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
按技术筛选：强化学习，清除
arXiv
Adaptive intervention进阶

UniIntervene++自适应分配干预，真机强化学习人类介入率降至0.77%

Yudong Lin, Haoyuan Deng, Zhuoxuan Yuan, Zaijia Yang, Yuanjiang Xue, Ziwei Wang

这篇arXiv预印本尚未经过同行评审。作者提出UniIntervene++，一种在真实机器人在线强化学习中动态分配自主执行与多种辅助行为的干预智能体。它在五个真实操作任务上平均成功率达89.67%，比最强基线高6个百分点，人类介入率仅0.77%，比基线中最低的14.29%相对降低94.6%。

RL
阅读论文全文（PDF）
arXiv
Curriculum RL进阶

BVER：从两端双向扩展的 Voronoi 偏置课程让机器人学习稀疏奖励任务更快

Juri Pfammatter, Kaixian Qu, Clemens Schwarke, Victor Klemm, Marco Hutter

BVER 是一个预印本方法，提出从目标状态和初始分布两端同时扩展中间起点与目标，训练单个目标条件策略。在仿真中，它在点质量迷宫、四足盒攀爬和机械臂套环转移任务上比所有无参考课程学习更快，攀爬 0.4 米盒时达到 95% 成功率的迭代数比最佳无参考基线少约 65%，并且是唯一能学会攀爬 0.7 米盒的无参考方法。该方法无需演示或奖励塑形，对稀疏奖励长程机器人任务训练具有实际价值。

RL
阅读论文全文（PDF）
arXiv
Quadruped locomotion进阶

PROMO用单一策略让四足机器人在跟踪、稳定与能效间实时切换偏好

Amr Mousa, Rifny Rachman, Neil Karavis, Michele Caprio, Richard Allmendinger

PROMO是一个预印本框架，将跟踪、稳定、能效作为语义目标，通过偏好向量在运行时控制单一四足机器人策略。仿真中100个偏好下67个为非支配解，平均偏好与目标相关性0.8434。真机Unitree Go2上仅改变偏好，能效较平衡偏好最高降低30.4%，位置误差降低38.7%，姿态偏差降低59.0%。

RL
阅读论文全文（PDF）
arXiv
Endoscopic navigation进阶

ColoACT：多线索动作分块实现自推进内镜机器人平滑结肠导航

Jian Hu, Shujing He, Leixin Chang, Zongze Li, Ding Huang, Chaoyang Shi, Chengzhi Hu

这篇预印本提出 ColoACT 系统，将 RGB、相对深度和伪高程图结合成多线索观测，并用 Action Chunking Transformer 策略控制自推进内镜机器人 BGER。在离体猪结肠中，直线段成功率为 85.4%，弯曲段为 72.5%，复杂弯道也有一定成功率，动作平滑性比行为克隆基线改善约一个数量级。这是首次在自推进结肠机器人上验证模仿学习导航，尚未经过同行评审。

RL
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。