Part 06 of the Dexterous Hand in Practice series discusses how STM32, ESP32, and Raspberry Pi divide responsibilities in dexterous hand control. The content centers on the roles each of these three types of control boards plays, and it is a tutorial-style article in this hands-on series.
According to foreign media reports on October 31, Meta partnered with Chinese robotics company Fourier Intelligence to develop a humanoid robot prototype named Max in only about three months, and a second-generation product is already in development. Max is about 1.5 meters tall and weighs 48 kilograms, is equipped with an NVIDIA Jetson Thor chip, has five-fingered dexterous hands and a display that can simulate human facial expressions, and needs to recognize voices and gestures and maintain eye contact with people.
At the 88th China Education Equipment Exhibition, Gaoqing Dynamics unveiled its first comprehensive embodied intelligence education solution and presented the Mini Pi plus humanoid robot. The solution uses the Mini Pi plus as its carrier and includes tiered lesson plans for all grade levels, project task packages, a teaching platform, and instructor training; it is already running as a regular course at schools including Beijing Renmin University Affiliated High School and Dongzhimen High School. A graphical programming area was set up at the exhibition, where students can drag and drop modules to send commands and observe the robot's responses in real time.
The Yomin LKZ series of liquid aluminum electrolytic capacitors targets space-constrained, high instantaneous current scenarios in robot joint motor controllers, using a single high-capacitance unit to reduce the number of MLCCs in parallel. Taking the LKZ 100V 150μF 8×25 as an example, a single unit has a nominal 150μF, typical ripple of 900mA, and ESR of about 0.20Ω; four in parallel in the example reach 600μF. The solution can be used for board-level filtering and transient energy storage evaluation; whether it applies must be verified against the BOM, operating conditions, and full-system testing, and the manufacturer offers free samples and Demo board testing.
Shanghai Sage Intelligent Technology has completed a Pre-B funding round worth hundreds of millions of yuan, with investors including Jiantou Investment, Nantong Investment Management, and Yunqi Capital. The funds will be used for large-model R&D, iteration of multi-arm robot bodies, production line expansion, and overseas market development. The company has built a body matrix spanning single-arm to six-arm robots; its six-arm robot "Xuanjia" uses a spatially heterogeneous design, and the company has released an industrial world model, Xuanshu·SageNexus (WASM). Its customers cover four major industries—3C and semiconductors, automotive, energy, and food and pharmaceuticals—with more than 50 Global Fortune 500 or listed-company customers and overseas intended orders exceeding 500 million yuan.
According to The Information, Meta has partnered with Chinese manufacturer Fourier Intelligence to develop a humanoid robot prototype named Max, and development of a second-generation Max 2 has already begun. Max is about 1.5 meters tall and weighs about 48 kilograms, is equipped with the NVIDIA Jetson Thor computing platform, has a head that can simulate human facial expressions, and has five-fingered dexterous hands capable of grasping small objects such as bottles and toys.
Flexible tactile sensor company Saigan Technology has completed a Pre-A++ funding round of tens of millions of yuan, exclusively invested by Guangzhou Industrial Holdings Donggao Fund, with proceeds going toward iontronic flexible technology R&D and next-generation product iteration. The company has secured its first batch of orders, to be deployed in automotive manufacturing; its iontronic flexible tactile sensors have a detection limit of about 1 milligram and a response frequency of up to 1KHz, and are delivered as fingertip modules with factory calibration completed.
The REEMAN Fly Boat AMR achieves cross-floor material transport through an elevator integration module: the robot can autonomously call, enter, ride, and exit elevators without human assistance. The model has a rated payload of 300 kg and autonomous jacking of 10 cm, uses LiDAR SLAM navigation, has positioning accuracy of ±5 cm (±3 cm with reflectors, ±2 cm with QR codes), and a travel speed of 0.3–1 m/s.
REEMAN autonomous forklifts use laser SLAM navigation and can connect to existing WMS, MES, and ERP systems without magnetic strips or QR codes; the integration focus is on location mapping and open API connectivity rather than rebuilding navigation infrastructure. The guide covers site surveys, map creation, task triggering, and multi-vehicle fleet scaling. Each model is rated for 6 hours of continuous operation (fully loaded)/8 hours (empty), supports automatic return to charging, and some models allow manual battery swapping.
China's first intelligent welding equipment set dedicated to pressure steel pipes in ultra-deep vertical shafts has officially entered service at the Songyang Pumped Storage Power Station in Zhejiang, according to China Three Gorges Corporation. The equipment is equipped with an outer circumferential seam welding robot and an inner circumferential seam automatic horizontal welding machine, and features 5G control, laser weld seam tracking, and a welding expert database, enabling it to automatically identify weld seam positions and match welding parameters. Welding speed reaches 30 to 50 centimeters per minute, efficiency is more than 65% higher than traditional manual welding, and the one-time pass rate for weld seams is 99%.
In the first CMG World Robot Mount Tai Climbing Competition, which began on November 2, a Unitree G1 Developer Edition robot of the same model seen on the Spring Festival Gala withdrew due to an overheating fault and was carried down the mountain by staff on a stretcher. The course is 3.9 kilometers long with more than 3,100 steps, and other robots on site climbed unsteadily and needed towing assistance to complete the race.
The Robot Report rounds up its 10 most popular robotics stories of October 2026: Gecko Robotics received a $300 million addition to its U.S. Navy and General Services Administration contract, quadrupling the contract ceiling.
At WTCC 2026, Arm China's Jishu Community released the open-source AIOS platform JishuFriends, along with its first prototype robot dog Puppy, and JishuBuddy, an AI hardware development tool for Agentic AI.
Shanghai flexible tactile sensing company Lingshu Zhifu announced the consecutive completion of its seed round and angel round. The seed round was co-invested by Oriza Holdings and Huawei Hubble, and the angel round was followed on by Oriza Holdings. The two rounds raised over ten million yuan. For embodied intelligence, the company launched finger tactile sensors that can be used in tactile data collection gloves and dexterous hands, as well as a "fingertip + palm sensor" module, supporting point touch, long press, sliding, and tangential force sensing. It says it has completed dual-85 testing and more than 10 million repeated mechanical tests. Lingshu Zhifu was founded in 2025 and is currently building a materials pilot line and sending samples to customers in multiple fields.
Meta has partnered with Fourier Intelligence to develop a humanoid robot prototype named Max, internally defined as the physical embodiment of its personal AI agent Muse. The prototype was completed in three months, and second-generation development has already begun. Max is about 1.5 meters tall and weighs 48 kilograms, and carries an NVIDIA Jetson Thor chip to support on-device running of vision-language-action models. It builds on Fourier's GR-series chassis and motion control capabilities, with newly customized head, screen, camera, and hand and foot modules.
A University of Bristol team built a tabletop physical model simulating muscle contraction using a row of ordinary electric motors coupled to each other through a shared mechanical skeleton, with results published in the Royal Society journal Interface. In the experiments, the motors made intermittent contact with the skeleton to transmit force, and without direct communication, muscle-like behaviors spontaneously emerged, including a load-velocity relationship, more units participating as load increased, and coordination waves. The researchers believe this approach, in which coordination is handled by the structure itself, could help improve how robots are actuated.
To address the selection challenges of space constraints and high instantaneous current in robot joint motor controllers, the Yongming LKZ series liquid aluminum electrolytic capacitors use a single high-capacitance unit to reduce the number of parallel connections. Taking LKZ 100V 150μF 8×25 as an example, a single unit provides 150μF, typical ripple 900mA, and ESR of about 0.20Ω; an example configuration of 4 in parallel reaches 600μF, which can reduce layout pressure. The solution also offers vibration resistance, wide temperature range, and low ESR; whether it applies must be verified against the BOM, operating conditions, and full-machine testing, and the manufacturer offers free samples and Demo board testing.
Orbbec's 2026 Q3 report shows robot vision solution revenue reached more than double the year-earlier level, cumulative robot customers exceeded 1,000, and the delivery cycle was compressed from about 40 days to 20 days. First-three-quarter revenue was 711 million yuan, down 0.43% year on year; net profit attributable to shareholders was 73.8615 million yuan, down 31.62% year on year; gross margin rose from 42.8% to 49.09%; and R&D investment was 175 million yuan, up 19.20% year on year.
According to The Information, Meta has partnered with Fourier Intelligence to develop a humanoid robot prototype named Max, completing development in three months, and has already started work on a second-generation Max 2. Max is about 1.5 meters tall and weighs about 48 kilograms, is equipped with Nvidia's Jetson Thor computing platform, and has five-fingered dexterous hands that can grasp small objects such as bottles and toys; Meta requires it to recognize human voices from 5 meters away, detect waving gestures from 3 meters away, and maintain eye contact.
STIER's AI flexible grinding robot has won the bid for an intelligent flexible grinding project for aviation material repair, entering the complex grinding scenarios of aviation maintenance (MRO). Addressing the issues of diverse aviation material categories, large differences in wear deformation, and difficulty in forming standardized machining benchmarks, STIER builds a full-stack solution with multimodal environmental perception, multi-source heterogeneous data analysis, intelligent decision-making, and precise execution, enabling self-analysis of workpiece features, self-generation of grinding paths, and intelligent matching of process parameters. Its PolishX flexible force-controlled actuator achieves force control accuracy of ±0.8N, adjustment response <10ms, and contact force accuracy of ±0.5% FS.
A new IDTechEx report, "Batteries for Humanoid Robots 2027-2037," predicts that demand for humanoid robot batteries will reach 10.5 GWh by 2037. Currently, NMC-based lithium-ion batteries are the most commonly used in humanoid robots, as they balance high energy density, fast charging, and cycle life; the report also evaluates solid-state batteries (about 400-500+ Wh/kg, with mass production expected in the late 2020s) and lithium-sulfur batteries (commercialization expected in the early 2030s) as future options.
The article addresses the backlash and lost motion problem in robot joint reducers by building a dual-inertia backlash transmission model described with a Play operator, and designing a direction-reversal state machine with rate-limited feedforward compensation. It quantitatively compares three control schemes through three sets of experiments and provides a Python simulation implementation path.
The Information reports that Meta has jointly developed a humanoid robot prototype codenamed Max with Fourier Intelligence and has started development of a second-generation Max 2. The Max prototype is about 1.5 meters tall and weighs 48 kilograms, is equipped with Nvidia's Thor chip, and is positioned as the physical embodiment of Meta's Muse large model, with the goal of entering home scenarios. The project took only three months from initiation to the first prototype, which was shipped back to Silicon Valley at the end of August this year and completed a dynamic demonstration at Meta's internal robotics summit.
VanJee LiDAR has launched the TunJing Max WLR-751, a stereo 3D camera for embodied intelligence and industrial automation, featuring a 108°×80° field of view, a recommended working distance of 0.2–6 m, and onboard AI object detection. Both the depth and RGB images support output at up to 1280×800 resolution at 30fps. The company claims depth error within ±0.8% at a distance of 2 m, and the camera supports 60fps customization and multi-camera synchronization better than 100μs.
Suzhou sandisiwei has launched the Jingxun V4 research-grade structured light scanner, featuring a measurement-grade DLP4710 optical engine, interchangeable C-mount lenses, and a Hikvision 14MP global camera, with CUDA acceleration throughout reconstruction and point cloud processing. The V1 to V4 series all offer open-source modules and support secondary development with libraries such as OpenCV, Halcon, and VisionMaster, and can be combined with robotic arms for vision guidance and measurement. The device targets 3D reconstruction of diffuse-reflection objects and comes with structured light reconstruction and PCL point cloud courses.
Robots from about 90 teams competed in the first World Mountain Robot Challenge on Mount Tai, on a 3.9-kilometer course with over 600 meters of elevation gain, requiring them to race or carry fragile items such as eggs and watermelons to the summit. A quadruped robot from Beijing Lingyi Technology (a Unitree subsidiary) won the quadruped speed category in 43 minutes 41 seconds, while a humanoid robot from the Beijing Zhishen Lingyue team completed a shorter course in 27 minutes 26 seconds. The event was hosted by China Media Group and included awards such as Fastest Robot and Best Load-Bearing Quadruped Robot.
The developer modified the Sesame robot's main frame to accommodate 2 18650 batteries and rerouted the wiring, cutting excess wire and re-crimping the connectors. A new mainboard was also built using perfboard to make future modifications easier.
REEMAN built a custom food delivery robot based on the Hot Wheels robot chassis (model WBOT11B), featuring a two-layer transparent enclosed compartment and supporting single-point and multi-point autonomous delivery as well as automatic charging at low battery.
At its CeMAT booth, Weimaier lists four things to check out: teleoperating a humanoid robot via VR to interact with VB2, experiencing the new V400 (basic mapping and deployment completed in 30 minutes), watching the H6's omnidirectional movement and 360° environmental perception chassis, and seeing the 120mm ultra-thin underride robot and the cage-cart handling robot. The exhibition runs November 3–6, 2026, at Booth C3-3, Hall N1, Shanghai New International Expo Centre. Weimaier is also showcasing its self-developed general-purpose core controller for mobile robots, which integrates a core processor, IO control, bus communication, and power management.
At the 2026 China Automation Congress, Kyland Technology exhibited its Physical AI solutions and a fully domestically produced embodied intelligent robot electronics architecture. The architecture integrates the Hongdao Intewell industrial operating system, the AUTBUS deterministic industrial bus, MaVIEW agent tool software, and domestic AI processor chips. In on-site technical tests organized by the National Industrial Information Security Development Research Center, robots equipped with this architecture passed tests related to fault isolation, cybersecurity, and real-time control under scenarios including joint power loss, simulated network flooding attacks, and simulated Trojan virus infections.
The 2026 Physical AI and World Models Conference was held in Nanjing, where Andrew Yao noted that reliability is the threshold physical AI must cross to move from demonstrations to real-world deployment. In September, Kuangda Technology released its first-generation flexible fabric skin system solution for embodied intelligent robots, which has already been delivered in small batches to some leading companies; the second generation is advancing multimodal sensor integration and operating-condition validation. GGII (Gaogong Industry Research Institute) forecasts that by 2030, global demand for flexible tactile sensors for humanoid robots will reach 1.525 million square meters, with a market size of about 27.4 billion yuan.
Animotion Robotics has announced progress on Éloi's lip-sync control; in English, Korean, and Japanese tests, its lip and jaw movements can now reproduce natural human pronunciation relatively accurately. The system is still being improved for movement precision and naturalness, and the next step is planned to use exaggerated mouth movements to demonstrate the expressiveness and flexibility of the 17 degrees of freedom shared by the lips and jaw.
At its AI DAY on October 29, Critical Point announced that cumulative production of its dexterous hands has surpassed 15,000 units, and launched its self-developed data-collection glove, OmniGlove Pro. The glove uses a fusion of EMF magnetic field positioning and IMU, achieves fingertip positioning accuracy of 0.1 mm, is equipped with 746 tactile sensing points, and has a tactile spatial resolution of 3 mm. The company also introduced the "real-machine Ready" concept, spanning from data collection to real-machine replay.
The REEMAN Ironhide 3.0 is a 1.5-ton laser SLAM AMR forklift that can autonomously identify pallets, position its forks, lift and transport loads, and place goods without reflectors or floor tape. In a case at a new energy factory in Huzhou, it completes about 160–200 pallet transports per day along a 47-meter route, runs continuously for 6 hours fully loaded and 8 hours empty, and supports 1-hour fast charging and automatic return to charge.
REEMAN compares the official rated specifications of three laser SLAM navigation AMR forklifts: Ironhide 3.0, HAMMER 2.0, and Rhinoceros. Ironhide 3.0 is a 1.5-ton flatbed transport vehicle; HAMMER 2.0 is a 1.2-ton stacker that supports battery swapping and Tianzi pallets; Rhinoceros is a 1.5-ton narrow-body stacker with a 2.5-meter lift.
The authors present MUSBRIC, a modular hardware platform and accompanying MuJoCo simulator for reconfigurable musculoskeletal robots, which uses LEGO-compatible endcaps to turn fiber-reinforced extensile pneumatic artificial muscles into reusable, plug-and-play muscle modules. An elbow-joint prototype validated load-dependent flexion and extension, with pulley-guided routing enabling reversible motion and a mechanical stop stabilizing the straight posture; a robotic hand demonstrated compliant grasping and multi-joint construction, 15 leg configurations completed matched sweeps in hardware and simulation, and a quadruped assembled from four legs achieved walking. The hardware design and simulation code will be open-sourced.
This study proposes Gaussian Evolutionary Specialists (GES), a reinforcement learning-based co-design framework. By maintaining a population of specialist policies whose design-space territories evolve according to their control performance, it mitigates behavioral diversity collapse, in which a single shared policy converges to the same control strategy across different morphologies.
A research team has released an open-source knee exoskeleton built from off-the-shelf components, whose biological torque controller is generated entirely by simulation, requiring no training data collected on the target device. The method uses a muscle-driven imitation policy to reproduce squatting motions from a public biomechanics dataset, then distills the knee joint torque into an estimator that relies only on onboard sensors.
An arXiv study used an elbow-assist exosuit to examine the physiological, perceptual, and cognitive consequences of force augmentation during lifting, finding that although assistance reduced muscle activity, behavioral outcomes did not simply correspond to this biomechanical change. Assistance reduced perceived weight, but this effect was strongly shaped by participants' initial experience; assistance also selectively reduced adaptation to changes in environmental conditions, and differences in effort-based decisions were likewise shaped by initial experience rather than simply following the decline in muscle activity or perceived fatigue. The authors therefore argue that the perceptual and cognitive consequences of force augmentation cannot be inferred from biomechanical benefits alone and must be assessed alongside physical performance.
Shanghai Lingshu Zhifu has completed consecutive seed and angel funding rounds, with participation from Oriza Holdings and Huawei Hubble, totaling over 10 million yuan across the two rounds; Linglu Capital served as exclusive financial advisor. Founded in April 2025, the company focuses on ionic-skin flexible tactile sensing materials and devices, with products including data-collection gloves and tactile sensors for dexterous hands. It has completed dual-85 testing and over 10 million repeated mechanical tests, is building a materials pilot line, and is sending samples to customers in multiple fields.