MEKAWIRE
研究

论文

机器人与具身智能领域的最新论文，以及每篇对产业的意义。

4 篇论文
主题全部Manipulation 65VLA 43Navigation 24Learning 23Robotics 22Perception 20Humanoid 15Safety 9Simulation 9Locomotion 8World Action Models 4Aerial 2Aerial manipulation 2Dexterous manipulation 2Sim-to-Real Manipulation 2Social Navigation 2Vision-Language Navigation 2World models 2World-action model 23D Assembly 13DGS dataset 15G Simulation 1AMR Operations 1Active vision manipulation 1Adaptive MPC 1Adaptive action horizons 1Adaptive intervention 1Aerial Manipulation 1Aerial navigation 1Agricultural Robotics 1Articulation Estimation 1Autonomous Driving 1Autonomous Exploration 1Battery-aware RL 1Belief-space planning 1Bimanual Manipulation 1Byzantine localization 1Canal inspection 1Co-speech Humanoid 1Compositional Manipulation 1Construction navigation 1Contact-Rich Manipulation 1Contact-rich Manipulation 1Continuum sensing 1Curriculum RL 1Dexterous Manipulation 1Distributed Manipulation 1Distribution Shift 1Driving Simulation 1Efficient VIO 1Egocentric data 1Egocentric video 1Embodied Agents 1Embodied policy 1Empowerment MPC 1Endoscopic navigation 1Endovascular robotics 1Event-camera VO 1Exoskeletons 1Failure recovery 1Federated 3D Perception 1Fisheye detection 1Floorplan SLAM 1Geometry-aware manipulation 1Grasping 1Grounding 1Humanoid Control 1Humanoid RL 1Humanoid Tool Use 1Humanoid control 1Humanoid loco-manipulation 1Humanoid safety 1Imitation Learning 1JEPA World Models 1Lab automation 1Laboratory Manipulation 1Latent World Models 1Legged Manipulation 1LiDAR Security 1Lifelong RL 1MAPF 1MAV guidance 1Manipulation LfD 1Manipulation Safety 1Marine simulation 1Memory-centric VLA 1Miniature Locomotion 1Mining Perception 1Mobile manipulation 1Model-based RL 1Monocular SSC 1Motion Planning 1Multi-Agent RL 1Multi-Robot Exploration 1Multi-Robot Manipulation 1Multi-UAV Exploration 1Multi-UAV State Estimation 1Multi-agent RL 1Multi-agent motion planning 1Multi-camera odometry 1Multi-fidelity RL 1Multi-robot manipulation 1Multi-skill Manipulation 1Multi-view perception 1Multimodal simulation 1Navigation & Mapping 1Object Pose Estimation 1Object Search 1Panoramic 3D Detection 1Panoramic segmentation 1Pedestrian tracking 1PersonNav 1Planning 1Policy 1Policy Optimization 1Preference Learning 1Quadruped locomotion 1Real-time VLA 1Real-to-sim 1Representation alignment 1Robot-Use Agents 1Runtime Verification 1Safe Generative Planning 1Safe RL-MPC 1Safe VLA 1Safety monitoring 1Safety-critical control 1Sim-to-real Navigation 1Sim-to-real manipulation 1Simulation geometry 1Skill Discovery 1Social navigation 1Soft Pneumatic Actuators 1Soft manipulation 1Sonar SLAM 1Streaming 3D reconstruction 1Submovement decomposition 1Surgical 1Surgical robotics 1Tactile 1Tactile Exploration 1Tactile VLA 1Temporal manipulation 1Terrain traversability 1Text-to-3D Policy 1Tool Co-Design 1Trajectory Correction 1Traversability 1UAV Navigation 1UAV Swarms 1UAV traffic monitoring 1Underwater Robotics 1Underwater active mapping 1Underwater perception 1Unified world-action model 1VLA Conditioning 1VLA Defense 1VLA Robustness 1VLA evaluation 1VLA manipulation 1VLA robustness 1Video world models 1Visual Generalization 1Visual Grounding 1Visual Reward Models 1Visuomotor Fusion 1Visuotactile manipulation 1World Models 1World-Action Models 1
难度不限入门进阶专业
arXiv
World Action Models专业

NAVA-WAM 从无动作视频直接预训练动作策略，改进世界动作模型泛化

Zhaochong An, Fei Zhang, Menglin Jia, Duncan Frost, Zijian Zhou, Yikai Wang, Xudong Wang, Aditya Patel, Belinda Zeng, Tao Xiang, Serge Belongie, Amir Bar, Sen He

本预印本提出 NAVA-WAM，一种世界动作模型，通过未来视频流匹配直接在无动作视频上预训练动作策略，避免了中间表示或潜在动作接口。在 LIBERO、RoboTwin 2.0 以及 Franka FR3 真机实验中，该方法分别达到 99.0%、83.5%、88.5%、73.6% 和 93.3% 的成功率，并在低动作标签预算下显著优于基线。该结果展示了从规模化无动作视频中直接学习动作先验的潜力，为降低对带动作标签机器人数据的依赖提供新路径。

阅读论文全文（PDF）
arXiv
World Action Models专业

XGenAct 将深度、法向与语义分割统一为视频生成，RLBench 未见过任务成功率 52%

Tingting Du, Ziyao Wang, Guoheng Sun, Ang Li

预印本 XGenAct 将 RGB、7 自由度动作、度量深度、表面法向和功能角色分割全部表示为 RGB 视频，通过一个共享的视频扩散 Transformer 进行跨任务生成。在未见过的 RLBench 任务上，结构化感知训练使平均闭环成功率比仅 RGB 训练提高最多 28.75 个百分点，五任务外部对比达到 52%，是最强基线（26%）的两倍。该方法避免了模态专用预测头或辅助损失，为机器人世界动作模型提供了一条可扩展的几何增强路径。

阅读论文全文（PDF）
arXiv
World Action Models进阶

CAG训练无关引导缓解世界动作模型任务不完整想象

Seungyeon Kim, Junhoo Lee, Baekseung Kim, Minkyu Kim, Nojun Kwak

本文是一篇预印本。研究者发现世界动作模型(WAM)在短视界控制中会产生任务不完整想象，即视觉与动作一致但遗漏完成任务所需的状态转换。他们提出无需训练的采样方法Completion Aware Guidance (CAG)，通过强化当前预测相关的指令条件，将RoboTwin 2.0子集平均成功率从64.4%提升至70.0%，并将零样本仿真中任务不完整想象比例从79%降至40%。

阅读论文全文（PDF）
arXiv
World Action Models专业

ProWAM用渐进式视觉子目标刷新WAM基准，零样本真机成功率70.0%

Fei Zhang, Zhaochong An, Duncan Frost, Yikai Wang, Pengfei Liu, Ya Zhang, Michal Drozdzal, Amir Bar

ProWAM是一种世界动作模型，通过预测按归一化任务进度索引的稀疏视觉子目标来引导动作生成，避免生成稠密视频。在LIBERO-Plus上达到85.8%，RoboTwin随机场景75.7%，零样本真机任务70.0%，超过最强基线DreamZero的55.0%。该论文为arXiv预印本，尚未经过同行评审。

阅读论文全文（PDF）

主题页

操作 8VLA 4World Action Models 5Aerial manipulation 3Dexterous manipulation 3Sim-to-Real Manipulation 3Social Navigation 3

论文来自 arXiv 机器人领域。尚未生成摘要的论文，显示摘要开头部分。