研究主题
Making touch part of the robot's action: a shared code for motion and contact lifts real-world success on peeling, flipping, cutting and wiping by 21 to 36.5 points论文
MEKAWIRE 论文库收录 1 篇Making touch part of the robot's action: a shared code for motion and contact lifts real-world success on peeling, flipping, cutting and wiping by 21 to 36.5 points论文，发表时间从 2026年10月13日 到 2026年10月13日。
已披露的记录尚少，本页暂不进入搜索结果，待数据充实后再开放。
论文数
1
机构数
1
最新论文
2026年10月13日
- National University of Singapore, Anyverse Robotics, Beijing Institute of Technology, University of Chinese Academy of Sciences, Fudan University (Open-Phoenix Team)
- 2026年10月13日
- 无数据
数据截至 2026年10月17日
MEKAWIRE 最新报道
这些论文涉及的技术
主题页
操作 125VLA 93导航 86机器人综合 75仿真 51人形机器人 45机器人学习 41感知 36运动控制 31世界动作模型 27安全 25触觉感知 10空中机器人 5手术机器人 4World Action Models 4humanoids 3Aerial manipulation 2humanoid loco-manipulation planning 2vision-language-action models 2world models 43D Assembly 13DGS dataset 15G Simulation 1A 31-scene sound-triggered mobile manipulation benchmark with 14.36M binaural RIRs; an occupancy-map navigation policy reaches 75.28% in unseen homes vs 71.47% for MAGNet 1A 3D world action model pre-trained on 1.15 million human video episodes reaches 69.0% on ten simulated dexterous-hand tasks, 11.7 points above NVIDIA's GR00T N1.6 1A 50 Hz force-control add-on lifts a pi0 robot model's average score on four contact-rich tasks from 15% to 80% without retraining the model on force data 1A UTS cobot learns latte art from one barista pour, cutting transition errors 3.4x and moving the heart from a 280 ml to a 400 ml cup without a new demonstration 1A coding agent reads three distilled demonstrations, writes and refines a robot policy program, and succeeds on 96.3% of 3,000 sealed LIBERO-PRO episodes against 89.3% for ASPIRE on the same model 1A fast-slow supervising harness with failure attribution lifts a frozen pi0.5 policy from 17.5% to 75.2% on new LIBERO-Pro states with a 4B planner, and reaches 31 of 40 real UR7e trials 1A frontier language model controlling a Franka arm learns from its own failed attempts by tracing late failures back to earlier decisions, with no demonstrations and no weight updates 1A general chat-style vision-language model drives a robot arm through mid-level commands and live feedback, with no robot training data 1A reinforcement-learning reaching controller trained only in Isaac Lab that guides a UR10e arm to the stem of hydroponic lettuce without touching the growing channels 1A skill-based agent on pi0.5 lifts real Astribot S1 success from 10% to 57.5% by retraining on about 20 self-curated runs per task per round. 1A task-space model predictive contouring controller with a constrained joint-velocity layer keeps a UR5e tool 20 to 22% closer on average to a path whose frame is knocked mid-motion than PI control or time-indexed MPC, while peak error stays unchanged 1A vision-language task predictor reading a self-revising finite-state memory of the user's routine, with pi0.5 as executor, completes 41 of 60 proactive desk-assistance tasks on a Franka arm against 23 for pi0.5 alone 1AMR Operations 1Active vision manipulation 1Adaptive MPC 1Adaptive action horizons 1Adaptive intervention 1Adding a tactile expert to the pi0.5 vision-language-action model so a robot learns contact-heavy tasks such as wiping, inserting and picking up chips from 50 demonstrations, without a separate tactile pretraining stage 1Aerial navigation 1Agricultural Robotics 1An ACT policy that outputs only end-effector force and torque, trained on bilateral force-feedback teleoperation data, averages 76.8% on five contact-rich assembly tasks against 40% for a position-based baseline 1Articulation Estimation 1Asking pi0.5 for an intent such as clearing a table instead of naming the action costs 15.2 points of task success, and people decompose multi-step requests less as tasks grow 1Autonomous Driving 1Autonomous Exploration 1BAAI's Human2Dex trains two different robot hands from one set of human wrist-camera videos, reaching 90.8% success on the Linker O6 and 80.8% on the 20-DoF Wuji hand across six real tasks, up from 26.3% with raw human data. 1Battery-aware RL 1Belief-space planning 1Blending operator corrections with the policy's own actions during interactive imitation learning lifted real-robot success to 50% from 15% and to 70% from 40% against HG-DAgger, with 57% smoother hand-overs 1Byzantine localization 1Canal inspection 1Choosing among 16 sampled human reactions after retargeting them to a Unitree G1 shows the best human motion and the best robot motion differ in 78.98% of cases, and raises retargeting feasibility by 1.61% at 9.2 Hz. 1Coding agents that control robots and keep what they learn as reusable skills and lessons 1Compositional Manipulation 1Construction navigation 1Contact-Rich Manipulation 1Continual reinforcement learning on top of robot foundation models 1Continuum sensing 1Controllable multimodal flow-matching policies 1Controlled comparison of how to add world models to VLA robot policies 1Curriculum RL 1Distributed Manipulation 1Distribution Shift 1Driving Simulation 1Efficient VIO 1Egocentric video 1Embodied Agents 1Embodied policy 1Empowerment MPC 1Endoscopic navigation 1Endovascular robotics 1Event-camera VO 1Exoskeletons 1Failure recovery 1Federated 3D Perception 1Fine-tuning pretrained robot policies such as NVIDIA's GR00T N1.7 on a few demonstrations without losing robustness to new camera views, backgrounds and objects 1Fisheye detection 1Floorplan SLAM 1Force-aware VLA 1ForceWAM reaches 85% to 95% real-robot success on four force-sensitive tasks on a Flexiv arm, against 20% to 65% for the best of seven baselines, by predicting future force as well as video. 1Geometry-aware manipulation 1Grasping 1Humanoid whole-body control 2Humanoid whole-body control with a behavior world model 1Imitation Learning 1JEPA World Models 1Lab automation 1Laboratory Manipulation 1Latent World Models 1LiDAR Security 1Lifelong RL 1Long-horizon manipulation with a language-planned world-action model 1Low-cost passive compliant leader arm for consistent imitation-learning data 1MAPF 1MAV guidance 1Manipulation LfD 1Marine simulation 1Miniature Locomotion 1Mining Perception 1Mobile manipulation from human video 1Monocular SSC 1Motion Planning 1Multi-Agent RL 2Multi-Robot Exploration 1Multi-Robot Manipulation 2Multi-UAV Exploration 1Multi-UAV State Estimation 1Multi-agent motion planning 1Multi-fidelity RL 1Multi-skill Manipulation 1Multi-view perception 1Multimodal simulation 1NVIDIA's Robota-Embed finds the right past robot experience 47.33% of the time at clip level against 25.2% for Gemini Embedding 2, and feeding that experience to policies lifts DROID-Sim success from 47.0% to 56.3%. 1National Tsing Hua University researchers show fine-tuned pi0.5 and GR00T N1.7 policies replay memorised tasks when a request needs a new action, and fix it with paired counterfactual training that lifts real UR5e unseen-position success from 3/40 to 35/40 1Navigation & Mapping 1Object Pose Estimation 1Object Search 1Object-centric 3D world models for model-predictive manipulation 1One reinforcement-learning policy that walks a Unitree Go2 with a 6-DoF arm and places the gripper to within 3.22 cm under simulated lunar gravity, with safety limits enforced during training 1Optimus-R adds a 7M-parameter skill memory to pi0.5 and reaches 88.6% on LIBERO with 30% of the data, versus 72.1% for full fine-tuning, while training in 86 instead of 560 GPU hours. 1Panoramic 3D Detection 1Panoramic segmentation 1Pedestrian tracking 1PersonNav 1Planning 1Playing robot demonstrations backwards and at different speeds let a policy trained on 50 demos reach 85.2% success on 16 RoboTwin tasks, level with a baseline trained on 100. 1Policy Optimization 1Pretraining a delivery robot's navigation model on 10,000 hours of first-person human walking video by predicting scene structure instead of pixels, then adapting it with 17 hours of robot driving 1Quadruped loco-manipulation: learned whole-body control 1Quadruped locomotion 1Real-time VLA 1Real-to-sim 1Reinforcement learning for industrial assembly 1Representation alignment 1Robot-Use Agents 1Runtime Verification 1Runtime recovery for a frozen VLA policy: a latent world model forecasts whether to keep going, move the camera or replan the arm 1Safe Generative Planning 1Safe RL-MPC 1SafeDriveVLA cut collisions under unsafe spoken instructions from 60 to 38 and raised driving score to 85.9 from 72.8 against SimLingo in CARLA, by imagining what would happen if it obeyed before acting. 1Safety monitoring 1Safety-critical control 1Scissor-shaped handheld teaching tool that lets people feel grip forces while recording robot demonstrations, used to fine-tune pi0.5 on dual-arm Franka and Flexiv robots 1Shrinking a 3.3-billion-parameter robot foundation model into a 451-million-parameter student that runs in two inference steps 1Simulation geometry 1Skill Discovery 1Social Navigation 2Social-WM cuts human collisions in simulated crowd navigation to 21.67% from 39.09% for the NavThinker world-model baseline (44.6% fewer) while raising success to 63.77%, by learning which commanded moves a robot can actually carry out near people. 1Soft Pneumatic Actuators 1Soft manipulation 1Sonar SLAM 1Speeding up world-model-based visual navigation by screening candidate trajectories with a distilled long-stride latent model before refining with an autoregressive teacher. 1Starting a robot policy's flow-matching generation from its own recent actions and frames instead of random noise, so vision-language-action and world-action models train in fewer epochs and act in one sampling step 1Streaming 3D reconstruction 1Submovement decomposition 1Surgical robotics 1Switching off one attack-linked internal feature only when a probe spots an adversarial patch lifts pi0.5 task success under attack from 26.0% to 32.4% without retraining. 1Synthetic data generation for robot policies 1TDV turns one human video into object trajectories that train a robot policy, reaching 91.8% average success on 12 RLBench tasks and 71 of 78 real UR5 trials after augmenting the single demo to 50 trajectories. 1Tactile Exploration 1Temporal manipulation 1Terrain traversability 1Testing whether failure alarms for robot AI models actually save time once false alarms and reset costs are counted 1Text-to-3D Policy 1Tool Co-Design 1Training a VLA for a drone with a robot arm entirely on synthetic trajectories, then chaining local skills across sites with a scene graph to complete multi-step missions 1Trajectory Correction 1Traversability 1Turning first-person human demonstrations into training data a humanoid can use directly, so a vision-language-action model trained without any robot demonstrations can carry objects about 10 m on a Unitree G1 1Turning phone-recorded human demonstrations into per-robot post-training data by retargeting object motion 1Turning recorded human hand-object demonstrations into physically valid robot-hand trajectories with one shared reinforcement-learning policy instead of one optimisation per clip 1Turning third-person human videos of table-tennis serves, pickups and ladder climbing into Unitree G1 skills by preserving where and how fast contacts happen 1UAV Navigation 1UAV Swarms 1UAV traffic monitoring 1USC's WACL lets a robot arm press, push and lift with its forearm while the gripper holds a cup, succeeding in 78% of constrained trials against 33% for a strong baseline, from 10 bare-hand human videos per task. 1Underwater Robotics 1Underwater active mapping 1Underwater perception 1Unified world-action model 1VLA Conditioning 1VLA execution speed 1VLA inference efficiency 1VLA robustness 1VLA robustness benchmark 1VLM preference feedback for robot reinforcement learning 1Video world models 1Vision-Language Navigation 1Vision-based competitive task allocation with a five-frame proposal window and an improved artificial potential field for collision-free dual-arm picking. 1Visual Generalization 1Visual Grounding 1Visual Reward Models 1Visual SLAM for mobile robots 1Visuomotor Fusion 1Weighting rare actions by inverse kernel density lets a behaviour-cloned driving policy trained on eight CARLA routes score 98 instead of 34 in an unseen town, with zero red-light infractions 1Whether labelling messy human demonstrations by quality improves robot foundation models 1World-model view imagination for occlusion-robust manipulation 1compliant humanoid whole-body control 1construction robotics 1dexterous in-hand manipulation with learned world models 1fleet memory for warehouse robots 1humanoid dexterous manipulation 1humanoid learning from human video 1humanoid teleoperation 1humanoid whole-body manipulation 1humanoid-human interaction 1mobile robot navigation 1pi0.5 and VLANeXt both succeed about 69% of the time under a camera shift, but pi0.5's successful runs become 22.5% longer and 24.1% jerkier while VLANeXt's barely change 1real-world reinforcement learning for robot policies 1robot foundation model training 1robot learning from human video 1tactile manipulation 1tactile pretraining for vision-language-action models 1teleoperation and data collection for legged manipulation 1visuo-tactile world models 1world models for dexterous manipulation 1