Skip to content
#Data and simulation
Nov 9Mon
  1. arXiv cs.RO62

    RevoSim: A Scalable Multimodal Tactile Simulator for Dexterous Manipulation

    The authors present RevoSim, a multimodal tactile simulator for the BrainCo Revo3 dexterous hand that jointly models 285 piezoresistive taxels and 5 visuotactile fingertips. The simulator can synchronously generate pressure, depth, RGB, and marker-displacement observations; on a single RTX 5090, its depth-conditioned marker-displacement configuration supports up to 4096 parallel environments. The authors trained in-hand manipulation and grasping policies entirely in simulation, laying a foundation for future sim-to-real transfer.

  3. arXiv cs.RO65

    HomeLoop: A Robot-IoT Collaborative Simulation Framework and Benchmark for Home Assistance and Safety

    The authors propose HomeLoop, a simulation framework and benchmark built on Isaac Sim that integrates robot bodies, networked devices and wearables, simulated residents, faulty sensors, and hazards that evolve over time within a single environment. The benchmark contains 20 tasks across 5 categories, where the same alert can have different causes. A runtime monitor uses temporal logic to score both the final outcome and process actions, and each action has a preset cost.

  4. arXiv cs.RO67

    Lodos: A lightweight simulator for contact-rich interactions with detailed meshes

    Lodos is a simulation framework designed from scratch, using new broadphase and narrowphase collision detection and contact dynamics computation to specifically handle mesh-mesh collisions between detailed meshes. The authors state that its physical fidelity is comparable to existing mature simulators, and that in mesh-mesh collision scenarios its throughput is about an order of magnitude higher; the source code has been released. The work targets contact-rich scenarios in large-scale parallel rigid-body simulation that are limited by approximating collision geometry with primitives such as spheres, capsules, cylinders, and boxes.

  5. arXiv cs.RO58

    It Takes Two to Tangram: Multi-Agent Object-Centric Reinforcement Learning for Assembly

    The authors propose an object-centric reinforcement learning framework that treats each part as an agent and learns a shared policy for continuous assembly control. A graph neural network represents the parts, their target poses, and their spatial relationships, and predicts translational and angular velocities for each component; per-agent PPO with a centralized graph critic learns motion and temporal coordination within a single feedback policy. The study validates the approach on planar Tangram assembly, using procedurally generated target configurations and randomized initial layouts to support training and evaluation, and demonstrates parallel assembly in simulation and transfer to sequential execution on a real robot.

  8. Guyuehome40

    Dexterous Hand Practice 20: Building a Single-Finger Environment in MuJoCo and Understanding the Isaac Simulation Chain

    The 20th installment of the Dexterous Hand Practice series explains how to build a single-finger simulation environment in MuJoCo and, on that basis, understand the Isaac simulation chain. The content centers on the process of setting up the single-finger environment, used to compare how the MuJoCo and Isaac simulation pipelines connect.

  9. OFweek Robotics77

    Apple unveils HALO humanoid robot control system; Unitree G1 achieves 91% task success rate in unfamiliar environments

    Apple's research team published the paper "Perceptive Humanoid Motion from Simulation" on arXiv, unveiling HALO, an autonomous humanoid robot control system, and validating it on the Unitree G1.

    Why it matters: Apple's HALO splits task orchestration, motion generation, and tracking into three layers, and reports comparative results of 91% in unfamiliar environments and 70% on composite tasks, offering a look at its layered design and data synthesis pipeline.

Nov 8Sun
  5. 3D视觉工坊 · 微信公众号69

    Tsinghua and others propose ART framework: plug-and-play tool use for VLA models, boosting success rate by about 20%

    Tsinghua University and other institutions have proposed the ART (Agentic Robot with Tool-use) framework, which can fine-tune any end-to-end VLA model into an agent capable of plug-and-play use of external tools. The method uses 30,000 tool-call trajectories and two-stage LoRA fine-tuning, achieving average success rates of about 75% in LIBERO simulation and about 62% on a real Astribot S1 robot, an improvement of about 20% over baselines such as OpenVLA and π0.

Nov 7Sat
  1. HuggingFace Daily Papers62

    WorldFoundry: Toward Unified Open-Source Infrastructure for World Intelligence

    WorldFoundry proposes open-source infrastructure for world intelligence, intended for reproducible inference and evaluation across video, 3D and 4D, embodied action, and interactive world systems. The work defines a generative world model as a predictive dynamical system that maintains a persistent, history-conditioned state representation, responds to actions or interventions, and generates temporally coherent trajectories. Its catalog includes 270 model entries, 74 benchmarks, and 62 metric entries, and it records execution readiness and evaluation conclusions separately through manifests, artifact contracts, and evidence-aware scorecards.

  2. 量子位67

    Moxin Technology releases MoWorld 2.0 general-purpose 4D world model, integrating more than ten physical elements

    At the World Internet Conference in Wuzhen, Moxin Technology released MoWorld 2.0, a new-generation general-purpose 4D world model that integrates more than ten physical elements, including gravity, elasticity, buoyancy, lighting, soft bodies, fluids, rigid bodies, deformable bodies, and thermal dynamics, into a single model to more accurately simulate object motion, collisions, and environmental changes.

  3. 深蓝AI · 微信公众号58

    Deep Blue AI: What panoramic cameras can and cannot add as they enter embodied data collection

    Deep Blue AI reviewed the trend of panoramic cameras being moved into the embodied data collection field, arguing that they are better suited as a spatial context layer within hybrid collection setups rather than as a replacement for fine-grained motion data. The article traces the evolution of data collection routes from real-robot teleoperation, UMI handheld grippers, and DexCap motion-capture gloves to EgoMimic first-person-view glasses, and notes that panoramic recording defers framing decisions until after collection, so the same footage can generate multiple observations.

  4. Guyuehome58

    Why ros2_control Leaves the Wheels Not Turning in ROS2 Mobile Robot Simulation

    The article focuses on ROS2 mobile robot simulation based on ros2_control, covering interface development, ground-truth validation, and the boundaries of the approach, for use in scenarios such as navigation benchmarks and SLAM algorithm comparison. Starting from the problem of the wheels not turning, it outlines how ros2_control is integrated into simulation and its scope of application.

  5. 机器人前瞻 · 微信公众号70

    Lingji Robotics upgrades Dexmal MaaS, opens robot model post-training services

    Lingji Robotics announced an upgrade to its embodied intelligence model service platform Dexmal MaaS, with a focus on opening post-training capabilities for real-world scenarios. Developers can upload robot manipulation data and complete training and inference deployment in the cloud based on DM0.5.

  6. 机器人前瞻 · 微信公众号83

    Apple releases HALO system, enabling Unitree G1 to perform whole-body skills such as crawling under tables and passing through door gaps zero-shot

    Apple released the HALO humanoid whole-body motion control system, which procedurally generates 1,000 virtual residential scenes and synthesizes nearly 300 hours of paired data, enabling the Unitree G1 to master skills such as sitting on chairs, turning sideways to pass through a half-open door, crouching under a table, and pushing boxes.

    Why it matters: Apple's HALO uses simulation-synthesized data to train humanoid whole-body skills, transfers them zero-shot to real scenes, and ablation experiments show the contribution magnitude of each module.

  7. 未来机器人网 · 微信公众号38

    Daxiao explores dual-brain collaboration: from real interaction to reusable physical experience

    Daxiao proposes a "dual-brain collaboration" architecture that connects the cloud brain SenseNova's task understanding and planning capabilities with the on-device Kaiwu world model's judgment of physical states and prediction of action consequences, while an embodied Harness organizes perception, memory, skills, and control. The exploration aims to preserve a single robot's interaction experience, along with evidence and applicable conditions, so that other robots can reuse it across tasks, scenarios, and embodiments, reducing repeated trial and error. The system is organized around three progressive loops: autonomous execution, experience learning, and recursive self-improvement. It is currently at the exploration stage and has not yet provided real-machine validation metrics.

  8. 机器之心 · 微信公众号22

    Feed It a Million Hours of Data—Will Robots Learn Everything? Zhangjiang Summit Breaks Down the 'Embodied Data War'

    On November 5, the 'Triple T' Zhangjiang Summit technical salon, co-hosted by an ecosystem company of Zhangjiang AI Innovation Town and Synced, was held under the theme 'The Next Data War in Embodied Intelligence,' featuring a two-person technical debate, three Open Mic sessions, and one industry panel. Huang Yongtao of Ant Lingbo Technology argued that at this stage priority should be given to accumulating real-robot data and incorporating touch as early as possible, while Liu Miao of Tsinghua University held that data selection depends on application positioning and the training stage. Ma Daolin of Qianjue Robotics demonstrated the performance of a VTLA model integrating vision, touch, language, and action in real-robot tasks such as automatic shoelace threading and carton forming.

  9. 机器之心 · 微信公众号78

    Yuance Future Releases Anchor 1 Whole-Body Control Model for Humanoid Robots

    Yuance Future has released Anchor 1, a whole-body control model positioned as the System 0 cerebellum layer within a whole-body intelligence architecture. It uses five anchor points—the pelvis, left and right wrists, and left and right ankles—as commands and does not rely on online retargeting.

    Why it matters: The original article provides quantitative comparisons of the whole-body control model's real-machine error and teleoperation collection efficiency, which can be used to assess how the cerebellum layer's precision affects the success rate of upper-layer VLA tasks.

  10. 机器之心 · 微信公众号78

    Northwestern, CMU and others propose WOVEN: cross-domain gains on 22 benchmarks with 2k samples, plus a training recipe

    A team from Northwestern, CMU, UNC Chapel Hill and Amazon, in the paper "WOVEN: Weaving Visual World Modeling into Multimodal LLMs," defines world modeling as estimating the state transition p(s′|s,a) and builds WOVEN, a training and evaluation base of 36K questions.

    Why it matters: The paper breaks world modeling into independently intervenable state-transition tasks and provides reusable rules for selecting training data, offering reference value for multimodal model training.

  11. 机器之心 · 微信公众号72

    DexRoam proposes learning mobile dual-arm dexterous manipulation from first-person human whole-body demonstrations

    The Hong Kong University of Science and Technology, Beijing Academy of Artificial Intelligence, Peking University and other institutions jointly proposed DexRoam, which uses first-person human whole-body demonstrations to train mobile dual-arm dexterous manipulation policies. The work has been accepted to CoRL 2026. The system narrows the human-robot motion distribution gap through three stages: embodiment alignment, action semantic alignment, and temporal alignment, reducing MMD and SWD metrics by an average of 41.7% and 31.1%, respectively.

  13. CVer · 微信公众号69

    miHoYo and Tsinghua University and others open-source GameScaling general game agent models

    miHoYo, together with Tsinghua University, the University of Hong Kong, the National University of Singapore, and other institutions, has open-sourced the GameScaling series of general game models, covering four size tiers—0.8B, 2B, 9B, and 27B—for a total of eight models. The weights and inference code are released under the Apache 2.0 license.

Nov 6Fri
  2. 开普勒人形机器人 · 微信公众号55

    Shanghai Kepler uses NVIDIA physical AI to close the loop from simulation to industrial sites

    Shanghai Kepler has built a closed loop from simulation training to real-machine validation for industrial humanoid robots based on NVIDIA Isaac Lab, Isaac GR00T, and Cosmos. The company develops its own planetary roller screws, linear and rotary actuators, joint modules, and robot bodies, introduces real dynamics parameters into Isaac Lab for Sim2Real iteration, and validates them in scenarios such as workshop assembly and CNC machine loading and unloading. Kepler is also working with a team from Zhejiang University's College of Artificial Intelligence to develop an embodied intelligence foundation model for long-horizon tasks.

  3. 帕西尼 · 微信公众号40

    PaXini and 58.com's 58AIR announce strategic partnership to build embodied data learning network with "1+1+N" open ecosystem

    PaXini has entered a strategic partnership with 58AIR, the AI industry service platform under 58.com, and 58AIR has officially become a PaXini inside ecosystem partner. The two parties will work with N data-collection companies to explore a "1+1+N" open collaboration model. PaXini will provide partners with high-precision tactile sensors and device integration support, aligning tactile, posture, and visual information by task timeline; 58AIR will open up real-world operation scenarios such as home repair and intra-city logistics. The two parties will also connect collaboration steps including collection interfaces, quality requirements, task design, and data security compliance.

  4. 机器人网 · 微信公众号47

    Avnet and National-Local Joint Humanoid Robot Innovation Center Release 76-Page Embodied Intelligence Chip Selection White Paper

    Avnet, together with the National-Local Joint Humanoid Robot Innovation Center, produced a 76-page white paper (August 2026) that uses five functional domains and six core modules as its framework to break down 10 categories of industrial deployment challenges, including heterogeneous computing workloads and platform adaptation, multi-axis real-time control, and dexterous hand integration.

  5. 至简动力 · 微信公众号72

    Zhijian Dynamics and Hangcha Group deploy robot sorting line for supermarket front warehouses

    On November 3, Zhijian Dynamics and Hangcha Group completed the deployment of the first robot sorting line for a supermarket front warehouse, connecting the full workflow from AMR merge feeding, robot autonomous planning and dexterous grasping and turning, and scan verification to order distribution. The line uses the iX robot body that Zhijian Dynamics customized for Hangcha, and relies on visual perception and VLA task planning to handle boxed, bagged, bottled, and other product forms without the need to model each SKU separately. Measured single-machine sorting efficiency reaches up to 450 items per hour, with accuracy stable above 98%, and under full load it can support 24-hour continuous fault-free operation.

    Why it matters: Readers can learn about the actual deployment conditions of the supermarket front-warehouse sorting line and the single-machine efficiency and accuracy data.

  6. HuggingFace Daily Papers67

    SLA: Scaling spatial-language-action models via continual pre-training

    The study proposes SLA, a spatial-language-action model initialized from a pretrained pi05 policy, which jointly optimizes action prediction and the alignment of intermediate visual embeddings with the spatial representations of a frozen 3D perception model during continual pre-training. The team unified heterogeneous robot datasets spanning embodiments, tasks, and scenes, and introduced feature-dependent gates that adaptively aggregate visual embeddings from multiple layers; the teacher model can use partially available depth and camera calibration information. All auxiliary components are used only during training, and the inference architecture remains unchanged.

  7. Guyuehome20

    Motion Capture Data onto the Humanoid Body: Skeleton Alignment, Scale Factors, and the Final Safety Gate

    Transferring motion capture data to a humanoid robot body requires handling skeleton alignment and scale factors, and setting up a final safety gate. The article centers on these three points, explaining how to adapt motion capture data to the joint and size differences of the humanoid body and add safety limits before execution.

  8. 36Kr Embodied Intelligence60

    EABOT completes nearly 400 million yuan in funding within a year, operates over 100 heavy trucks to validate heavy-duty physical AI

    Shanghai EABOT Technology (EABOT) recently completed two consecutive funding rounds totaling nearly 400 million yuan, with investors including Ge Weidong, Chentao Capital, Hony Capital, and Zero One Automotive. Founded in February 2026, the company focuses on heavy-duty industrial physical AI. It already operates more than 100 heavy trucks across 60 routes, mainly serving short-haul bulk material scenarios of 0-300 kilometers, and has conducted real-road zero-intervention testing in Xinjiang, Inner Mongolia, and other regions.

  9. HuggingFace Daily Papers83

    A2-MEAS proposes embodied multi-agent framework with code as scaling interface

    The research team proposes A2-MEAS, an embodied multi-agent framework that uses code as a scaling interface. It combines correction codes with corrective language, spatial evidence, execution history, and action proposals, while MetaBrain provides training supervision and runtime guidance.

    Why it matters: The framework uses code as a scaling interface, injects corrective language and execution history into the policy, and presents comparison data across multiple benchmarks and real-robot experiments.

  10. 机器之心 · 微信公众号80

    LiberAI releases world action model Liber-0, publishes technical report and online simulator

    LiberAI, founded by Liu Songming, has released Liber-0, a new-generation world action model that uses three expert streams for language, vision, and action along with Multimodal Attention to jointly predict future frames and actions.

    Why it matters: The technical report uses controlled experiments to break down the contributions of human data, action supervision, and embodiment diversity to dexterous manipulation, which can inform judgments about data-mix strategies.

  11. CVer · 微信公众号62

    NeurIPS 2026 Paper RePO-VLA: Dual-Arm Robot Disturbance Recovery Success Rate Raised to 75%

    Sun Yat-sen University, Peng Cheng Laboratory, and other institutions propose RePO-VLA, which segments recovery trajectories, trains a progress-aware semantic value function, and performs value-conditioned fine-tuning so that dual-arm VLA policies can continue advancing tasks after disturbances. The study also builds FRBench, a failure-recovery benchmark; the RoboTwin simulation contains 46 dual-arm tasks and 23,453 trajectories. On real robots in water-pouring and towel-folding tasks, as recovery demonstrations per task increase from 50 to 200, the average disturbed success rates are 30%, 65%, and 75%, respectively.

Nov 5Thu
  1. 新智元 · 微信公众号58

    Embodied AI MaaS rises: comparing three approaches from Yuanli Lingji, Physical Intelligence, and Dream Labs

    The article argues that, limited by onboard compute and heat dissipation in robot bodies, embodied model inference is shifting to the cloud, and embodied AI MaaS is becoming a new direction. In July 2026, Yuanli Lingji released a general embodied MaaS service; in October, Physical Intelligence launched an invitation-only Pi API Beta; and Dream Labs launched Dream API backed by a $90 million seed round.

  2. Tech Xplore Robotics62

    MIT proposes UQ-DAAAM to correct erroneous object descriptions in robot memory using multi-view images

    MIT researchers propose the UQ-DAAAM system, which quantifies a robot's uncertainty about what it sees by comparing multiple descriptions of the same object from different viewpoints, selects additional viewpoints to correct erroneous annotations, and writes the corrections back to memory. The method adds uncertainty quantification to the DAAAM framework, uses heuristic rules to select frames that can reduce uncertainty without rerunning the vision-language model, and then uses a large language model to fuse the multiple descriptions.