Skip to content
#Data and simulation
Oct 10Sat
  1. Leiphone Robotics72

    Columbia's Yunzhu Li team presents progress and ecosystem of open-source tactile sensor FlexiTac at IROS 2026

    At the tactile-themed workshop at IROS 2026, Columbia University's Yunzhu Li team presented progress roughly a year and a half after the open-sourcing of FlexiTac, an open-source flexible piezoresistive tactile sensor. The sensor uses a layered structure of FPC and force-sensitive film and can be assembled in 3 minutes after parts are prepared; the team open-sourced the complete BOM, assembly instructions, and reading software and integrated it into the LeRobot framework. Simulation adaptation requires calibrating only 3 hyperparameters of a spring-damper system.

  2. Chelsea Finn51

    Chelsea Finn shares Mulligan paper: the more reliable the robot, the less efficient DAgger data collection becomes

    Chelsea Finn points out that as robots become more reliable, DAgger-style data collection efficiency drops sharply; for example, a 90% success rate means a human spends more than 90% of the time as a passive observer. The Mulligan paper she cites proposes the key idea that failures often come from similar initial states, so learning can be focused on these states; in deployment, the robot performs the task and the human intervenes when needed, with each collection round focusing on the initial states where the robot fails. Across 3 real tasks and 2,550 blind tests, it outperformed uniform collection under the same budget. Paper: https://arxiv.org/abs/2610.05882 .

Oct 9Fri
  2. The Robot Report64

    SafeWorld exits stealth mode with $12.2 million seed round to build robot safety simulation

    SafeWorld has exited stealth mode and announced a $12.2 million seed round co-led by Shine Capital and a16z Speedrun. Its platform builds scenarios in the browser based on historical incidents, safety standards, and robot logs, then runs thousands of variants with realistic reactive human motion to test robot safety performance, covering robotic arms, humanoids, and mobile robots, with customers across industrial, manufacturing, logistics, construction, and home scenarios. The funding will be used for enterprise outreach, team expansion, and advancing AI safety research.

Oct 8Thu
  1. Robotics 24/766

    Amazon releases open-source Physical AI Toolchain on AWS

    Amazon has released the open-source platform Physical AI Toolchain on AWS, integrating NVIDIA's physical AI stack and covering five stages: synthetic data generation, model training, simulation validation, edge deployment, and continuous improvement. Customers can adopt the whole platform or select components as needed, and use fleet management capabilities to manage thousands of machines via over-the-air updates. The platform's architecture guidance draws on Amazon's own experience operating more than 1 million robots, helping manufacturers launch physical AI capabilities within weeks.

  2. Tech Xplore Robotics36

    How Automation Is Shaping the Future of American Manufacturing: Smart Automation Practices at ORNL's Manufacturing Demonstration Facility (MDF)

    Researchers at Oak Ridge National Laboratory's (ORNL) Manufacturing Demonstration Facility (MDF) are designing and validating smart automation systems that can sense their environment in real time and respond to changes, aimed at high-mix, low-volume production needs to expand the capacity of a constrained workforce.

  4. 机器人daily · 微信公众号61

    The 4D world model direction backed by Fei-Fei Li is now running successfully in factories through Yingshen Intelligence

    The article uses AMD's announcement of an all-stock acquisition of Fei-Fei Li's World Labs for about $8.2 billion as an entry point to compare Yingshen Intelligence's approach of betting on native 4D world models since its founding. Yingshen Intelligence's self-developed "Yingshen 360" capture system uses 4 to 6 consumer-grade RGB cameras to achieve millimeter-level, 25 frames per second real-time 4D data generation, reducing overall hardware costs by more than 90%; in the 4D foundation world model "Pojie S1", the GAF Gaussian Action Field achieves an average success rate more than 10 percentage points higher than the previous best method on dynamic manipulation tasks.

Oct 7Wed
Oct 5Mon
  1. HuggingFace Daily Papers53

    SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models

    SimForcing proposes a simulation-guided framework that injects motion knowledge from a simulation teacher into an action-conditioned robot world model through latent-variable distillation, mitigating appearance differences and reducing the extent to which inaccurate simulation predictions mislead real-video generation.

Oct 2Fri
  1. Robohub31

    Robot Talk Episode 164: Accelerating Robot Learning with Michelle Lu

    Michelle Lu, co-founder and CEO of Vsim Technology, discusses using simulation and artificial intelligence to teach robots new skills on the podcast. She previously served as Director of Simulation Technology at NVIDIA, where she and her co-founder developed Isaac Gym, the first end-to-end GPU-accelerated reinforcement learning framework. In 2022, the two left NVIDIA to found Vsim, aiming to address limitations in efficiency, scalability, and the sim-to-real gap in simulation-based robot AI.

Sep 30Wed
  1. Robotics 24/751

    Innodata and Vicon Open Motion Capture AI Lab to Provide Training Data and Independent Performance Validation for Humanoid Robots

    Data engineering company Innodata announced the opening of a research and development lab in New Jersey, designed in collaboration with motion capture technology company Vicon, which will provide ongoing technical consulting. The lab is equipped with high-precision, low-latency infrared optical tracking cameras that can measure 3D motion data at sub-millimeter accuracy and millisecond latency, used to generate physical AI training data for humanoid and industrial robots, and to support cross-platform motion retargeting. Customers can purchase ready-made motion capture data packages or custom projects, and can also send robots to the lab for evaluation, where external calibrated cameras verify internal telemetry data, providing an independent third-party benchmark.

  2. Leiphone Robotics64

    Yuansheng Intelligence's Yang Sicheng: Before Embodied Model Capabilities Break Through, Dexterous Hands Must First Compete on Performance

    In an interview, Yuansheng Intelligence founder Yang Sicheng proposed that when model capabilities are not strong enough, hardware capabilities must be very strong, and only after models break through can dexterous hands simplify. Its self-developed Apex Hand uses an in-palm hybrid tendon-driven scheme, has 21 degrees of freedom, a maximum single-hand active payload of 30 kg, and an open-close time of about 0.2 seconds, and was carried by the gold, silver, and bronze medal teams in the heavyweight categories of weightlifting and tug-of-war at the 2nd World Humanoid Robot Games in August 2026. He emphasized prioritizing reliability and dexterity, using unidirectional tendon drive plus end encoders to compensate for creep, and believes the endgame for dexterous hands is a reliable general-purpose productivity tool.

  3. Leiphone Robotics59

    X Square Robot releases TwinDEX embodiment-free data collection system, with hundreds of data samples supporting a 24-step chemistry experiment demonstration

    X Square Robot has released the TwinDEX system, consisting of a wearable embodiment-free data collection kit, a matching robot end effector, and data processing and policy training pipelines. Using hundreds of purely embodiment-free data samples (none from a real robot), the robot completed a chemistry experiment in a single continuous take, performing 24 sub-actions including opening a bottle and sampling, dropper operation, guiding liquid with a glass rod, and shaking to mix.

  5. Robotics 24/749

    IROS 2026: Daimon Robotics showcases tactile intelligence infrastructure for physical AI

    At IROS 2026, under the theme "From Touch to Intelligence," Daimon Robotics publicly demonstrated its tactile intelligence infrastructure on real hardware for the first time, covering three layers: the DM-Tac series of vision-based tactile sensors (more than 12 tactile modalities and over 110,000 sensing units), the Data-Nexus data collection system, and the Daimon-TWM world model released in August.

  6. 北京智在无界科技有限公司58

    Being-H0.7 from ZhiZaiWuJie accepted to NeurIPS 2026, Being-H series completes ICML, CoRL, and NeurIPS acceptances within one year

    Being-H0.7, the general-purpose dexterous manipulation large model independently developed by ZhiZaiWuJie, has been accepted to NeurIPS 2026, marking the Being-H series' completion of acceptances to the three top conferences ICML, CoRL, and NeurIPS within one year.

Sep 29Tue
  1. Sharpa59

    Sharpa launches D01 tactile robot, W02 dexterous hand, and AE01 data glove at IROS 2026

    Sharpa launched three products at IROS 2026: the D01 manipulation robot with integrated tactile sensing, featuring an end-effector speed over 10.5 m/s, repeatability of 0.2 mm, and electronic-skin tactile sampling at 100 Hz; the W02 fully tactile compact dexterous hand, with 21 active degrees of freedom, about 30% smaller than the W01, and fingertip force sensing from 5 mN to 30 N; and the AE01 high-fidelity tactile exoskeleton data glove, which uses 22 encoders for teleoperation and data collection and supports 256-level continuous tactile feedback per fingertip.

Sep 28Mon
  1. Leiphone Robotics59

    Shutu Technology completes nearly 100 million yuan Pre-A funding round, securing three rounds of investment within one month

    Shutu Technology has completed a nearly 100 million yuan Pre-A funding round, co-led by CDH Baifu and Kunpeng Fund, with joint investment from Guangzhou Industrial Investment and Yihe Capital, and an oversubscribed follow-on investment from existing shareholder Qushi Investment; this is the company's third funding round within one month. The funds will be used for R&D on tactile data representation training, to drive iteration of the SynaTac tactile product line, and to expand business for robot contact strategy training and on-device deployment; the company also publicly unveiled for the first time its embodied data and skill evaluation system covering three stages: data metric evaluation, trainability evaluation, and task and real-environment validation.

  2. Leiphone Robotics58

    Sharpa unveils D01 humanoid robot, W02 dexterous hand, and AE01 data glove at IROS

    Sharpa unveiled three fully self-developed new products on-site at IROS in Pittsburgh: the tactile-sensing dexterous manipulation robot D01, the dexterous hand W02, and the exoskeleton tactile data glove AE01. D01 has a maximum end-effector speed exceeding 10.5 m/s, repeat positioning accuracy of 0.2 mm, and is equipped with a full-body electronic skin; W02 integrates 21 active degrees of freedom and is about 30% smaller than W01; AE01 includes 22 encoders and 256-level tactile feedback per fingertip, for teleoperation and data collection. The IROS exhibition runs until October 1 Beijing time, at booth 514.

  3. PsiBot/灵初智能66

    Lingchu Intelligence releases Psi-R2.5, using strong Pair Data to solve human-machine data alignment challenges

    Lingchu Intelligence has officially released its embodied model Psi-R2.5, which uses a two-tier architecture with a QwenVL3.5-4B high-level planner plus a Wan2.2-IT2V-5B low-level controller, and proposes the strong Pair Data standard. The model reverse-invokes the Psi-W0 world model to generate human demonstration videos backward from real-robot data, enabling mass production of paired data, and supports in-context learning (ICL) for zero-shot generalization to new tasks. It comes with a HIL+RL post-training framework and is claimed to raise task success rates to 99% after a few iterations taking only 1-2 working days, and has already been deployed at customer sites.

    Why it matters: The original article details the model architecture, the strong Pair Data data standard, and the reverse-generation method, letting readers understand how its data approach supports real-robot generalization.

Sep 27Sun
  1. 鹿明机器人 · X45

    Lumos Robotics releases Lumos Ego Vue head-mounted data collection device

    Lumos Robotics has launched the Lumos Ego Vue, a head-mounted first-person multimodal data collection device designed to turn real-world operational experience into structured skill data usable for robot learning. The device supports binocular first-person capture, high-precision hand tracking, and multimodal time synchronization, and can collect real task workflows and operational data. When connected to Lumos NexCore, the data pipeline covers multi-source data input, quality control and preprocessing, scene semantic understanding, spatial intelligence modeling, and standardized skill data delivery.

Sep 25Fri
  1. 简智机器人 · X48

    Gen-HumanEgo open-source robot training dataset

    Run it now 👉 https://www.genrohub.com/blog/gen-human-ego Quoted tweet highlights: Introducing Gen-HumanEgo, a more readily usable open-source egocentric human dataset for robot learning. Powered by its Data Foundation Model (DFM), synchronized egocentric video is converted into ready-to-use signals: video, motion, robust hand tracking, depth, and semantic annotations are precisely aligned and encoded into unified tokens, forming a shared representation. It aims to turn real-world human experience into ready-to-use training data to help models learn better—Gen-HumanEgo is the starting point. #EgoData #Opensource #EmbodiedAI

  2. Mondo HK Limited · X62

    Mondo Robotics open-sources Beni reinforcement learning environment

    Mondo Robotics announced that the open-source reinforcement learning environment for Beni is now live, allowing developers to train their own policies with MJLab and test them on the track. The environment already provides entry points on Hugging Face Space and GitHub. The quoted content states that Beni is the most-funded personal robot on Kickstarter.

  3. Leiphone Robotics53

    Mifeng Technology launches Mifeng Pai, a physical AI data crowdsourcing service platform, and unveils a 100-million-yuan subsidy plan

    On September 23, Mifeng Technology launched Mifeng Pai, a full-category physical AI data crowdsourcing service platform, in Shanghai. Its foundation consists of the MEgo series collection devices, the Mifeng Pai app, and MEgo Engine, while its upper layers are a scenario network and a collector network.

Sep 24Thu
  1. 求之科技 · 微信公众号55

    Qiuzhi Technology launches DEGO S1 life recorder and forms strategic partnership with Alibaba Cloud

    Qiuzhi Technology launched the DEGO S1 life recorder at the 2026 Yunqi Conference. It is thumb-sized and magnetically worn, features a built-in AI Agent that automatically selects and edits footage, and adds a data-collection task mode. It is now recruiting 499 co-creators for limited pre-orders.

  2. 机器人daily · 微信公众号55

    Mifeng Technology launches Mifeng Pai, a crowdsourced physical AI data service platform

    On September 23, Mifeng Technology launched Mifeng Pai in Shanghai, a full-category, high-quality crowdsourced physical AI data service platform. It is positioned as an underlying hub connecting people, tasks, devices, and a closed loop of robot training data, linking 22 major categories of real-world work scenarios such as hotels, catering, and factories.

  3. Beijing Humanoid Robot Innovation Center40

    Zhang Guowei visits Beijing Humanoid Robot Innovation Center, receives high-jump champion robot Tiangong Ultra

    High-jump star Zhang Guowei visited the Beijing Humanoid Robot Innovation Center, where he interacted with Tiangong Omni, Tiangong Ultra, and Tiangong 3.0 in running, high-jumping, and tug-of-war experiences; Beijing Humanoid gifted Tiangong Ultra to Zhang Guowei. Tiangong Omni can run at speeds exceeding 10 m/s, while Tiangong Ultra has broken world records 34 times and set a 3.4-meter high-jump record, supported by the Huisi Kaiwu embodied intelligence platform. Its data base covers nearly 6,000 square meters, is equipped with more than 150 robots, has an annual data capacity of up to 180,000 hours, and has delivered nearly 30,000 hours of real-machine data.

Sep 23Wed
  1. Skild AI62

    Skild AI releases physical self-play post-training results; S1 model learns soccer in simulation and transfers to humanoid robots

    Skild AI announced that it post-trained its foundation model S1 through physical self-play, letting the policy play against a recent version of itself with scoring as its sole objective. In NVIDIA Isaac Sim, over 140 years of simulated time, it learned skills such as dribbling past opponents, shielding the ball, and tackling, and these skills were successfully transferred to humanoid robots for matches. The authors believe self-play can break through the capability ceiling of pretrained human data, and the next step will be to extend it to everyday tasks such as collaborative manipulation and city-scale navigation.

    Why it matters: The authors describe using physical self-play to let a foundation model acquire soccer skills in simulation and transfer them to real robots, which lets readers learn about a feasible path for self-play-style post-training.

Sep 22Tue
  1. Tsinghua Embodied Intelligence and Robotics Institute25

    2026 AI Computing Conference Embodied Intelligence and Intelligent Computing Development Forum Held: Unlocking the Future of Robotics and Intelligent Computing Innovation

    The Embodied Intelligence and Intelligent Computing Development Forum of the 2026 AI Computing Conference (2026AICC) was held in Beijing on September 21, hosted by Tsinghua University's Institute for Embodied Intelligence and Robotics, under the theme "Breaking Through the Critical Point of Human-Machine Symbiosis." Scholars including Zhang Tao and Zhao Mingguo of Tsinghua University, along with representatives from companies such as Lingyu Intelligence, Shouyi Technology, and Qianjue Technology, shared results on directions including clinical applications of embodied intelligence, brain-inspired approaches for humanoid robots, data infrastructure, and world models. The forum built an exchange platform for industry, academia, and research, promoting the engineering and deployment of embodied intelligence technologies.

Sep 21Mon
Sep 20Sun
  1. PsiBot/灵初智能73

    Psi Robotics Releases Psi-R2.5 Model: Scaling Human Data for Embodied Intelligence with Strong Pair Data

    Psi Robotics released the Psi-R25 robot manipulation model. Its core upgrades are improved data quality and data attribute compression: it reviewed and extracted high-quality data from 100,000 hours of data, and used strong pair data to align human data with robot data.

    Why it matters: The original article details how strong pair data is generated and the data quality standards, giving readers a referenceable path for aligning human data to robot data.

Sep 19Sat
Sep 18Fri
Sep 17Thu
  1. Figure AI79

    Figure AI releases Helix 2.5, achieving zero-shot full-body autonomy in 30 unfamiliar homes

    Figure AI released Helix 2.5, which completed three long-horizon full-body behaviors—tidying a living room, folding towels, and making a bed—zero-shot in 30 Bay Area homes where no data had ever been collected, without collecting data or fine-tuning in the evaluation environments.

    Why it matters: The original article provides controlled comparison data on Index pretraining for zero-shot generalization and evaluation details, helping readers understand the actual level of humanoid robot pretraining transfer.

  2. Rainbow Robotics54

    Samsung Medical Center demonstrates ORchestra humanoid surgical assistant robots with two-robot collaboration reproducing cholecystectomy

    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.

Sep 16Wed
  1. ROBROS · YouTube44

    ROBROS unveils IGRIS-C Real-Time FBT full-body teleoperation

    ROBROS unveiled Real-Time FBT, a real-time full-body teleoperation technology for its IGRIS-C humanoid robot that maps the operator's movements onto the robot's full-body motion in real time. The demo includes basic full-body movements such as squatting, kicking, turning, and bowing, as well as box handling, sandbag punching, and ball kicking. The technology extends teleoperation from the previous upper-limb-focused control to the whole body, allowing the operator to coordinate locomotion, posture changes, and manipulation in real time as one continuous behavior.