. [Online]. Available: <a href="https://www.hamamatsu.com/jp/en/product/optical-sensors/photodiodes.html">https://www.hamamatsu.com/jp/en/product/optical-sensors/photodiodes.html</a>.[9] Optical Sensors. Hamamatsu Photonics K.K. [Online]. Available: <a href="https://www.hamamatsu.com/jp/en/product/optical-sensors.html">https://www.hamamatsu.com/jp/en/product/optical-sensors.html</a>.[10] Environmentally Contributing and Friendly Products (2021). Hamamatsu Photonics K.K. [Online]. Available: <a href="https://www.hamamatsu.com/jp/en/ourcompany/sustainability/environment/environmentally-contributing-and-friendly-products/2021.html">https://www.hamamatsu.com/jp/en/ourcompany/sustainability/environment/environmentally-contributing-and-friendly-products/2021.html</a>.

Enabling precision, efficiency, and miniaturization in industrial automation through advanced photonics.

Compact LiDAR Systems Powered by Low-Profile Pulse Laser Diodes For Automation Applications

<h1 id="isPasted">Daily Training of Robots Driven by RL</h1>Segments of daily training for robots driven by reinforcement learning. Multiple tests done in advance for friendly service humans. The training includes some extreme tests, please do not imitate!

Segments of daily training for robots driven by reinforcement learning.
Multiple tests done in advance for friendly service humans.
The training includes some extreme tests, please do not imitate!

Daily Training of Robots Driven by RL

A human clearing junk out of an attic can often guess the contents of a box simply by picking it up and giving it a shake, without the need to see what’s inside. Researchers from MIT, Amazon Robotics, and the University of British Columbia have taught robots to do something similar.They developed a technique that enables robots to use only internal sensors to learn about an object’s weight, softness, or contents by picking it up and gently shaking it. With their method, which does not require external measurement tools or cameras, the robot can accurately guess parameters like an object’s mass in a matter of seconds.This low-cost technique could be especially useful in applications where cameras might be less effective, such as sorting objects in a dark basement or clearing rubble inside a building that partially collapsed after an earthquake.Key to their approach is a simulation process that incorporates models of the robot and the object to rapidly identify characteristics of that object as the robot interacts with it. The researchers’ technique is as good at guessing an object’s mass as some more complex and expensive methods that incorporate computer vision. In addition, their data-efficient approach is robust enough to handle many types of unseen scenarios.“This idea is general, and I believe we are just scratching the surface of what a robot can learn in this way. My dream would be to have robots go out into the world, touch things and move things in their environments, and figure out the properties of everything they interact with on their own,” says Peter Yichen Chen, an MIT postdoc and lead author of a <a href="https://arxiv.org/pdf/2410.03920" target="_blank">paper on this technique</a>.His coauthors include fellow MIT postdoc Chao Liu; Pingchuan Ma PhD ’25; Jack Eastman MEng ’24; Dylan Randle and Yuri Ivanov of Amazon Robotics; MIT professors of electrical engineering and computer science Daniela Rus, who leads MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL); and Wojciech Matusik, who leads the Computational Design and Fabrication Group within CSAIL. The research will be presented at the International Conference on Robotics and Automation.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1747357229462-ezgif-290e6964e4b891.gif" style="width:100%px" class="fr-fic fr-dib" />With a new simulation method, robots can guess the weight, softness, and other physical properties of an object just by picking it up. Credit: MIT News, iStock<h2 id="isPasted">Sensing signals</h2>The researchers’ method leverages proprioception, which is a human or robot’s ability to sense its movement or position in space.For instance, a human who lifts a dumbbell at the gym can sense the weight of that dumbbell in their wrist and bicep, even though they are holding the dumbbell in their hand. In the same way, a robot can “feel” the heaviness of an object through the multiple joints in its arm.“A human doesn’t have super-accurate measurements of the joint angles in our fingers or the precise amount of torque we are applying to an object, but a robot does. We take advantage of these abilities,” Liu says.As the robot lifts an object, the researchers’ system gathers signals from the robot’s joint encoders, which are sensors that detect the rotational position and speed of its joints during movement. Most robots have joint encoders within the motors that drive their moveable parts, Liu adds. This makes their technique more cost-effective than some approaches because it doesn’t need extra components like tactile sensors or vision-tracking systems.To estimate an object’s properties during robot-object interactions, their system relies on two models: one that simulates the robot and its motion and one that simulates the dynamics of the object.“Having an accurate digital twin of the real-world is really important for the success of our method,” Chen adds.Their algorithm “watches” the robot and object move during a physical interaction and uses joint encoder data to work backward and identify the properties of the object.For instance, a heavier object will move slower than a light one if the robot applies the same amount of force.<h2>Differentiable simulations</h2>They utilize a technique called differentiable simulation, which allows the algorithm to predict how small changes in an object’s properties, like mass or softness, impact the robot’s ending joint position. The researchers built their simulations using NVIDIA’s Warp library, an open-source developer tool that supports differentiable simulations.Once the differentiable simulation matches up with the robot’s real movements, the system has identified the correct property. The algorithm can do this in a matter of seconds and only needs to see one real-world trajectory of the robot in motion to perform the calculations.“Technically, as long as you know the model of the object and how the robot can apply force to that object, you should be able to figure out the parameter you want to identify,” Liu says.The researchers used their method to learn the mass and softness of an object, but their technique could also determine properties like moment of inertia or the viscosity of a fluid inside a container.Plus, because their algorithm does not need an extensive dataset for training like some methods that rely on computer vision or external sensors, it would not be as susceptible to failure when faced with unseen environments or new objects.In the future, the researchers want to try combining their method with computer vision to create a multimodal sensing technique that is even more powerful.“This work is not trying to replace computer vision. Both methods have their pros and cons. But here we have shown that without a camera we can already figure out some of these properties,” Chen says.They also want to explore applications with more complicated robotic systems, like soft robots, and more complex objects, including sloshing liquids or granular media like sand.In the long run, they hope to apply this technique to improve robot learning, enabling future robots to quickly develop new manipulation skills and adapt to changes in their environments.“Determining the physical properties of objects from data has long been a challenge in robotics, particularly when only limited or noisy measurements are available. This work is significant because it shows that robots can accurately infer properties like mass and softness using only their internal joint sensors, without relying on external cameras or specialized measurement tools,” says Miles Macklin, senior director of simulation technology at NVIDIA, who was not involved with this research.

With a novel simulation method, robots can guess the weight, softness, and other physical properties of an object just by picking it up.

System lets robots identify an object's properties through handling

A robotic hand developed at EPFL can pick up 24 different objects with human-like movements that emerge spontaneously, thanks to compliant materials and structures rather than programming.

Robotic hand moves objects with human-like grasps

MIT engineers are getting in on the robotic ping pong game with a powerful, lightweight design that returns shots with high-speed precision.The new table tennis bot comprises a multijointed robotic arm that is fixed to one end of a ping pong table and wields a standard ping pong paddle. Aided by several high-speed cameras and a high-bandwidth predictive control system, the robot quickly estimates the speed and trajectory of an incoming ball and executes one of several swing types — loop, drive, or chop — to precisely hit the ball to a desired location on the table with various types of spin.In tests, the engineers threw 150 balls at the robot, one after the other, from across the ping pong table. The bot successfully returned the balls with a hit rate of about 88 percent across all three swing types. The robot’s strike speed approaches the top return speeds of human players and is faster than that of other robotic table tennis designs.<iframe width="640" height="360" src="https://www.youtube.com/embed/FqyKfi_myLM?&amp;wmode=opaque&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" class="fr-draggable"></iframe>Now, the team is looking to increase the robot’s playing radius so that it can return a wider variety of shots. Then, they envision the setup could be a viable competitor in the growing field of smart robotic training systems.Beyond the game, the team says the table tennis tech could be adapted to improve the speed and responsiveness of humanoid robots, particularly for search-and-rescue scenarios, and situations in a which a robot would need to quickly react or anticipate.“The problems that we’re solving, specifically related to intercepting objects really quickly and precisely, could potentially be useful in scenarios where a robot has to carry out dynamic maneuvers and plan where its end effector will meet an object, in real-time,” says MIT graduate student David Nguyen.Nguyen is a co-author of the new study, along with MIT graduate student Kendrick Cancio and Sangbae Kim, associate professor of mechanical engineering and head of the <a href="https://biomimetics.mit.edu/" target="_blank">MIT Biomimetics Robotics Lab</a>. The researchers will present the results of those experiments in a <a href="https://www.arxiv.org/pdf/2505.01617" target="_blank">paper</a> at the IEEE International Conference on Robotics and Automation (ICRA) this month.<h2>Precise play</h2>Building robots to play ping pong is a challenge that researchers have taken up since the 1980s. The problem requires a unique combination of technologies, including high-speed machine vision, fast and nimble motors and actuators, precise manipulator control, and accurate, real-time prediction, as well as higher-level planning of game strategy.“If you think of the spectrum of control problems in robotics, we have on one end manipulation, which is usually slow and very precise, such as picking up an object and making sure you’re grasping it well. On the other end, you have locomotion, which is about being dynamic and adapting to perturbations in your system,” Nguyen explains. “Ping pong sits in between those. You’re still doing manipulation, in that you have to be precise in hitting the ball, but you have to hit it within 300 milliseconds. So, it balances similar problems of dynamic locomotion and precise manipulation.”Ping pong robots have come a long way since the 1980s, most recently with designs by Omron and Google DeepMind that employ artificial intelligence techniques to “learn” from previous ping pong data, to improve a robot’s performance against an increasing variety of strokes and shots. These designs have been shown to be fast and precise enough to rally with intermediate human players.“These are really specialized robots designed to play ping pong,” Cancio says. “With our robot, we are exploring how the techniques used in playing ping pong could translate to a more generalized system, like a humanoid or anthropomorphic robot that can do many different, useful things.”<h2>Game control</h2>For their new design, the researchers modified a lightweight, high-power robotic arm that Kim’s lab developed as part of the MIT Humanoid — a bipedal, two-armed robot that is about the size of a small child. The group is using the robot to test various dynamic maneuvers, including navigating uneven and varying terrain as well as jumping, running, and doing backflips, with the aim of one day deploying such robots for search-and-rescue operations.Each of the humanoid’s arms has four joints, or degrees of freedom, which are each controlled by an electrical motor. Cancio, Nguyen, and Kim built a similar robotic arm, which they adapted for ping pong by adding an additional degree of freedom in the wrist to allow for control of a paddle.The team fixed the robotic arm to a table at one end of a standard ping pong table and set up high-speed motion capture cameras around the table to track balls that are bounced at the robot. They also developed optimal control algorithms that predict, based on the principles of math and physics, what speed and paddle orientation the arm should execute to hit an incoming ball with a particular type of swing: loop (or topspin), drive (straight-on), or chop (backspin).<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1747231279859-MIT-PingPongRobot-03-press.jpg" style="width:100%px" class="fr-fic fr-dib" />The team fixed the robotic arm to a table at one end of a standard ping pong table and set up high-speed motion capture cameras around the table to track balls that are bounced at the robot. Here, it performs a back spin. Credit: Courtesy of the researchersThey implemented the algorithms using three computers that simultaneously processed camera images, estimated a ball’s real-time state, and translated these estimations to commands for the robot’s motors to quickly react and take a swing.After consecutively bouncing 150 balls at the arm, they found the robot’s hit rate, or accuracy of returning the ball, was about the same for all three types of swings: 88.4 percent for loop strikes, 89.2 percent for chops, and 87.5 percent for drives. They have since tuned the robot’s reaction time and found the arm hits balls faster than existing systems, at velocities of 20 meters per second.In their paper, the team reports that the robot’s strike speed, or the speed at which the paddle hits the ball, is on average 11 meters per second. Advanced human players have been known to return balls at speeds of between 21 to 25 meters second. Since writing up the results of their initial experiments, the researchers have further tweaked the system, and have recorded strike speeds of up to 19 meters per second (about 42 miles per hour).“Some of the goal of this project is to say we can reach the same level of athleticism that people have,” Nguyen says. “And in terms of strike speed, we’re getting really, really close.”Their follow-up work has also enabled the robot to aim. The team incorporated control algorithms into the system that predict not only how but where to hit an incoming ball. With its latest iteration, the researchers can set a target location on the table, and the robot will hit a ball to that same location.Because it is fixed to the table, the robot has limited mobility and reach, and can mostly return balls that arrive within a crescent-shaped area around the midline of the table. In the future, the engineers plan to rig the bot on a gantry or wheeled platform, enabling it to cover more of the table and return a wider variety of shots.“A big thing about table tennis is predicting the spin and trajectory of the ball, given how your opponent hit it, which is information that an automatic ball launcher won’t give you,” Cancio says. “A robot like this could mimic the maneuvers that an opponent would do in a game environment, in a way that helps humans play and improve.”This research is supported, in part, by the Robotics and AI Institute.

Time lapse photos show a new ping-pong-playing robot performing a top spin. The robot quickly estimates the speed and trajectory of an incoming ball and precisely hits it to a desired location on the table. Credit: Courtesy of the researchers

robotics

Latest Posts