Skip to content
Only Research#Data and simulation
  1. Tech Xplore Robotics78

    UC Berkeley and NVIDIA propose agentic robotics to generate and improve robot programs in simulation

    Ken Goldberg's team at UC Berkeley and Spencer Huang, NVIDIA's head of robotics engineering, proposed an "agentic robotics" method that lets AI agents generate, test, and correct robot control programs in simulation without additional data collection.

    Why it matters: The report describes a method for using multi-agent systems to generate, test, and correct robot programs in simulation, and presents real-world data from warehouse sorting.

  2. arXiv cs.RO79

    A2-MEAS: An Embodied Multi-Agent Framework with Code as a Scaling Interface

    The authors propose A2-MEAS, an embodied multi-agent framework that uses code as a scaling interface, combining corrective language, spatial evidence, execution history, and action proposals into correction codes; during training, MetaBrain provides 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 provides quantitative comparisons across benchmarks and real-robot tasks.

  3. 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.

  1. 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.

  1. 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.

  1. arXiv cs.RO84

    HALO: Humanoid Autonomy System Trained on Synthetic Simulation Data Achieves Zero-Shot Real-World Transfer

    The research team proposes HALO, a humanoid robot autonomy system that synthesizes vision-language-action data across roughly one thousand procedurally generated home scenes, eliminating reliance on teleoperation data collection. HALO learns skills including sitting on chairs, navigating to specified objects, stepping sideways through half-open doors, crouching and crawling under tables, and pushing boxes, and can combine them to complete long-horizon tasks. Without ever seeing real home scenes during training, HALO transfers zero-shot to the physical world, achieving a 91% success rate across 360 trials in six unmapped real-world environments.

    Why it matters: The paper presents a complete path from synthesizing vision-language-action data using procedurally generated home scenes to zero-shot transfer to real robots; its approach to data scaling is worth referencing.

  2. HuggingFace Daily Papers78

    PyRUA-DataFarm: Using LLM agents instead of teleoperation to generate real-ready robot data

    PyRUA-DataFarm proposes having a coding agent rebuild tasks in simulation, with a video model rendering them into real-ready data, replacing teleoperation for collecting robot demonstrations. On five real-robot tasks, policies trained only on this data achieved 93/100 successes, versus 84/100 for policies trained on teleoperated data; under an unseen tablecloth and colored lighting, the former kept 87 successes while the latter fell to 46.

    Why it matters: The paper presents a complete pipeline and cost comparison for using a coding agent to replace teleoperation in collecting demonstrations, which can be used to assess the room for replacing this data-collection route.

  3. 未来机器人网 · 微信公众号77

    D-Robotics and University of Tokyo release RawVLA: frozen VLA, only imaging front end trained, low-light dual-arm task success rate rises from 0 to 66.5%

    D-Robotics, together with the University of Tokyo and other institutions, released the RawVLA technical approach, which adds a learnable neural ISP module before the VLA policy while keeping the VLA model frozen, using action error to train the imaging front end in reverse. On real robots, four dual-arm tasks were tested with π0.5; the average success rate in low light rose from 0% with the default ISP to 66.5%, versus 75.0% in normal light, where the default ISP achieved 76.5%.

    Why it matters: The approach brings the imaging front end into the learnable pipeline and provides comparative data under low light and normal light, offering a reference for vision pipeline design.

  1. HuggingFace Daily Papers85

    PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

    The research team proposes PrimeSim, an action-conditioned multiview world model simulator, midtrained on robot demonstration data covering 22 platforms and 30,110 hours, and has released the model weights, inference code, and training code.

    Why it matters: This work presents a world model simulator trained on demonstrations spanning 22 platforms and 30,000 hours, and releases the weights and training code, facilitating comparison of its long-horizon stability and action-following capability.

  1. Xbotics具身智能实验室 · 微信公众号78

    GE-Sim 2.0 and π0.5 closed-loop simulation test: Why does reward hacking occur in VLA training?

    The Xbotics Embodied Intelligence Lab built a closed-loop simulation pipeline using the AgiBot GE-Sim 2.0 world model and the OpenPI π0.5 policy. In testing, the world model generated about 4.33 frames per second, the pure-policy closed loop ran at about 3.20 frames per second, and after adding MiMo online scoring, the rate dropped to about 0.88 frames per second.

    Why it matters: The author uses a four-stage test to break down the frame-rate bottlenecks and causes of reward hacking in world-model closed-loop simulation, which can be transferred to the design of VLA evaluation workflows.

  2. PsiBot/灵初智能71

    Lingchu Intelligence and collaborators propose FAFM, a continuous action generation method for heterogeneous-frequency data, accepted to NeurIPS 2026

    Lingchu Intelligence, together with Beihang University, Peking University, and The Chinese University of Hong Kong, proposed a frequency-aware flow matching method called FAFM; the paper was accepted to the NeurIPS 2026 main conference. The method uses the discrete cosine transform (DCT-II) to represent actions as frequency-domain coefficients corresponding to real time, performs flow matching in coefficient space and constrains the first-order time derivative, requires no additional learnable parameters, and can be used independently or integrated into VLA models such as π₀ and π₀.₅.

    Why it matters: The paper presents a frequency-domain action representation that adds no learnable parameters and can be integrated into existing VLA models, offering a transferable approach for joint training on heterogeneous-frequency data.

  3. PsiBot/灵初智能71

    PKU-Spirit AI Joint Lab's RoboFFT Accepted to CoRL2026, Uses Reinforcement Learning Post-Training to Generate Robotic Policies

    RoboFFT, proposed by the PKU-Spirit AI Joint Lab, has been accepted to CoRL2026. It is a reinforcement learning post-training method for generative robotic policies that reuses the forward noising process from diffusion model and flow model pretraining to construct an approximate probability ratio for PPO-style clipped updates.

    Why it matters: The method reuses the forward noising loss of diffusion and flow models to construct policy update signals, offering a reusable approach for post-training generative policies.

  1. arXiv cs.RO80

    TacClaw-Infinity: A Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation

    The research team released TacClaw-Infinity, a large-scale structured Vision-Tactile-Language-Action (VTLA) dataset for contact-rich manipulation, spanning over 10,000 hours, 1 million episodes, and 1 billion frames across more than 1,000 task types.

    Why it matters: This dataset provides a collection interface and quality control pipeline for ten-thousand-hour-scale tactile manipulation data, and its cross-embodiment transfer validation approach can serve as a reference.

  2. arXiv cs.RO80

    Movens-Zero: Scaling humanoid motion foundation models with large-scale human videos

    The research team proposes Movens-Zero, a scalable understanding-generation-execution architecture that supports real-time closed-loop humanoid motion generation under text, speech, music, and video inputs. Its accompanying dataset, Movens-5M, is built from Internet videos through clip generation, quality filtering, semantic annotation, motion recovery, and physical refinement with humanoid retargeting. It contains 15 million human motion sequences and 5 million physically executable humanoid motion sequences, totaling over 10,000 hours.

    Why it matters: This technical report presents a complete path for building a humanoid motion dataset from Internet videos and training a unified understanding-generation-execution model, offering a reference for data scale and architecture design.

  3. arXiv cs.RO80

    SimuGuard: Auditing Contact Artifacts in Simulation Benchmarks Such as LIBERO and RoboTwin

    The authors propose SimuGuard, an auditing plugin for LIBERO, RoboTwin, RoboCasa, and RoboDojo that identifies failures caused by the simulator rather than the policy. On RoboTwin, the authors trace these failures to the physics engine's collision detection: when geometry is 1 to 2 centimeters apart, the engine reports a penetration of about 2 centimeters, and the solver ejects the object at several meters per second because the distance algorithm discards triangles below a fixed area threshold.

    Why it matters: The original traces failures in simulation benchmarks to a physics engine collision detection constant and provides a before-and-after success rate comparison, which can serve as a reference for teams doing simulation evaluation.

  4. arXiv cs.RO78

    ∇Mimic: Efficient Whole-Body Control for Humanoid Robots with Differentiable Simulation

    The authors propose ∇Mimic, which uses exact gradients from a differentiable simulator to train whole-body motion-tracking policies for humanoid robots, reaching a score of 0.82 in 20 minutes and 0.874 in 1.8 hours on a single GPU, whereas the world-model method takes 1.2 hours to reach 0.82.

    Why it matters: The paper presents a complete scheme for training humanoid policies with exact gradients under differentiable simulation and open-sources the engine and code, making it easy to compare the efficiency of first-order and zeroth-order methods.

  5. HuggingFace Daily Papers76

    RoboColosseum: A distributed real-world robot policy evaluation framework across four embodiments

    RoboColosseum is a distributed evaluation framework that evaluates general-purpose robot policies over a network of locally operated robots in multiple locations, using unified policy serving and standardized protocols.

    Why it matters: This distributed evaluation framework used 5,699 paired trials to compare VLA policies with frontier agents, revealing inconsistent rankings across embodiments and a ranking reversal after fine-tuning.

  1. 甲子光年 · 微信公众号78

    Peking University's Dong Hao team proposes One Scan is Enough: embodied navigation post-training with a single scan

    Dong Hao's team at Peking University has published the paper "One Scan is Enough," which uses a LiDAR-equipped iPhone to scan a target environment once, automatically generates navigation tasks, and uses the reconstructed scene geometry for reinforcement post-training, without needing manual teleoperation demonstrations.

    Why it matters: A single iPhone scan replaces manual demonstrations; 200 real-robot tests give a success-rate comparison from 25% to 85%, showing how post-training costs could fall.

  1. Leiphone Robotics78

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

    At IROS 2026, Columbia University's Yunzhu Li team presented progress on FlexiTac, an open-source flexible piezoresistive tactile sensor platform, a year and a half after its open-source release. The sensor can be assembled in 3 minutes, bent and cut, and wrapped around gloves, fingertips, or robot skin. The team has integrated it into LeRobot and modified the UMI handheld device to add tactile recording, enabling synchronized visual-tactile data collection and policy pretraining. ADI is advancing a commercial version with tactile resolution five times that of a human finger, manufactured at scale using semiconductor fabrication processes.

    Why it matters: From sensor design and simulation calibration to UMI data collection, it presents a complete technical path toward scaling tactile perception.

  2. 3D视觉工坊 · 微信公众号88

    Infinigence AI, Tsinghua and AgiBot propose Collective Experience Learning (CEL), validated on 96 robots with 98.3% success rate

    Infinigence AI, together with Tsinghua University and AgiBot, proposed the Collective Experience Learning (CEL) paradigm and completed prototype validation on 96 robots. In a phone packaging task, policies trained with CEL completed 120 tests on two robots of the same model that did not participate in training, with the success rate rising from 79.2% to 98.3%; when the number of robots participating in learning increased from 16 to 96, the test success rate rose from 86.7% to 98.3%.

    Why it matters: Fault-tolerant asynchronous training across a 96-robot real-machine cluster and failure-guided experience retrieval provide a reproducible system and scale-benefit data for Collective Experience Learning.