arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

视觉与机器人

机器人 / 具身智能

机器人、具身智能、机器人学习、操作、导航和具身世界模型。

共收录 61134 信号源:cs.RO, cs.AI, cs.CV, cs.LG

1. 机器人操作 22067 篇

2204.10935 2022-04-26 cs.RO 81%

Certifiable Robot Design Optimization using Differentiable Programming

Charles Dawson, Chuchu Fan

专题命中 机器人操作 :robotics(abstract);manipulation(abstract);navigation(abstract);robotic(abstract)

Comments Accepted for RSS 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2109.04749 2022-02-10 cs.RO 81%

A Holistic Approach to Reactive Mobile Manipulation

Jesse Haviland, Niko Sünderhauf, Peter Corke

专题命中 机器人操作 :manipulation(title,abstract);robotics(comments,journal_ref);分类 cs.RO

Comments IEEE Robotics and Automation Letters (RA-L). Preprint Version. Accepted January, 2022. The code and videos can be found at https://jhavl.github.io/holistic/

Journal ref IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 3122-3129, April 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2004.00880 2020-04-03 cs.RO 81%

CLASH WRIST -- A hardware to increase the capability of CLASH fruit gripper to use environment constraints exploration

Werner Friedl, Maximo A. Roa

专题命中 机器人操作 :robotics(abstract);manipulation(abstract);world model(abstract);robotic(abstract)

Comments IROS 2019, Factory of the Future

详情

展开后加载摘要…

URL PDF HTML 收藏
2003.07272 2020-04-02 cs.RO physics.flu-dyn physics.med-ph 81%

Motion Control Simulations for a Magnetically-Coupled Bacterium and Robotic Arm

Ahmet Fatih Tabak

专题命中 机器人操作 :robotic(title,abstract);分类 cs.RO;robotics(comments);manipulation(comments)

Comments International Conference on Manipulation, Automation and Robotics at Small Scales, 2020, Toronto, Canada (Submitted, Accepted, Corrected, to be submitted to MARSS2021)

详情

展开后加载摘要…

URL PDF HTML 收藏
1905.03502 2020-04-02 cs.RO 81%

An Omnidirectional Aerial Manipulation Platform for Contact-Based Inspection

Karen Bodie, Maximilian Brunner, Michael Pantic, Stefan Walser, Patrick Pfändler, Ueli Angst, Roland Siegwart, Juan Nieto

专题命中 机器人操作 :manipulation(title,abstract);robotics(comments,journal_ref);分类 cs.RO

Comments Accepted submission to Robotics: Science and Systems conference 2019. 9 pages, 12 figures

Journal ref Proceedings of Robotics: Science and Systems, 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
1808.00092 2019-01-14 cs.RO 81%

Multimodal Sensing and Interaction for a Robotic Hand Orthosis

Sangwoo Park, Cassie Meeker, Lynne M. Weber, Lauri Bishop, Joel Stein, Matei Ciocarlie

专题命中 机器人操作 :robotic(title,abstract);robotics(comments,journal_ref);分类 cs.RO

Comments 8 pages. 9 Figures. IEEE Robotics and Automation Letters. Preprint version. Accepted Dec, 2018

Journal ref IEEE Robotics and Automation Letters, Vol. 4, No. 2, pp. 315 - 322, April 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
1501.05611 2015-02-27 cs.RO 81%

Learning Contact-Rich Manipulation Skills with Guided Policy Search

Sergey Levine, Nolan Wagener, Pieter Abbeel

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO;robotics(journal_ref)

Journal ref S. Levine, N. Wagener, P. Abbeel, "Learning Contact-Rich Manipulation Skills with Guided Policy Search," in International Conference on Robotics and Automation (ICRA), 2015

详情

展开后加载摘要…

URL PDF HTML 收藏
1304.6146 2013-04-24 cs.RO 81%

Manipulation in Clutter with Whole-Arm Tactile Sensing

Advait Jain, Marc D. Killpack, Aaron Edsinger, Charles C. Kemp

专题命中 机器人操作 :manipulation(title,abstract);robotics(comments,journal_ref);分类 cs.RO

Comments This is the first version of a paper that we submitted to the International Journal of Robotics Research on December 31, 2011 and uploaded to our website on January 16, 2012

Journal ref The International Journal of Robotics Research April 2013 vol. 32 no. 4 pg. 458-482

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.00071 2024-04-18 cs.RO cs.CG cs.CV cs.LG 81%

GIRA: Gaussian Mixture Models for Inference and Robot Autonomy

Kshitij Goel, Wennie Tabib

专题命中 机器人操作 :robotics(abstract,comments);manipulation(abstract);robotic(abstract);分类 cs.RO、cs.CV、cs.LG

Comments 2024 IEEE International Conference on Robotics and Automation (ICRA)

详情

展开后加载摘要…

URL PDF HTML 收藏
1903.08693 2021-11-24 cs.RO cs.AI cs.LG 81%

Using Local Experiences for Global Motion Planning

Constantinos Chamzas, Anshumali Shrivastava, Lydia E. Kavraki

专题命中 机器人操作 :robotics(abstract,comments);manipulation(abstract);navigation(abstract);分类 cs.RO、cs.AI、cs.LG

Comments 6 pages, to appear in International Conference on Robotics and Automation (ICRA), 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
1811.06964 2018-11-20 cs.RO cs.AI cs.CV 81%

Grasp2Vec: Learning Object Representations from Self-Supervised Grasping

Eric Jang, Coline Devin, Vincent Vanhoucke, Sergey Levine

专题命中 机器人操作 :robot learning(abstract,journal_ref);manipulation(abstract);robotic(abstract);分类 cs.RO、cs.AI、cs.CV

Comments CoRL 2018. Eric Jang and Coline Devin contributed equally to this work

Journal ref Proceedings of The 2nd Conference on Robot Learning, in PMLR 87:99-112 (2018)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.25960 2026-08-21 cs.CR cs.AI cs.RO 版本更新 81%

WaveVerif: Acoustic Side-Channel based Verification of Robotic Workflows

WaveVerif:基于声学侧信道的机器人工作流验证

Zeynep Yasemin Erdogan, Shishir Nagaraja, Chuadhry Mujeeb Ahmed, Ryan Shah

机构 * Newcastle University(新castle大学)

专题命中 机器人操作 :robotic(title,abstract);分类 cs.RO、cs.AI

AI总结 该研究提出WaveVerif框架,利用声学侧信道分析开发机器学习验证系统,可实时低成本无源验证机器人工作流,准确率超80%且无需硬件修改。

Comments 11 pages, 3 figures, Corresponding Author: Zeynep Yasemin Erdogan (z.y.erdogan2@newcastle.ac.uk)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.16806 2026-08-20 cs.RO cs.AI 版本更新 81%

Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents

当状态成为攻击面:大语言模型驱动的具身智能体中的状态语义注入

Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu, Juan Wang, Jinlin Fan, Bowen Xiao, Chi Guo, Keyan Guo, Hongxin Hu

机构 * Wuhan University(武汉大学) University at Buffalo(布法罗大学)

专题命中 机器人操作 :embodied agent(title,abstract);分类 cs.RO、cs.AI

AI总结 该文聚焦LLM驱动的具身智能体,梳理其技术演进与现有模型,指出其需结合多类信息完成任务落地后执行,为后续状态语义注入攻击研究奠定基础。

Comments submitted to USENIX Security 2027

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.17129 2026-08-19 cs.CV cs.RO 新提交 81%

PROBE: Manipulation-Grounded Visual Question Answering with VLM Agents

PROBE:基于操作的视觉问答(使用VLM智能体)

Vineet Bhat, Siyi Chen, Alex Zook, Xuning Yang, Stan Birchfield, Valts Blukis, Jonathan Tremblay

机构 * NVIDIA(英伟达)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.CV

AI总结 针对现实杂乱环境中需操作遮挡物体的视觉问答问题,提出PROBE框架,含模拟器、基准测试集及微调方案,提升VLM智能体性能并验证模拟到现实的迁移。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.29662 2026-08-19 cs.CV cs.RO 版本更新 81%

SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation

SAFE-Pruner: 语义注意力引导的未来感知令牌剪枝用于高效视觉-语言-动作操控

Shilin Ma, Chubin Zhang, Changyuan Wang, Yuji Wang, Yue Wu, Zixuan Wang, Jingqi Tian, Zheng Zhu, Yansong Tang

机构 * Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院,清华大学)

专题命中 机器人操作 :manipulation(title);robotic(abstract);分类 cs.RO、cs.CV

AI总结 针对视觉-语言-动作模型推理加速中现有剪枝方法忽略深层视觉信息的问题,提出SAFE-Pruner框架,通过引入未来层注意力线索和语义注意力一致性实现前瞻性令牌剪枝,在仿真和真实实验中取得最高1.89倍加速且成功率下降小于1.7%。

Comments Accepted to ECCV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05513 2026-08-18 cs.RO cs.AI 版本更新 81%

DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter

DECO:解耦多模态扩散变压器用于配备插件触觉适配器的双臂灵巧操作

Xukun Li, Yu Sun, Lei Zhang, Bosheng Huang, Yibo Peng, Yuan Meng, Haojun Jiang, Shaoxuan Xie, Guocai Yao, Alois Knoll, Zhenshan Bing, Xinlong Wang, Zhenguo Sun

机构 * Beijing Academy of Artificial Intelligence, Beijing, China(北京人工智能研究院) School of Computation, Information and Technology, Technical University of Munich, Garching, Germany(慕尼黑技术大学计算与信息学院) Department of Shenyang Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing, China(中国科学院沈阳计算技术研究所部门) State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China(新型软件技术国家重点实验室) Department of Computer Science and Technology, Tsinghua University, Beijing, China(清华大学计算机科学与技术系)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.AI

AI总结 DECO通过解耦多模态输入和触觉适配器,实现了双臂灵巧操作的高效整合与高成功率

Comments 25 pages, 8 figures. Project Page: https://baai-humanoid.github.io/DECO-webpage/

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.14028 2026-08-17 cs.RO cs.AI 新提交 81%

AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning

AdvDex:通过关节对齐动作与对抗学习从人类演示中学习灵巧操作

Zhiyue Zhao, Jingyi Wu, Hairuo Liu, Mingyu Liu, Liyang Li, Hengdi Zhang, Tong He, Zhengxue Cheng

机构 * Zhejiang University(浙江大学) Shanghai Innovation Institute(上海创新研究院) Fudan University(复旦大学) Shanghai Jiao Tong University(上海交通大学) Paxini Tech(帕西尼科技)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.AI

AI总结 AdvDex是一种统一视觉-语言-动作框架,通过OmniShare数据集、JAAS动作空间与领域对抗学习,实现从人类和机器人演示中学习灵巧操作,提升跨实体泛化与技能迁移能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.10756 2026-08-12 cs.RO cs.CV 新提交 81%

Embodied Multimodal Grounding for Open-Vocabulary Mobile Manipulation via Semantic 3D Gaussian Splatting

基于语义三维高斯溅射的开放词汇移动操作具身多模态定位

Huosen Ou, Dongni Song, Yuncong Wang, Tao Zhou, Yiding Ji

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) Midea Group(美的集团) The Hong Kong University of Science and Technology(香港科技大学)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.CV

AI总结 本文针对家庭场景开放词汇移动操作的目标定位问题,提出整合Semantic-3DGS的具身多模态框架,经50次真实机器人试验,在长 horizon、杂乱场景等任务中优于PointVLA等基线方法,提升了操作鲁棒性。

Comments 9 pages, 11 figures. Accepted to ACM Multimedia 2026 (MM '26)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.08009 2026-08-11 cs.CV cs.AI 新提交 81%

Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation

基于证据的取证推理:检测与定位多模态媒体篡改

Yichun Yeh, Yiheng Li, Xiaobo Hu, Zhen Lei, Yang Yang

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.AI、cs.CV

AI总结 本文针对多模态媒体篡改检测与定位问题,提出基于证据的取证推理框架,结合锚定-验证推理链、可验证奖励系统与模态解耦优势路由机制,实现最优性能与可解释性的统一。

Comments accepted by ACM MM 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.05369 2026-08-07 cs.RO cs.CV 新提交 81%

World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation

世界到手腕:面向精细机器人操作的任务条件未来手腕建模

Yuhao Pan, Haosong Peng, Zhengshen Zhang, Zhengyang Yan, Yalun Dai, Fushuo Huo, Chujie Wang, Tianyu Qi, Xiucheng Wang, Nan Cheng, Wenchao Xu

机构 * The Hong Kong University of Science and Technology(香港科技大学) National University of Singapore(新加坡国立大学) Nanyang Technological University(南洋理工大学) Wuhan University(武汉大学) Sun Yat-sen University(中山大学) Xidian University(西安电子科技大学) Southeast University(东南大学)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.CV

AI总结 本研究提出W2-VLA模型,通过任务条件未来手腕建模结合W2-CoT辅助监督,在LIBERO等数据集及真实任务中提升了机器人精细接触敏感操作能力,动作生成速率超80Hz。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24572 2026-08-07 cs.CV cs.RO 81%

SCOPE: Semantic Conditioning for Sim2Real Category-Level Object Pose Estimation in Robotics

Peter Hönig, Stefan Thalhammer, Jean-Baptiste Weibel, Matthias Hirschmanner, Markus Vincze

机构 * Vision for Robotics Laboratory, Automation and Control Institute, TU Wien(机器人视觉实验室,自动化与控制研究所,维也纳技术大学)

专题命中 机器人操作 :robotics(title);manipulation(abstract);分类 cs.RO、cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.15560 2026-08-06 cs.CR cs.AI cs.LG 交叉投稿 81%

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models

时序上下文感知:一种针对大型语言模型多轮操纵攻击的防御框架

Prashant Kulkarni, Assaf Namer

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.AI、cs.LG

AI总结 针对LLMs易受多轮操纵攻击的问题,本文提出TCA框架,通过分析语义漂移等实现防御,初步评估显示其能识别传统方法遗漏的微妙操纵模式,为对话式AI系统提供安全保障。

Comments 6 pages, 2 figures, IEEE CAI

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00568 2026-08-04 cs.LG cs.AI 新提交 81%

Fairness Auditing: Lower Bounds on Company Manipulation

公平性审计:公司操纵的下界

Rachit Verma, Padala Manisha, Sujit Gujar

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.AI、cs.LG

AI总结 该研究将公平性审计建模为公司与审计员的极小极大优化,推导了两种审计机制下审计后人口统计 parity 偏差的下界,实证显示增加审计资源无法消除审计后操纵。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.18557 2026-08-04 cs.CV cs.GR cs.RO 版本更新 81%

SynAgent: Generalizable Cooperative Humanoid Manipulation via Solo-to-Cooperative Agent Synergy

SynAgent:通过独狼到协作代理协同实现通用化的人形机器人操作

Wei Yao, Haohan Ma, Hongwen Zhang, Liangjun Xing, Zhile Yang, Yuanjun Guo, Yunlian Sun, Yebin Liu

机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院) Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院) School of Artificial Intelligence, Beijing Normal University(北京师范大学人工智能学院) Department of Automation, Tsinghua University(清华大学自动化系) College of Artificial Intelligence, Nanjing Forestry University(南京林业大学人工智能学院)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.CV

AI总结 本文提出SynAgent框架,通过独狼到协作代理协同转移单agent人-物体交互技能,实现可扩展且物理合理的协作操作,实验显示其在协作模仿和轨迹条件控制方面优于现有基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.28993 2026-08-03 cs.RO cs.CV 新提交 81%

ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts

ST-WAM:面向视觉分布偏移下鲁棒操作的语义-时间世界动作模型

Mingxin Wang, Bin Hu, Bin Qian, Kaitao Jiang, Haoning Wu, Feng Yan, Bowen Jing, Ruiyang Hao, Enyi Wang, Kangning Niu, Yandan Yang, Mu Xu, Yan Wang, Houde Liu, Tianlun Li

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.CV

AI总结 该研究针对视觉分布偏移下机器人操作的鲁棒性问题,提出ST-WAM模型,采用DINOv3等技术,在多个基准测试中取得优异性能,大幅提升了偏移场景下的零样本操作表现。

Comments 9 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.28198 2026-07-31 cs.RO cs.CV 新提交 81%

UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis

UniCross:统一跨技能灵巧操作合成

Hui Zhang, Julian Ferchow, Jie Song, Mirko Meboldt

机构 * ETH Zürich(苏黎世联邦理工学院) inspire AG(inspire AG公司) HKUST (Guangzhou)(香港科技大学(广州))

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.CV

AI总结 本研究提出UniCross框架,将抓取、重定位等四种灵巧操作技能统一建模,提炼出跨技能策略,可泛化到新物体、抗干扰,还能在不同手型间迁移,实现长时程操作。

Comments Project page: https://zdchan.github.io/UniCross/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.11891 2026-07-31 cs.RO cs.LG 版本更新 81%

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

评论家架构的重要性:双评论家与统一评论家在人形机器人移动操作中的对比

Mehmet Turan Yardımcı

机构 * Department of Computer Engineering(计算机工程系) Çukurova University(丘布亚大学)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.LG

AI总结 针对人形机器人多目标强化学习,对比统一评论家与双评论家架构,实验表明双评论家策略在到达速度、吞吐量和成功率上显著优于统一评论家,且架构选择比奖励工程影响更大。

Comments Accepted at the ICRA 2026 Workshop on Reinforcement Learning for Imitation Learning (RL4IL), Vienna. 5 pages, 2 figures. v2: corrects the unified-critic run's curriculum level (10 of 40) and per-run environment counts, adds a Confounding Factors section, and softens the causal framing; measurements unchanged. https://mturan33.github.io/critic-architecture-matters/

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.13349 2026-07-31 cs.CV cs.AI 版本更新 81%

ID-Guard: A Universal Framework for Combating Facial Manipulation via Breaking Identification

ID-Guard:一种通过破坏身份特征来对抗面部操纵的通用框架

Zuomin Qu, Wei Lu, Xiangyang Luo, Qian Wang, Xiaochun Cao

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.AI、cs.CV

AI总结 本研究针对面部操纵滥用的问题,提出ID-Guard通用框架,通过身份破坏模块生成跨模型可迁移扰动,可防御多种操纵模型并集成到其他任务中。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.12109 2026-07-29 cs.RO cs.AI 版本更新 81%

InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation

弥合形态差距:通过意图条件微调使VLA模型适应灵巧操作

Chuanke Pang, Junyi Huang, Zhijun Zhao, Yaobing Wang, Kun Xu, Xilun Ding

机构 * Beihang University(北京航空航天大学) China Academy of Space Technology(中国空间技术研究院)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.AI

AI总结 提出InDex框架,通过将预训练的1-DoF平行抓取输出重用作宏观虚拟抓取意图代理,结合两阶段解耦学习架构,实现VLA模型从低自由度夹爪到高自由度灵巧手的适应,有效缓解灾难性遗忘和动作流形坍缩。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.20399 2026-07-23 cs.RO cs.HC cs.LG 新提交 81%

Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning

利用虚拟现实和强化学习实现微型仿人机器人的远程定位操作

Nicolas Kosanovic, Jordan Dowdy, Jean Chagas Vaz

机构 * University of Louisville(路易斯维尔大学)

专题命中 机器人操作 :manipulation(title,abstract);分类 cs.RO、cs.LG

AI总结 研究针对微型仿人机器人缺乏类似全尺寸机器人控制堆栈的问题,利用虚拟现实和强化学习开发了控制堆栈,经实验验证能实现一定速度行走及远程定位操作,展现了微型仿人机器人远程定位操作的潜力。

Comments 8 pages, 6 figures. Accepted manuscript. Published in the 2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids), pp. 1233-1240

Journal ref 2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids), pp. 1233-1240 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏