In a humanoid surgical assistant robot demonstration hosted by Samsung Medical Center, the lead surgeon issued commands by voice only, and two humanoid robots, acting as an instrument-passing nurse and a camera-holding assistant respectively, collaborated to reproduce a cholecystectomy on a goat liver.
Tutor has unveiled its next-generation robots Cassie and Sonny, general-purpose robot workers designed for scenarios such as supply chains and warehousing; both models are already in use at production facilities in multiple locations across the United States.
In an interview, Xspark AI co-founder and chief scientist Ding Wenbo proposed that vision has already solved about 99% of robot perception problems, and that touch should form a low-latency, body-adjacent "spinal cord"-level model rather than being directly integrated into vision large models. He proposed a three-layer architecture of "slow brain VLM—fast brain VTLA+TWAM—spinal cord VTA," arguing that touch mainly serves collision-avoidance safety and post-training for dexterous manipulation, and noted that current bottlenecks lie in sensor consistency, tactile data representation, and unification across sensors, modalities, and embodiments.
At Logis-Tech Tokyo 2026, Damon Technology launched for the Japanese market its Flying Shuttle M-series ultra-multi-chute flexible sorting solution and an embodied-intelligence humanoid robot handling solution. The former offers over 1,000 chutes, a sorting efficiency of 14,400 items per hour, and 99.99% accuracy; the latter can be installed and deployed in just 2 weeks. The booth also showcased Damon's Flash Shuttle four-way shuttle plus AMR combined system and a narrow-belt sorter system. Damon has already delivered 30+ large-scale logistics automation systems in Japan, with customers including Sumitomo, Mitsubishi, Uniqlo, and Sagawa Express.
Chelsea Finn shared a video of a Pi robot deployed at Dandelion Chocolate, running fully autonomously with no human intervention. In her review, she said the hardest part was unexpectedly reliable stacking rather than box folding itself: the original table-mounted robot struggled to see the stacking state without a separately added camera, and each box was placed in a different position, with a misplacement causing the whole stack to collapse later.
Europe, meet the next generation of service robots. At IFA 2026, UniX AI demonstrated two real service scenarios: 🛒 Retail — Can a humanoid robot autonomously restock a micro-fulfillment center? 🏨 Hotel — Can it help prepare and tidy a room for the next guest?
AgiBot has released AGILE 2.0, a second-generation perception-driven locomotion and whole-body control framework that brings visual perception into the motion control loop and introduces a unified whole-body motion representation, supporting manipulation while moving, real-time replanning, and cross-robot coordination. In the demo video Acrobat BOT, the AGIBOT X2 completes tasks such as ball balancing, three-robot jump rope, and collaborative carrying; the framework also supports risk perception and autonomous recovery from disturbances in human-robot shared environments.
PKU EPIC Lab proposes UniPart, a feed-forward cross-modal 3D Transformer conditioned on CLIP text embeddings that uses free-text phrases to select functional parts on point clouds, achieving zero-shot language-driven 3D part segmentation.
Why it matters: The paper presents a text-driven 3D part segmentation method and a self-built dataset, and validates transfer to real-world language-conditioned grasping.
Tashi Intelligence released AWE3.7, an iterative version of its AWE series general embodied AI model, claiming cross-environment, cross-embodiment, and cross-task generalization, with the same model deployable on dual-arm collaborative robots, wheeled chassis, and humanoid robots. The materials show its performance in industrial scenarios, including parts sorting, tape wrapping, network cable insertion, phone boxing, screw tightening, drive belt grasping, and block sorting, as well as household tasks such as clothes folding, whiteboard wiping, and smoothie making, and claim that model-level changeover time has been compressed to the hour level.
Stial Robotics has won the bid for an AI flexible grinding project with a leading domestic rail transit sound barrier company; the workpieces are sound barrier columns up to 9 meters long. The solution uses the SeeV vision system to extract weld seams via 3D line laser scanning, with NextBrain™ AI automatically matching grinding trajectories and force control parameters. The end effector carries the PolishX flexible force control system and adopts hybrid force/position control technology, achieving contact force control accuracy of ±0.5% FS and capable of removing weld spatter particle residue up to 2 mm.
PKU EPIC Lab has released FoldNet++, a large-scale synthetic dataset for robotic T-shirt folding and unfolding, covering 6 robotic embodiments, 1K T-shirts, 1K environmental assets, and 120K richly annotated demonstrations.
Why it matters: The source gives the dataset scale and the real-world deployment success rate, so readers can assess the feasibility of training garment manipulation policies purely on synthetic data.
MIT CSAIL, together with Google and Northeastern researchers, launched InstructMesh, which combines TRELLIS with GPT-4 to let users repair AI-generated 3D models using natural language before 3D printing them.
Why it matters: The research presents a new tool and user experiment data, letting readers learn how ordinary users can repair AI-generated 3D models and complete printing.
The TP7 team was invited to showcase its dual-arm mobile AI robot at a Toyota internal supplier event; the robot can work alongside existing production lines without cages. It learns new tasks in minutes through vision and natural language and connects directly to existing production lines without reprogramming or changes to line layout. The original text did not disclose the robot's specific model, version, payload, or success rate metrics.
At the 26th China International Fair for Investment and Trade, Zhijian Dynamics exhibited the full-scenario embodied intelligent robot i7 Pro, the full-scenario service robot iX, a modular force-controlled humanoid arm, and the Simple Claw developer platform. In the supermarket retail scenario, i7 Pro runs the full unmanned retail process from tablet ordering to product delivery; in the smart logistics scenario, it autonomously performs waybill recognition, mobile grasping, flipping and adjustment, and sorting. The company says it is the industry's first enterprise to implement WAM on the edge-side Thor.
In the Kepler Bumblebee smart coffee cabin, the Bumblebee humanoid robot handles the entire coffee-making process. Powered by a self-developed VTLA (vision-tactile-language-action) omni-modal large model that coordinates and controls a professional coffee machine, it produces a cup in about 45 seconds, runs continuously for 8 hours on a 1-hour charge, and supports 24/7 unattended operation.
The Cell and BioRobotics Group (CBoRG lab) at the Technical University of Munich (TUM) Munich Institute of Robotics and Machine Intelligence (TUM MIRMI) proposes "Embodied Laboratory Intelligence," in which robotic assistants and virtual agents work together to explore the internal mechanisms of cancer cells.
NexArm ROS is an educational robotic arm designed for schools. It uses a dual-control architecture with an NVIDIA Jetson or Raspberry Pi host paired with an ESP32 controller, comes preinstalled with the OpenClaw agent, and supports voice and vision operations driven by large models such as Qwen and DeepSeek.
PKU EPIC Lab proposes GIF, an agentic generation framework for robot learning that reframes the problem as disentangled reconstruction followed by relative pose recovery. CoGen combines 2D and 3D generative models to produce instance-disentangled meshes and coarse initial poses; GPRM refines the relative poses under joint geometric and physical guidance; and a VLM verifier selects the candidate that best matches the structured specification.
Why it matters: The paper splits interactive and functional object composition generation into disentangled reconstruction and relative pose recovery, and provides a benchmark of eight contact-geometry classes along with collision-rate figures, which can help readers assess this route to simulation data generation.
The Institute of Automation of the Chinese Academy of Sciences, Zhongguancun Academy, and the CASBOT team propose World4RL, a policy optimization framework for robot manipulation that combines a diffusion world model with reinforcement learning, enabling robot policies to be optimized end-to-end in imagined trajectories generated by the model without additional real-robot interaction.
Why it matters: The paper turns the world model from a trajectory-prediction tool used at test time into a reinforcement learning training environment, giving readers a concrete path to understanding how the cost of real-robot interaction can be reduced.
At the 2026 XAIR Expo Embodied Intelligence Industry Expo, Zhido Future unveiled a technical preview of its differentiable world model "Zhizi World" (PGD World Model) and demonstrated validation progress on its embodied intelligent robot Xiaozhi S3. "Zhizi World" reconstructs particle-based scenes from short multi-view videos and can edit parameters such as object pose, material, mass, and friction to predict the physical outcomes of actions. S3 Xiaozhi features bionic dual arms, lidar-vision fusion navigation, and multimodal voice interaction; on-site demonstrations included scooping popcorn, filling cups and delivering them, and self-service retail shopping.
STIER has launched the PolishV series radial compliant spindle, featuring three main characteristics: high torque, precise force adjustment, and automatic tool change. The spindle delivers output torque of over 2.7 N.m and a floating torque of up to 24 N.m, providing 360° circumferential compliance and ±5° oscillating radial force, with floating accuracy of ±1 N, and supports automatic tool change in conjunction with a robot tool magazine. It has already been deployed in fields including liquid-cooling computing, chip manufacturing, aluminum alloy die casting, bearing manufacturing, medical devices, and 3C consumer electronics, and together with PolishX compliant force control and six-axis force sensors, forms its AI compliant grinding product system.
Stial has built a full-stack physical AI technology system spanning flexible force control, AI process decision-making, motion control, and robotic execution, focused on complex grinding, polishing, and deburring scenarios. Its PolishX flexible force control system can achieve contact force control accuracy of up to ±0.5% FS within the specified range and test conditions, and NextBrain™ AI Mushroom Cloud provides robot modeling, task planning, simulation, digital twin, and AI process decision-making capabilities. The related solutions have been applied in computing infrastructure, shipbuilding, auto parts, 3C electronics, and other fields, and have entered overseas markets such as Southeast Asia.
Physical AI company ZINOVA, using the LimX Dynamics TRON 2 dual-arm embodied robot, partnered with construction robotics company RIC Robotics to complete a scaled demonstration of a concrete tilt-up panel construction scenario, covering processes including formwork and frame assembly, and multi-layer rebar laying and tying.
[On-site case vol.63] Humanoid robots take over pharmaceutical packaging work / Bushu Pharmaceuticals | robot digest | a web magazine focused on industrial robots robot-digest https://www.robot-digest.com/contents/?id=1787123831-133424
PKU EPIC Lab published the ZETA study on arXiv (arXiv:2609.02546), proposing a unified definition of zero-shot cross-embodiment VLA transfer and a controlled benchmark covering 14 held-out target embodiments, distinguishing strict zero-shot transfer from pretrain-exposed transfer. Experiments show that local end-effector state-action representations, source embodiment diversity, and auxiliary co-training improve transfer by about 15, 18, and 7 percentage points, respectively, and that adding only 5% target-embodiment data during pretraining raises average target-embodiment progress by 13.4 percentage points.
Why it matters: The paper provides a unified definition of zero-shot cross-embodiment transfer and a controlled benchmark, allowing readers to understand the actual benefits of different representation and data strategies.
Huan'er Technology details the complete ROS 2 agent pipeline of the ROSOrin Pro robot: voice commands are recognized by WonderEcho Pro, then passed to the OpenClaw gateway for understanding and broken down into subtasks such as navigation, detection, and grasping.
X Square Robot releases TwinDEX, a pair of twin three-finger, nine-degree-of-freedom dexterous hands: one is wearable for data collection, and one is mounted on a robot for real-machine deployment, enabling dexterous manipulation driven purely by embodiment-free data with zero real-machine teleoperation data.
Why it matters: The original text provides specific design dimensions for consistency between the collection end and the execution end, along with a data-efficiency comparison, offering a transferable understanding of the engineering path for replacing real-machine teleoperation with embodiment-free data.
Stial has released an AI flexible wet grinding solution for repairing scratches and pits in titanium alloy plates. The process includes the SeeV AI perception system to identify defects, the NextBrain™ AI brain to plan grinding paths and process parameters online, and PolishX flexible force control to stabilize contact force, with wet cooling simultaneously carrying away grinding heat. Under the specified range and test conditions, the system's contact force control accuracy can reach ±0.5% FS. The solution transforms experience-driven grinding into a controllable process driven by data and algorithms, and the related technology has been applied in multiple high-end manufacturing fields such as shipbuilding, automotive parts, and 3C electronics.
ZINOVA, using LimX Dynamics' TRON 2 dual-arm embodied robot, partnered with RIC Robotics to complete a POC demo of a scaled concrete slab construction scenario, covering processes such as formwork frame assembly, and multi-layer rebar laying and tying. In the demo, two TRON 2 robots respectively held a nail gun and wooden boards to collaboratively assemble and secure the concrete formwork frame. TRON 2 supports human-machine collaborative teleoperation, with operators intervening at key points while accumulating data to lay the foundation for future autonomous capabilities and model training.
RoboScience has launched REX G1, a wheeled humanoid general-purpose manipulation robot equipped with its self-developed Visics general embodied large model built on the VLOA architecture, targeting scenarios including logistics, factories, retail, and homes. REX G1 has 22 degrees of freedom, can carry 10 kg with both arms, supports ±0.1 mm repeat positioning accuracy, is only 540 mm wide and can enter 0.75-meter narrow passages, and relies on 2070 TFLOPS of on-device compute to complete the perception, decision, and control loop.
STIAL's AI flexible grinding robots have recently won another bid for a flexible grinding line equipment upgrade project at a well-known domestic medical equipment manufacturer. The workstations have run continuously for tens of thousands of hours in real high-load production lines. In processing tens of thousands of structural parts, the oxide layer removal rate reached over 99%, substrate scratch rate was kept within 0.1%, and pre-coating preparation yield rose from 85% to 98%. A single machine replaces 3–4 skilled grinding workers, grinding efficiency is more than 3 times higher, and processing time per part is shortened by 42%.
At the "Embodied Intelligence, Data Elements, Vertical Applications" industry ecosystem exchange event at the 2026 China International Big Data Industry Expo, CASBOT CEO Yang Ping delivered a keynote speech titled "Bringing Data into the Physical World: A New Data-Driven Path for Embodied Intelligence," proposing that the value of embodied intelligence data must be built on real scenarios, real data, and real industrial capabilities.
In the "Assembly and Loading Station" event of the 2026 World Humanoid Robot Games Industrial Scenario Competition, Lingxi Zhihong's robot completed three tasks fully autonomously: transporting and shelving, picking and loading, and sub-millimeter assembly of 18 engine valves, scoring 84, 65, and 21 points respectively. After a 10-point special deduction, it finished with a total score of 160 points, ranking second only to two teams under a leading industry robotics company in the enterprise rankings, making it the only startup to break into the national top three on its first participation.
Tashi Intelligent's industrial embodied robot cluster was featured on CCTV's Xinwen Lianbo. The company worked with a leading automotive manufacturer to tackle flexible automotive assembly challenges, using the AWE general-purpose embodied large model to empower real production lines and achieve large-scale robot deployment.
The 3rd Tsinghua University Embodied Intelligence Challenge (THUEI-3) is recruiting teams from undergraduate and graduate students at universities nationwide. It features two tracks, gripper and dexterous hand, each including basic tasks, optional advanced tasks, and innovation challenges that test robots' abilities in recognition, localization, grasping, placement, and assembly. The gripper track uses the full set of equipment and competition scheme from the company Zibianliang Robotics, which also offers a separate special award: the first prize is two high-performance six-axis robotic arms. Combined prize money for the two tracks totals 70,000 yuan. Registration runs from August 27 to August 31, with 2–5 members per team and cross-university teams allowed.
Lingchu Intelligence announced the completion of a new funding round of over $100 million. Investors include Tuopu Group, Ruicheng Fund under Chery Holding, Lens Technology, 37 Interactive Entertainment, Wuhu Municipal Investment Holding Group, and Fosun Chuangfu, while existing shareholder Zhuhai Technology Industry Group made an excess additional investment. The proceeds will focus on embodied world model R&D and commercial deployment in logistics and advanced manufacturing scenarios. The company's self-developed dual-system architecture comprises the Psi-R2 manipulation policy model and the Psi-W0 action-conditioned world model, and it plans to expand the scale of human data collection and accelerate the layout of data collection facilities.
Why it matters: Lingchu Intelligence officially announced the completion of the funding and stated that the funds will go toward world model R&D and commercialization in logistics and manufacturing scenarios, giving readers insight into its industry-finance resource layout.
Galbot's G1 robot won gold in all three of WHRG's most challenging scenario competitions: household, food service, and retail. It operated autonomously throughout, with a 100% win rate. The household competition covered tidying, laundry, pick-and-place delivery, and long-horizon tasks that included unexpected interruptions; the food service competition involved understanding voice commands, food handling and heating, drink preparation, and delivery; and the retail competition included picking, restocking, store patrols, and returning misplaced products to their correct positions.
Shihang Intelligence released the world's first ocean embodied large model, "Cangqiong CEORION," trained on a combination of real operations and simulation data; in simulation tests, its task success rate exceeded 90%, and its fine-control positioning and grasping success rate exceeded 90%. Its self-developed magnetic coupling thruster has a rated lifespan exceeding 10,000 hours, and its deployment and recovery system increases operational efficiency 10-fold. The "Orca" series robots have achieved routine integration of ship inspection and cleaning services for vessels entering and leaving ports at core hubs such as Yantai Port, and order value exceeded 1 billion yuan in the first half of 2026.
The intelligent loading system developed by Boshi has been officially completed and commissioned at PetroChina Lanzhou Petrochemical Yulin Branch, becoming another implemented case in its petrochemical intelligent logistics field. The system integrates 3D vision, LiDAR, and deep learning, and can accommodate mainstream transport vehicle models on the market, with a complete loading operation per vehicle taking about 36 minutes. As of August 23, after two weeks of operation, it had completed the loading and outbound shipment of 5,181 tons of high-density polyethylene products, with all operating indicators meeting the project design requirements.
Philips announced it has received up to $33.7 million in funding from the U.S. ARPA-H Autonomous Interventional and Robotics (AIR) program to advance automation of AI robotic surgery for stroke treatment.