Lumos NexCore Connects the Entire Robot Skill Workflow
Your first robot skill starts here. Train it. Test it. Improve it. Deploy it. Lumos NexCore connects data, models, skills, and robots in one continuous workflow. Start building with NexCore.
#Data and simulation
鹿明机器人 · XAI score1616
简智机器人 · XAI score1212 Reliable Whole-Body Data Is More Than a Human-Looking Mesh
Reliable whole-body data is more than a mesh that looks human. It requires precise ground truth, temporally consistent motion, and a production pipeline built for scale.
Elite Robots/艾利特机器人AI score2727 Elite Robots attends 2026 CIOE forum to discuss embodied intelligence deployment in optical communications
Dr. Wu Min, CTO of Elite Robots, delivered a keynote speech titled "Optically Connected Intelligence: Large-Scale Deployment of Embodied Intelligent Robots in the Optical Communications Industry" at the Embodied Intelligent Robot Integrated Applications Forum of the 27th China International Optoelectronic Exposition, which opened on September 10.
MIT CSAILAI score5252 MIT CSAIL releases X-Hinges design software that 3D-prints everyday objects into interactive devices with built-in sensing
Researchers at MIT CSAIL and Tianjin University have introduced X-Hinges design software, which automatically embeds two different materials when 3D-printing interactive objects, allowing sensor signals and wire-like traces to avoid interfering with each other, and supports up to three axes of motion. The team used it to make a smart glove that transmits grasp-motion data to a humanoid robotic hand, an origami-style desk lamp that senses pinching to adjust brightness, and a detection device that can identify the objects placed on it, and used a computer vision system to align sensor-reading differences among devices from the same batch. The work will be presented at UIST.
PKU EPIC LabFeaturedAI score7373 FoldNet++: A Large-Scale Synthetic Dataset for Robotic T-Shirt Folding and Unfolding
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.
OFweek RoboticsAI score4949 How PaXini Gives Robots the Sense of Touch That Took Millions of Years to Evolve
PaXini AI, drawing on the tactile sensing logic of the human Pacinian corpuscle, has released the PX6AX GEN4 product matrix, equipped with the GEN4 FUSE true 6D tactile sensing chip, and completed a new funding round of 1 billion yuan.
云启资本FeaturedAI score6060 Yunqi Podcast Roundtable: Three Embodied AI Founders Discuss World Models, Scaling, and Deployment Bottlenecks
During the World Robot Conference, Yunqi Capital co-hosted a themed roundtable with SEE Fund, which was included in the podcast Attent!on. Three founders—Xu Huazhe of PokeBot, Li Qiang of Quantum Dynamics, and Liu Nianqiu of Feimo Yi Technology—shared their views on world models, scaling, and deployment.
Why it matters: The three entrepreneurs approached the topic from models, hardware systems, and mobility respectively, specifically breaking down where the bottlenecks in embodied intelligence deployment lie and where they diverge on scaling efficiency.
简智机器人 · XAI score3232 How Genrobot scales whole-body manipulation data
How to scale whole-body data? Start from the ego perspective—vision only, full-body mesh, whole-body error of about 3 cm, 100,000 hours per month. Generate whole-body manipulation data directly usable for policy training from real human behavior, at scale. See the blog for details👉: https://www.genrobot.ai/blog/whole-body
帕西尼 · 微信公众号AI score4646 PaXini x BeingBeyond: Co-building a New Ecosystem for Embodied Intelligence Data and Models
PaXini AI has entered into a partnership with BeingBeyond, a general-purpose embodied foundation model company. BeingBeyond becomes a PaXini Inside ecosystem partner, and the two parties will work around the Being-H series of models to advance embodied foundation model training, full-modality data production, and POC validation in real-world scenarios.
简智机器人 · XAI score5252 GenRobot.AI launches whole-body manipulation data production system that generates model-ready data from first-person video
GenRobot.AI introduces its Whole-Body Manipulation Data production system, which uses DFM to reconstruct coherent whole-body motion from first-person video, unifying the body, both hands, objects, contact, vision, and task semantics.
Noetix Robotics/松延动力AI score3535 Songyan Dynamics launches embodied intelligence sub-brand Scalabot, releases first world model HERON-World Model
Songyan Dynamics has launched Scalabot, an embodied intelligence sub-brand, and released its first world model, HERON-World Model. Building on its strengths in robot hardware, the brand focuses on letting intelligence grow in the real world.
简智机器人 · XAI score2121 Ego vision enables whole-body data at scale
How do you scale whole-body data? 😜 Start with Ego! Vision only, full-body mesh! ≈3 cm whole-body error 100,000 hours of data per month. From real human behavior to whole-body manipulation data usable for policies—acquired at scale. See the whole body. Learn complete skills. #PhysicalAI #Robotics
TUM MIRMIAI score4646 TUM MIRMI uses Embodied Laboratory Intelligence to collaboratively explore the internal mechanisms of cancer cells
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.
北京智在无界科技有限公司AI score3636 BeingBeyond and PaXini AI announce comprehensive partnership
BeingBeyond and PaXini AI have signed a cooperation agreement, making BeingBeyond an official PaXini Inside ecosystem partner. The two parties will collaborate in depth on embodied foundation model R&D, POC validation for deployment scenarios, and co-building embodied data standards. PaXini will provide key multimodal data for Being-H0.8, the implicit tactile world-action model BeingBeyond released on July 28; the model was pretrained on over 500,000 hours of human video data.
PKU EPIC LabFeaturedAI score6868 GIF: An agentic generation framework for interactive and functional object compositions for robot learning
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.
中科慧灵 · 微信公众号FeaturedAI score6565 CASIA and others propose World4RL: diffusion world model combined with reinforcement learning to optimize robot manipulation policies, real-world success rate rises to 93.3%
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.
OFweek RoboticsAI score7272 Fourier Intelligence, Shanghai Jiao Tong University, and Fudan University Open-Source HandEdit Dexterous Hand Image Editing Dataset and Benchmark
Fourier Intelligence, together with Shanghai Jiao Tong University, Fudan University, and others, has open-sourced the HandEdit dataset and benchmark, which studies editing first-person human hand images into specified robotic dexterous hand configurations. The data contains more than 200 million image editing samples and over 300,000 video clips, covering 26 URDF configurations, more than 600 scenes, over 1,100 object types, and more than 400 task categories; it uniformly tests 11 image editing methods, sets up two evaluation tracks, Hand-only and Hand-Arm, and combines general similarity, VLM judgment, and embodied task metrics.
卧安机器人AI score4646 Greater Bay Area's First JUBAOPEN Officially Opens, OneRobotics Builds an Embodied Intelligence Industry Acceleration Platform
On September 1, JUBAOPEN, the Greater Bay Area's first embodied intelligence innovation community, officially opened at Kexing Science Park in Qianhai, Shenzhen. It is led by OneRobotics. The community covers a total area of 6,039 square meters and can run up to 100 teleoperation and UMI data collection terminals in parallel, covering 50 to 100 types of task scenarios, using a "1+N" real-world setup. At the launch ceremony, five first-batch innovation projects, including Physen AI, signed to move in.
智动未来AI score4949 Zhido Future Launches "Zhizi World" World Model, Enabling Xiaozhi S3 to Understand the Real World
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.
PKU EPIC LabFeaturedAI score7979 ZETA: A Controlled Study of Zero-Shot Cross-Embodiment VLA Transfer for Tabletop Manipulation
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.
自变量机器人 · 微信公众号FeaturedAI score7171 X Square Robot releases TwinDEX: a three-finger, nine-DOF dexterous hand trained on purely embodiment-free data
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.
北京智在无界科技有限公司AI score3333 Connecting Data, Models, and the Real World | BeingBeyond and Shutu Technology Deepen Cooperation
BeingBeyond and Shutu Technology recently formally signed a strategic cooperation agreement. The two parties will deepen collaboration around high-quality data construction, model training and validation, and industry data standards, and will explore building an industry-oriented data-sharing ecosystem platform. Shutu Technology had previously served as one of BeingBeyond's core data partners, providing data support for embodied foundation model training. On July 28, BeingBeyond released the embodied foundation model Being-H0.8, which was pretrained on more than 500,000 hours of raw first-person video data.
中科慧灵 · 微信公众号AI score3030 CASBOT CEO Yang Ping Shares New Data-Driven Path for Embodied Intelligence at 2026 China International Big Data Industry Expo
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.
Pollen Robotics · YouTubeFeaturedAI score6464 Pollen Robotics opens pre-orders for Microduck, a 25 cm reinforcement learning robot
Pollen Robotics has opened pre-orders for Microduck at $399 (excluding taxes and shipping), with first deliveries targeted before Christmas 2026. The 25 cm-tall robot is built for reinforcement learning, with 15 degrees of freedom, a front camera, an 8x8 LiDAR, two IMUs and a full sensor suite, and supports designing behaviors in simulation and transferring them to the real robot.
Why it matters: It packs the full loop from simulation training to real-world deployment into a small, pre-orderable complete robot, letting readers gauge the barrier to building their own reinforcement learning workflow.
PsiBot/灵初智能FeaturedAI score6969 Lingchu Intelligence completes over $100 million new funding round, with industrial capital including Tuopu Group and Chery Ruicheng Fund participating
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.
机器人daily · 微信公众号AI score6262 2026 World Robot Conference Highlights Diverging Paths in Embodied Intelligence: Scenarios, Data, and Form Factor Debates
At WRC 2026, more than 300 companies in the embodied intelligence supply chain exhibited, with clear disagreements emerging across deployment scenarios, data training approaches, and robot body form factors. On scenarios, Leju and Dobot are targeting industrial and logistics warehouse settings, while Moqi argues for first entering unstructured settings such as the home to accumulate data. On data approaches, Galaxea uses almost entirely real-world data and is advancing a 1 million-hour real-data plan, while Galbot sticks with a Sim2Real simulation-based generalization approach.
OFweek RoboticsAI score5252 Leju Hosts Three Dialogues at WRC: Robotics Industry Shifts from Making Movements to Doing Things Reliably
The author reviews three dialogues hosted jointly by Leju and Ant Lingbo at WRC, covering whether embodiments are easy to learn, whether data is easy to use, and whether models are easy to evaluate, with 12 guests in total. Key viewpoints include that hardware is becoming a precondition for model capability, that Ant Lingbo's real-world data exceeds 100,000 hours and covers more than 20 configurations, that Noitom says about 20% of data plays a core role in model behavior, and that evaluation should guide adjustments to data distribution; on this basis, the author argues that industry attention is shifting from making a single movement to doing a task reliably and consistently.
Figure AIFeaturedAI score6262 Figure AI launches Index app to build large-scale, diverse robot training dataset
Figure AI announced it is exiting stealth mode and launching the Index app on Google Play and the App Store to collect real-world physical data from Creators worldwide to train its Helix AI system.
Why it matters: The original article provides scale figures for the Index data pipeline and a five-stage processing workflow, which readers can use to assess the actual progress of its human data collection approach.
自变量机器人 · 微信公众号AI score6262 XinZhiYuan Robot appears at WRC 2026, showcasing WALL-B-driven logistics sorting and home services
At the 2026 World Robot Conference, XinZhiYuan Robot presented under the theme "Full-stack evolution: bringing embodied intelligence into real applications," showing a logistics sorting production line driven by its self-developed world unified model WALL-B, a 22-DOF dexterous hand performing box-opening and flower-arranging tasks, and the home service robot "Xiao Liang."
TetraBOT/天创机器人AI score5757 Tianchuang Robotics and partners' industrial multimodal safety evaluation dataset InspecSafe accepted by Scientific Data
The paper on InspecSafe-V1, an industrial multimodal safety evaluation dataset released by Tianchuang Robotics together with Tsinghua University, DAMO Academy, and Southeast University, has been accepted by Scientific Data, a journal under Nature.
OFweek RoboticsAI score5555 PaXini Unveils Fourth-Generation GEN4 Tactile Sensor and PX-FOOTRIX Plantar Tactile Sensor at WRC 2026
At WRC 2026, PaXini released its fourth-generation GEN4 multi-dimensional tactile sensor matrix, featuring the self-developed fourth-generation native true 6D tactile sensing chip FUSE, adding the Superior flagship sensing unit, Neuron full-body electronic skin, and Gripper perception module, and offering 19 sensor options in different sizes.
智源研究院 · 微信公众号FeaturedAI score7575 BAAI releases FlagEval-Robo embodied intelligence evaluation system and dual leaderboards
BAAI released the FlagEval-Robo embodied intelligence evaluation system on August 21, launching the FlagEval-Robo-Sim and FlagEval-Robo-Real leaderboards and publishing evaluation results for 12 open-source models. All models underwent equal post-training on the evaluation dataset.
Why it matters: The evaluation uses a unified dual-track benchmark to quantify the performance gap between simulation and real robots, helping readers judge the limits of how far simulation leaderboard results can be generalized.
OFweek RoboticsAI score3434 Paxini's "2026 Global Embodied Ecosystem Night" Concludes in Beijing, PaXini Inside Partner Program Launched
On August 19, Paxini held the "2026 Global Embodied Ecosystem Night" (GEEN 2026) in Beijing, bringing together nearly 200 representatives from industry, academia, and capital partners. At the event, the PaXini Inside partner program was launched, committing hundreds of millions of yuan in funding and industry resources, opening up six core benefits, and announcing a national super embodied data collection infrastructure acceleration plan. The event also saw the signing of multiple cooperation agreements with Tencent Cloud, the China Industrial Control Systems Cyber Emergency Response Team, Tianjin Sino-German University of Applied Sciences, and others.
加速进化 · 微信公众号FeaturedAI score7272 Tsinghua's Zhao Mingguo team publishes Science Robotics paper proposing a unified perception-motion reinforcement learning framework for vision-driven humanoid soccer skills
On August 19, Professor Zhao Mingguo's team in Tsinghua University's Department of Automation published the paper "Learning Vision-Driven Reactive Soccer Skills for Humanoid Robots" in Science Robotics, selected for the August 2026 humanoid robotics special issue; the robot platform used was a humanoid robot independently developed by Booster.
Why it matters: The paper breaks down three failure points of the traditional perception-planning-control pipeline and presents a reproducible sim-to-real transfer method.
开普勒人形机器人 · 微信公众号AI score4747 Kepler Qilin Series Heavy-Duty Quadruped Robots Debut at WRC2026, NVIDIA Executive Huang Minshan Experiences Them On-Site
Kepler exhibited its full Qilin series of heavy-duty quadruped robots at WRC2026. Huang Minshan, NVIDIA Senior Director of Physical AI and Robotics, visited the booth and experienced the Qilin heavy-duty model. The Qilin heavy-duty model has a 300kg-class body weight and a near-ton-class full-load payload, can run continuously for 8 hours on a single charge, and its core components reach IP67 protection rating; the rideable model supports dual modes of carrying a real person for riding plus rear cargo transport.
OFweek RoboticsAI score4545 WRC 2026 | PaXini unveils full-stack new products including PX-FOOTRIX plantar tactile sensor
At the 2026 World Robot Conference, PaXini AI debuted three new products: PX-FOOTRIX, the world's first multi-dimensional plantar tactile sensor; PXCap Pro, a new-generation five-finger data collection glove; and the fourth-generation ITPU sensor series PX6AX GEN4, equipped with the self-developed 6D tactile sensing chip GEN4 FUSE.
机器人daily · 微信公众号AI score5656 Octopus Dynamics releases SYNWorld V0.5, a general world model for embodied intelligence
Octopus Dynamics has released SYNWorld V0.5, a general world model for embodied intelligence. It uses a MoT architecture, has a parameter scale of 10+B, and was trained on 300,000+ hours of data covering images, video, and robot action trajectories with action annotations.
OFweek RoboticsAI score7373 University of Auckland and Xi'an Jiaotong University release Video2Knowledge framework to extract robot task knowledge from monocular phone video
The LISMS lab at the University of Auckland and Xi'an Jiaotong University jointly proposed the Video2Knowledge framework, which extracts 6D hand and object trajectories from an ordinary monocular RGB video and converts them into robot action sequences. The system uses WiLoR to recover 3D hand meshes, combines OnePoseViaGen for object tracking, and designs a four-stage physics-aware correction module; manipulated-object pose accuracy rises from 52.5% to 59.0% under frontal views.
X Square Robot/自变量机器人AI score4545 X Square Robot debuts at WRC: dual-scenario demos in home services and logistics sorting, with hands-on QUANXTA Zero bodyless data collection
At the Beijing World Robot Conference (WRC), held August 19–23, X Square Robot showcased three exhibition areas: home services, logistics sorting, and bodyless data collection. Its fully self-developed end-to-end unified world model WALL-B drives robots to complete dozens of household chores. Logistics sorting reaches an efficiency of 1,816 items per hour with 98% accuracy, at a cost 70% lower than the "humanoid robot + five-fingered dexterous hand" approach, and has already entered routine operation on real production lines. The QUANXTA Zero data collection solution achieves a data-ingestion validity rate above 85% and can reduce training-data costs by 90%.
达纳灵动 · XAI score6262 Dyna Robotics publishes reproducible training method for Dyna-2 on one million hours of first-person video
Dyna Robotics published how to reproducibly train Dyna-2 on more than 1,000,000 hours of egocentric video.