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。

75 篇论文
主题全部Manipulation 76VLA 66Navigation 35Robotics 32Learning 27Perception 22Humanoid 21Simulation 15Locomotion 14Safety 11World Action Models 4World-action model 3Aerial 2Aerial manipulation 2Dexterous manipulation 2Sim-to-Real Manipulation 2Social Navigation 2Vision-Language Navigation 2World models 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 control 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 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 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
暂无中文版,显示英文原文。
arXiv
Memory-centric VLA进阶

Optimus-R:记忆中心VLA框架实现低数据适应与终身学习

Zaijing Li, Rui Shao, Bing Hu, Haoyu Zhang, Dongmei Jiang, Liqiang Nie

本文提出预印本方法Optimus-R,一个记忆中心的视觉语言动作模型框架,将机器人适应任务转化为显式的查询技能记忆调优,而非反复更新模型参数。在LIBERO、CALVIN、RoboTwin 2.0仿真基准及真实机器人上,Optimus-R在低数据适应、跨域迁移和终身学习中均优于基线π0.5,显著缓解灾难性遗忘。该框架通过内联记忆接口、查询技能记忆库和轻量桥接适配机制,为机器人持续学习提供了高效路径。

arXiv
Temporal manipulation进阶

PhasePlan 用有序未来阶段规划改进机器人操作动作预测

Xiaoyu Yang, Yafei Zhang, Wensheng Li, Qing Zhan, Nan Wu

这是一篇预印本。作者提出 PhasePlan,一种有序未来阶段规划方法,让机器人脑模型为未来每个动作位置预测任务阶段,并用该阶段信息调节对应动作。在传送带操作任务上,PhasePlan 将离线关节动作误差相对原始 π0.5 降低 22.5%,相对 future-skill histogram 基线降低 12.7%,真机部署也显示连贯执行。

arXiv
Social Navigation进阶

重新思考社交机器人走廊导航中的可读性:意图表征与行人分心的影响

Pranav Goyal, Andrew Stratton, Christoforos Mavrogiannis

这篇arXiv预印本通过两项各45人的真机走廊实验,比较了机器人可读性运动的不同意图表征。结果显示,动态自适应的通行侧可读性(DPL和SM)比目标可读性(GL)和非可读性基线(NL)带来更平滑的人类运动和更高的能力评分;在行人分心时,可读性运动仍能降低人类平均加速度,但主观评分无显著差异。这表明面向交互的意图表征和自适应机制对受限空间协调很重要。

arXiv
Underwater active mapping进阶

相机声纳融合主动建图在水下垃圾搜索中优于割草机覆盖

David Rete, Patrick Boros, Lucian Busoniu

这篇预印本提出一种融合前视声纳与相机的主动水下垃圾建图方法,利用贝叶斯占用栅格和下一步最佳视角规划,在MARUS仿真中比固定割草机模式更快找到全部11个目标,并且双传感器优于任一单独传感器。该方法使用Mask R-CNN进行实例分割,通过数据驱动的传感器模型处理不确定性,有望提升自主水下机器人垃圾调查效率,但尚未经过实地验证。

arXiv
World-action model进阶

Magic-W0:面向物理智能的结构化世界动作基础模型

Xuhua Chen, Zhenhan Yin, Yuan Zhang, Lingfeng Zhang, He Zheng, Tong Mu, Shun Zuo, Dian Zhou, Di Wu, Xuan Zhou, Shaojie Wan, Rongtian Shen, Qiulong Xu, Yiduo Li, Yinglong Wang, Yanqian Wang, Kun Wang, Tao ZhangMagiclab Robotics Inc. (Magic-Lab Team)

机器人企业MagicLab发布预印本,介绍34亿参数的机器人模型Magic-W0,它在决定动作的同时预测场景三维结构会如何运动、动作结束后场景应呈现什么状态。在10月3日的修订版中,它以平均36.75分登上RoboDojo-Sim榜首,但仅领先第二名0.48分;在五项真机任务上以94.6%对91.8%胜过Physical Intelligence的π0.5。

arXiv
Vision-Language Navigation进阶

NavHarness 用自适应目标和验证压缩提高视觉语言导航成功率

Haoxiang Shi, Zaijing Li, Muhe Ding, Xiang Deng, Yaowei Wang, Liqiang Nie

NavHarness 是哈尔滨工业大学(深圳)等机构发布在 arXiv 的预印本框架,面向视觉语言导航任务。它提出目标智能体、验证智能体、记忆智能体和视觉运动智能体,用自适应目标与完成验证对齐执行,并在验证完成时压缩历史。在 R2R-CE 和 RxR-CE 上,基于 GPT-6-Astra 的 NavHarness 零样本成功率分别达到 79.0% 和 82.5%,优于同骨干的 Codex CLI;真机测试成功率 83.3%,导航误差 1.51 米。

arXiv
VLA进阶

ChunkTrust:利用动作专家证据自适应调整机器人策略的执行时域

Fanding Huang, Jingyan Jiang, Shifeng Bao, Mingkang Pu, Shiwei Li, Jing Xu, Shijia Xu, Guanbo Huang, Chenghao Gu, Yuzhi Huang, Chenxin Li, Faisal Nadeem Khan, Huan Yang, Yan Wang, Cheng Chi, Zhi WangTsinghua University, Beijing Academy of Artificial Intelligence (BAAI), Renmin University of China, Shenzhen Technology University, Hefei University of Technology, Jiangnan University, Chongqing University, The Chinese University of Hong Kong

机器人AI模型每次预测一段未来动作,执行多少步之后再重新观察环境,过去大多由工程师手动设为固定值。清华大学、北京智源人工智能研究院(BAAI)等机构发布的这篇预印本提出一个即插即用模块,在运行中自动决定这一步数,无需重新训练,就提升了Physical Intelligence和英伟达现有模型在仿真和真实双臂机器人上的成功率。

arXiv
Trajectory Correction进阶

MaDE:冻结后处理算子将神经轨迹预测强制到学习动力学流形,显著降低残差但位移误差上升

Kevin Yu, Tao Guo, Constantinos Antoniou, Panagiotis Angeloudis

论文提出Markovian Dynamics Enforcer(MaDE),一个无需真值控制、时间不变的后处理算子,可为任意神经轨迹预测器附加动力学一致性与不等式约束修正。在inD真实车辆轨迹上,MaDE将一步运动学自行车模型残差从原始预测器的0.1703至0.1714降至0.0071至0.0072,但平均位移误差增大1.57至1.83倍。该工作为arXiv预印本,未经同行评审。

arXiv
Text-to-3D Policy进阶

T3DP:细粒度语言-行为对齐提升文本到3D策略的未见过规格泛化

Xinhao Yang, Wenhao Wu, Ning Lv, Yanshen Ding, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Zhi Wang

本文提出T3DP框架,通过在指令token和局部行为表示之间建立双向细粒度对齐,让3D扩散策略能执行训练中未出现的精细行为规格。在Meta-World、ManiSkill和RoboTwin上,T3DP较全局语言-行为对齐平均成功率提升11.0至14.2个百分点;在真实机器人上平均成功率从47.5%升至65.0%。该工作为预印本,尚未经过同行评审。

arXiv
Social Navigation进阶

Social-WM:用可执行动作差异做安全社交导航的隐世界模型

Zhihao Zheng, Mooi Choo Chuah

Social-WM 是一个使用 RGB 视频离线训练的隐世界模型规划框架,区分名义动作与实际可执行动作。在 Social-HM3D 上,它取得 63.77% 成功率,行人碰撞率降至 21.67%,比 NavThinker 相对降低 44.6%;零样本迁移到 Social-MP3D 仍保持 54.15% 成功率和 23.34% 碰撞率。该工作为未同行评审的预印本。

arXiv
Manipulation进阶

RoboCoach 让世界模型主动当教练:想象失败后定向补数据,真机成功率升至 75.0% 和 83.8%

Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang

RoboCoach 是一个预印本框架,用世界模型中的想象执行来诊断长程机器人任务中最先失败的子任务,并据此请求对应技能专家的演示数据。在 Franka 和 AgileX 真机上,仅追加 150 条子任务演示,成功率分别从 13.3% 升至 75.0%、从 40.0% 升至 83.8%,显著超过统一采集加共享适配器的基线。该工作表明世界模型可以成为主动教练,把稀缺的真实数据导向可复用的技能模块。

arXiv
Manipulation进阶

Encore:编码智能体用少量演示发现机械臂操作策略,LIBERO-PRO扰动集成功率96.3%

Yifan Kang, Zihan Wang, Zhiwen Fan, Bangya Liu

这篇arXiv预印本提出Encore框架,将遥操作演示蒸馏为编码智能体可查询的证据包,让智能体编写、运行并迭代修复策略程序,运行时不调用模型。在LIBERO-PRO的60个扰动单元上,3条演示的冻结程序在3000个密封回合中成功2889次(96.3%),无演示为2846次(94.9%);在RoboDojo上无演示全部失败,3条演示在前10个任务取得95/450成功。双臂真机上完成手递手和杯子倒扣,各9/10成功。

arXiv
Mining Perception进阶

Towards Spatial Perception for Heterogeneous Robot Collaboration in Subterranean Mining Environments

Mario Alberto Valdes Saucedo, Akash Patel, Christoforos Kanellakis, George Nikolakopoulos

In this preprint, the authors build an onboard perception pipeline that lets a lightweight Explorer robot find minerals in underground mines from free-text prompts and hand compact, oriented 3D inspection targets to a heavier Inspector robot. Field tests in a test mine and an active magnesite mine detected two mineral types without retraining and condensed about 38,000 raw mineral points into a few dozen polygons, roughly two orders of magnitude smaller. This matters because autonomous mining inspection requires no mine-specific labels and low-bandwidth robot-to-robot handover.

主题页

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。