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。

42 篇论文
主题全部操作 76VLA 65导航 35机器人综合 32机器人学习 27感知 22人形机器人 21仿真 15运动控制 13安全 11World Action Models 4World-action model 3Aerial 2Aerial manipulation 2Dexterous manipulation 2Sim-to-Real Manipulation 2Social Navigation 2Vision-Language Navigation 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 1Continual reinforcement learning on top of robot foundation models 1Continuum sensing 1Cross-embodiment transfer of humanoid whole-body controllers 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 1Evaluating robot world models against real executions 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 loco-manipulation 1Humanoid safety 1Humanoid whole-body control 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 Optimization 1Preference Learning 1Quadruped locomotion 1Real-time VLA 1Real-to-sim 1Reinforcement learning for industrial assembly 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 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 models 1World-Action Models 1
难度不限入门进阶专业
暂无中文版，显示英文原文。
按技术筛选：强化学习，清除
arXiv
VLA专业

Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning

Seongmin Park, Jaewon Lee, Yujun Heo, Yoonsik Kim, Seheon Choi, Hyoung-rock Kim, Jungwook Choi

Quantization lowers deployment costs of vision-language-action (VLA) policies but can compromise task completion. Across five VLA models and 4,050 real-world trials, we systematically reveal that quantization-aware training (QAT) generally improves on post-training quantization (PTQ) but leaves substantial gaps to full precision (FP) on long-horizon tasks and under visual and semantic shifts, while its imitation-based objective does not explicitly use rollout success or partial completion.

VLARL
阅读论文全文（PDF）
arXiv
Locomotion专业

PointWalker: Mapless Quadruped Locomotion Directly From Raw LiDAR Point Clouds

Sicen Li, Zhen Chu, Chao Li, Jun Zheng, Qiuguo Zhu, Jun Wu

Quadruped robots deployed for inspection and field missions must cross heterogeneous terrain, from stairs, slopes, and gaps to high platforms, stepping stones, and balance beams, where safe support is sparse or see-through. Existing methods interpose a terrain map or a depth image between sensing and control.

RL激光雷达
DEEP Robotics
阅读论文全文（PDF）
arXiv
Humanoid专业

P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning

Xue Wang, Yitang Li, Yiming Zhang, Siqin Wang, Junhan Sun, Zhihao Liu, Yaojie Shen, Jingbo Yuan, Hao Zhao, Qingdu Li

Behavioral foundation models (BFMs) provide humanoids with reusable repertoires of whole-body behaviors; in real-world humanoid control, the same behavioral intent may require fundamentally different motions under different terrain constraints. Covering such variation with terrain-matched demonstrations requires enumerating a combinatorial space of behaviors and terrain geometries.

RL
HumanoidFoundation
阅读论文全文（PDF）
arXiv
Learning专业

Reinforcement Learning Based Heterogeneous Task Allocation Under Spatio-Temporal Environmental Uncertainty for Multi-Robot Teams

Xi Lin, Yaxuan Li, Paul Szenher, Brendan Englot

Autonomous Surface Vehicles (ASVs) have been increasingly deployed to perform different kinds of maritime tasks in recent years, which motivates the need for a reliable task allocation policy that can adapt to heterogeneous tasks and maritime disturbances. In this work, we formulate a multi-robot task allocation problem in which a team of ASVs with heterogeneous capabilities needs to complete tasks of different types and appearance times under unknown stochastic spatio-temporal uncertainties from maritime disturbances.

RL
阅读论文全文（PDF）
arXiv
Learning专业

Phase-Gated Constrained Reinforcement Learning for End-to-End Capture and Detumbling of Non-Cooperative Targets

Álvaro Belmonte-Baeza, Celia Redondo-Verdú, José L. Ramón, Miguel Cazorla, Leonard Felicetti, Jorge Pomares

Active debris removal requires a servicer spacecraft to approach a non-cooperative tumbling object, capture it, and arrest its rotation. This sequence is conventionally divided among phase-specific controllers, each depending on knowledge of the target's inertia, a dedicated grappling fixture, or a hand-designed switch at the contact-rich seam where such pipelines are most fragile.

RL
阅读论文全文（PDF）
arXiv
VLA专业

Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving

Yuechen Luo, He Chong, Fang Li, Shaoqing Xu, Hexin Zhang, Ruiqi Zhang, Ziying Song, Lei Yang, Zhi-Xin Yang, Fuxi Wen

Reinforcement Learning (RL) substantially improves planning performance in autonomous-driving Vision-Language-Action (VLA) models. However, existing RL methods rely on scalar trajectory rewards that measure overall quality but fail to identify specific planning errors or provide actionable correction signals.

VLARL
阅读论文全文（PDF）
arXiv
Manipulation专业

Evo-RL: Iterative Robot Reinforcement Learning from Selective Experience

Kai Ye, Yifan Jin, Qianhang Luo, Hongru Zhang, Jiedong Zhang, Shuyuan Hu, Song-Yuan Wu, Jihai Xu, Jie Zhao, Bo Zhao

Existing real-world reinforcement learning methods improve robot policies by combining human corrections with autonomous rollouts. However, accumulated experience varies in its value for policy improvement, and even successful trajectories can contain inefficient or redundant behavior, motivating more selective experience reuse.

RL
阅读论文全文（PDF）
arXiv
Learning专业

Dream to Remember: Continual Steering of Generalist Robot Policies with World Models

Bahey Tharwat, Iman Nematollahi, Marvin Alles, Xingyuan Zhang, Akshay L Chandra, Abhinav Valada

Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy.

世界模型模仿学习RL
阅读论文全文（PDF）
arXiv
Learning专业

MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS

Tom Philipp Backert, Mohammad D. Soorati, Javad Ghofrani

Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulator is widely used to study emergent swarm behavior. Yet despite this growth, systematic support for reuse and reproducibility in MARL-based swarm robotics remains limited and insufficiently standardized: a single experiment is assembled from manually aligned simulator files, training scripts, configuration values, paths, seeds, and environment details, so reuse and reproduction stay fragile even within one research group.

RL
阅读论文全文（PDF）
arXiv
Visual Generalization专业

VIGOR：潜空间一致性驱动模型强化学习零样本视觉泛化

Mingyu Park, Samyeul Noh, Hyun Myung, Donghwan Lee

本文提出VIGOR框架，在TD-MPC2骨干上融入非对称弱到强增强（AW）、动力学一致性（DC）和编码器稳定化（ES），解决基于模型的强化学习（MBRL）在未见视觉干扰下的两层级脆弱性。在DeepMind Control Suite和Robosuite的零样本泛化评测中，VIGOR分别超越次优基线3.4%和43.6%，同时保持TD-MPC2的样本效率。该论文为预印本，尚未经过同行评审。

RL
阅读论文全文（PDF）
arXiv
Lifelong RL专业

AMSC 用任务相似度挑选复用策略面具，提升终身强化学习前向迁移

Saptarshi Nath, Inish M. D'Souza, Antonio Carta, Soheil Kolouri, Andrea Soltoggio

这篇预印本提出 AMSC，一种利用在线任务相似度选择并组合先前策略面具的方法。在 CT28 和 MG16 上，AMSC 的 AUC 和 FWT 分别为 0.94/0.94 和 0.73/0.54，且遗忘为零；但在 CW10 上不如学习式组合。结果表明任务相似度可作为一种免优化信号来提升终身强化学习的复用效果，但跨层组合仍需改进。

RL
阅读论文全文（PDF）
arXiv
Multi-agent RL专业

SCOUT：测试时分解价值梯度传输实现离线多智能体协调

Dongsu Lee, Haoran Xu, Amy Zhang

本文为arXiv预印本，提出SCOUT框架，将流匹配行为先验与分解价值函数解耦，在测试时通过Stein变分梯度下降把动作样本传输到高价值区域，避免训练时策略参数化和固定正则化系数。在SMACv1和MA-MuJoCo共24个离线数据集上平均得分最高，并在全部离线到在线实验中取得提升。该方法为生成式策略与值优化提供了一种不牺牲多模态的测试时精修路径。

RL
Foundation
阅读论文全文（PDF）
arXiv
Legged Manipulation专业

ReCo：用响应一致运动与策略感知MPC提升腿式移动操作轨迹跟踪

Kuankuan Sima, Yichao Gao, Chenxi Gu, Kefan Zhao, Lin Zhao

这篇预印本提出ReCo框架，通过训练响应一致的四足运动策略并识别其闭环响应模型，让策略感知MPC同时规划运动指令和机械臂动作。在MuJoCo仿真基准中，位置和姿态RMSE分别比各自最优基线降低28.7%和27.4%，100轮测试成功75次。真机实验展示了在Unitree Go2加ARX X5平台上进行物体整理、开门和抓取放置等连续移动操作。

RL
阅读论文全文（PDF）
arXiv
Policy Optimization专业

FERPO：前向熵正则化策略优化

Sebastian Sanokowski, Alireza Sarmadi, Majid Khadiv

这篇预印本提出 FERPO，一种在线最大熵强化学习算法。它不用评论家对动作的梯度，而是通过前向 KL 拟合熵与 KL 正则化的最优目标分布来更新策略。在 MuJoCo Playground 和 ManiSkill 上表现与 REPPO 相当，并在 DMC 和 ManiSkill 上展现出更高样本效率；在 K=16 时，未缓存 actor 更新比 REPPO 快 6.9%，缓存后总计节省 22.2%。

RL
阅读论文全文（PDF）
arXiv
Multi-fidelity RL专业

MFPG-PPO 用低保真仿真数据稳定数据稀缺强化学习，真机仅4条片段提升抓取成功率

Xinjie Liu, Ruihan Zhao, Anirban Chaudhuri, Cyrus Neary, Ufuk Topcu, David Fridovich-Keil

这篇预印本提出 MFPG-PPO 算法，用低成本仿真数据作为控制变量来稳定高保真数据稀缺的强化学习。在仿真和真机实验中，MFPG-PPO 在多数设置下优于仅用高保真数据的 PPO，并且用 4 条真实机器人片段即可将 Franka 抓取成功率从 40% 提升至 91.7%。该论文尚未经过同行评审。

RL
阅读论文全文（PDF）
arXiv
Tactile Exploration专业

触觉好奇心驱动机器人交互：TacEx框架用触觉不确定性引导探索

Klemens Iten, Alexander Proshkin, Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza

TacEx是一个预印本框架，通过将模型认知不确定性按视觉、触觉和潜变量分解并加权触觉项，让机器人在无任务奖励的探索阶段主动寻求接触。在仿真中，纯触觉探索实现了零奖励涌现抓取，采集的接触密集数据支持离线训练抓放策略；在LIBERO-90八个接触丰富任务上，用触觉不确定性引导冻结VLA的扩散后训练，成功率高于DSRL-SAC基线。该工作表明触觉不仅是观测模态，也是高效的探索信号。

RL
阅读论文全文（PDF）
arXiv
Grounding专业

GroundingPI：以视觉基元构建4B接地基础模型，34项基准平均73.68%超越GPT-6 Astra

Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang, Yi Zou, Kaixuan Wang, Tianxing Chen, Wenxuan Song, Bohan Zhou, Mingleyang Li, Siqiao Huang, Yuqi Ye, Caigao Jiang, Wei Wei, Ruihai Wu, Hang Zhang

这是一篇预印本论文。作者提出 GroundingPI，一个基于点和边界框等视觉基元的 4B 参数接地基础模型，在 34 个接地基准上达到 73.68% 平均得分，超过更大的 GPT-6 Astra（71.54%）。该模型作为视觉骨干用于机器人操作和自动驾驶时，在 RoboTwin 2.0 全部四个分布外设置中优于所有主流骨干，相对最强基线最高提升 24.8%，并在 RoboCasa-GR1 上以 50% 演示数据超过其他基线用 75% 数据的表现。这项工作表明专门的接地预训练可成为物理智能的感知基础，尤其适合系统1的快速执行。

VLARL
Physical Intelligence
阅读论文全文（PDF）
arXiv
Safe RL-MPC专业

RL引导PAC-NMPC：固定翼无人机视觉导航实现概率安全与远见

Adam Polevoy, Dillon Capalongo, Katherine Tang, Mark Gonzales, Marin Kobilarov, Joseph Moore

本文提出将强化学习训练的actor-critic和传感器预测模型嵌入PAC-NMPC框架，为未知环境中基于感知的导航提供有限时间概率安全保证和长期性能。在固定翼无人机上，该方法在仿真中取得90%成功率，在硬件试验中取得80%成功率，均优于纯RL和传统规划基线。本文为预印本，未经同行评审。

RL
阅读论文全文（PDF）
arXiv
Battery-aware RL专业

电池感知强化学习让Crazyflie Brushless赛道时间缩短10.3%：滤波电压输入解锁更高推力指令

Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren

该预印本提出一种电池感知强化学习控制方法，在38克Crazyflie Brushless真机上联合增加推力指令范围和滤波电压输入，同时保留飞控的电压补偿和速率控制。硬件实验中，3.84 m/s圆周跟踪误差较Stock降低49.3%，20圈赛道时间从106.22秒降至95.24秒。相比同样增加指令范围但不使用电压输入的High，误差降低15.3%、赛道时间快4.5%。结果表明显式电压信息能补充飞控原有补偿。

RL
阅读论文全文（PDF）

主题页

操作 8VLA 4World Action Models 5World-action model 3Aerial 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。