arXivDaily arXiv每日学术速递 周一至周五更新

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 8666 信号源:cs.RO, cs.AI, cs.CV, cs.LG

1. 机器人数据与评测 8666 篇

1808.07712 2018-08-24 cs.CV cs.AI cs.RO 67%

Predicting Action Tubes

Gurkirt Singh, Suman Saha, Fabio Cuzzolin

专题命中 机器人数据与评测 :robotics(abstract);分类 cs.RO、cs.AI、cs.CV

Comments ECCV workshop; Anticipating Human Behaviour 2018; 16 page 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
1711.01391 2017-11-08 cs.AI cs.LG cs.RO 67%

Guiding the search in continuous state-action spaces by learning an action sampling distribution from off-target samples

Beomjoon Kim, Leslie Pack Kaelbling, Tomas Lozano-Perez

专题命中 机器人数据与评测 :robotics(abstract);分类 cs.RO、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
1708.01648 2017-08-08 cs.CV cs.AI cs.LG stat.ML 67%

3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks

Chuhang Zou, Ersin Yumer, Jimei Yang, Duygu Ceylan, Derek Hoiem

专题命中 机器人数据与评测 :robotics(abstract);分类 cs.AI、cs.CV、cs.LG

Comments ICCV 2017

详情

展开后加载摘要…

URL PDF HTML 收藏
1704.05588 2017-04-28 cs.RO cs.CV cs.LG 67%

Learning to Fly by Crashing

Dhiraj Gandhi, Lerrel Pinto, Abhinav Gupta

专题命中 机器人数据与评测 :navigation(abstract);分类 cs.RO、cs.CV、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
1603.03541 2016-03-14 cs.CV cs.LG cs.RO 67%

Watch-n-Patch: Unsupervised Learning of Actions and Relations

Chenxia Wu, Jiemi Zhang, Ozan Sener, Bart Selman, Silvio Savarese, Ashutosh Saxena

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.CV、cs.LG

Comments arXiv admin note: text overlap with arXiv:1512.04208

详情

展开后加载摘要…

URL PDF HTML 收藏
1507.06821 2015-08-19 cs.CV cs.LG cs.NE cs.RO 67%

Multimodal Deep Learning for Robust RGB-D Object Recognition

Andreas Eitel, Jost Tobias Springenberg, Luciano Spinello, Martin Riedmiller, Wolfram Burgard

专题命中 机器人数据与评测 :robotics(abstract);分类 cs.RO、cs.CV、cs.LG

Comments Final version submitted to IROS'2015, results unchanged, reformulation of some text passages in abstract and introduction

详情

展开后加载摘要…

URL PDF HTML 收藏
1407.0698 2014-07-04 cs.NE cs.MA 67%

Continuous On-line Evolution of Agent Behaviours with Cartesian Genetic Programming

Davide Nunes, Luis Antunes

专题命中 机器人数据与评测 :robotics(abstract);embodied agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.29599 2026-08-17 cs.RO cs.CV 版本更新 66%

How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments

如何缓解越野环境语义分割中的分布偏移

Ji-Hoon Hwang, Daeyoung Kim, Hyung-Suk Yoon, Dong-Wook Kim, Seung-Woo Seo

机构 * Department of Electrical and Communication Engineering, Seoul National University(电子与通信工程系,首尔国立大学)

专题命中 机器人数据与评测 :navigation(abstract);分类 cs.RO、cs.CV;robotics(comments)

AI总结 提出ST-Seg框架,通过风格扩展和纹理正则化缓解越野场景中源-目标域差异和传感器退化导致的分布偏移,提升语义分割鲁棒性。

Comments 8 pages, 6 figures. Accepted to IEEE Robotics and Automation Letters (RA-L)

Journal ref IEEE Robotics and Automation Letters, vol. 10, issue. 5, pp. 4500-4507, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.21666 2026-08-04 cs.RO cs.CV 版本更新 66%

Uncertainty Quantification for Visual Object Pose Estimation: S-Lemma Ellipsoidal Bounds

视觉目标姿态估计的不确定性量化

Lorenzo Shaikewitz, Charis Georgiou, Luca Carlone

机构 * Massachusetts Institute of Technology(麻省理工学院)

专题命中 机器人数据与评测 :robotics(abstract,comments);分类 cs.RO、cs.CV

AI总结 SLUE通过凸优化方法为视觉目标姿态估计提供高概率的椭球不确定性界,有效缩小平移界限并保持方向精度。

Comments 18 pages, 9 figures. Code available: https://github.com/MIT-SPARK/PoseUncertaintySets. Published in IEEE Transactions on Robotics

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18314 2026-07-29 cs.CV cs.GR cs.RO 版本更新 66%

Diff2DGS: Reliable Reconstruction of Occluded Surgical Scenes via 2D Gaussian Splatting

Diff2DGS: 通过2D高斯点散布实现遮挡手术场景的可靠重建

Tianyi Song, Danail Stoyanov, Evangelos Mazomenos, Francisco Vasconcelos

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.CV;robotics(comments)

AI总结 Diff2DGS通过两阶段框架提升遮挡手术场景的3D重建精度,结合扩散模型和可学习变形模型,实现更准确的几何和外观重建。

Comments This work has been accpeted by the IEEE Robotics and Automation Letters(RA-L)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.17699 2026-07-21 cs.RO cs.CV 新提交 66%

SLAM in Low-Light Environments: Project Report

低光照环境下的同步定位与地图构建:项目报告

Oleh Basystyi, Anna Stasyshyn, Oleksandr Kosovan, Yaroslav Prytula

机构 * Applied Sciences Faculty, Ukrainian Catholic University(乌克兰天主教大学应用科学学院)

专题命中 机器人数据与评测 :robotics(abstract);分类 cs.RO、cs.CV;navigation(comments)

AI总结 研究低光照环境下RGB相机的SLAM问题,对六种不同范式的系统在五个序列上进行基准测试,发现仅RGB的SLAM需惯性融合和全局优化才能稳定跟踪,为后续改进提供方向。

Comments Conducted as part of the certification program "Off-Road Visual Navigation: Development and Evaluation of Systems in Challenging Environments'' at the Faculty of Applied Sciences, Ukrainian Catholic University, in collaboration with the UCU UGV Club

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.16862 2026-07-21 cs.CV cs.RO 新提交 66%

InLiER: Learning-Free Heterogeneous LiDAR Place Recognition via Intermediate Mixed-Radix Structural Keypoint Tokenization

InLiER:通过中间混合基数结构关键点令牌化实现无学习的异构激光雷达地点识别

Nikolaos Stathoulopoulos, George Nikolakopoulos

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.CV;robotics(comments)

AI总结 研究针对机器人平台结合多种激光雷达致现有描述符性能下降的问题,提出无学习管道InLiER,通过混合基数令牌ID编码关键点信息,经三个检索阶段处理,在相关数据集和实验中表现出色,优于基于学习的基线。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L). 8 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.05669 2026-07-08 cs.RO cs.LG 新提交 66%

Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba

使用证据曼巴进行本体感知车辆定位的不确定性感知速度校正

Abinav Kalyanasundaram, Karthikeyan Chandra Sekaran, Wolfgang Utschick, Michael Botsch

机构 * AImotion Bavaria, Technische Hochschule Ingolstadt(巴伐利亚AImotion公司,英戈尔施塔特技术应用大学) Technische Universität München(慕尼黑工业大学)

专题命中 机器人数据与评测 :navigation(abstract,comments);分类 cs.RO、cs.LG

AI总结 针对智能车辆在GNSS信号缺失时定位难题,提出EVC-Mamba架构,利用车载传感器数据转化为虚拟速度传感器校正IMU漂移,经曼巴模型捕捉动态、证据深度学习量化不确定性,实现高精度定位且支持实时车载部署。

Comments Accepted at the 2026 International Conference on Indoor Positioning and Indoor Navigation (IPIN 2026), Rome, Italy. 6 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.03553 2026-07-07 cs.CV cs.RO 新提交 66%

iVISION-2DCD: A Long-Term Change Detection Dataset for Large-Scale Outdoor Construction Monitoring

iVISION-2DCD:用于大规模户外建筑监测的长期变化检测数据集

Dayou Mao, Yuchen Lin, Ashkan Ebadi, John Zelek, Alexander Wong, Yuhao Chen

机构 * National Research Council Canada(加拿大国家研究委员会) Vision and Image Processing Research Group, Systems Design Engineering, University of Waterloo(滑铁卢大学系统设计工程系视觉与图像处理研究小组)

专题命中 机器人数据与评测 :robotics(abstract,comments);分类 cs.RO、cs.CV

AI总结 研究从检测建筑工地变化监测施工进度,针对跨视角变化检测算法缺开源基准数据集问题,用LiDAR点云生成iVISION-2DCD数据集,提出合成数据生成等方法,为相关领域带来新挑战。

Comments 11 pages, 7 figures, 1 table. Accepted for publication at the 2026 IEEE International Conference on Robotics and Automation (ICRA 2026). Project page: https://danielmao2019.github.io/iVISION-2DCD-dataset.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.06355 2026-06-30 cs.RO cs.AI 66%

UNCOM: Zero-shot Context-Aware Command Understanding for Tabletop Scenarios

UNCOM:面向桌面上场景的零样本上下文感知命令理解

Antonio Galiza Cerdeira Gonzalez, Paweł Gajewski, Bipin Indurkhya

机构 * Jagiellonian University(杰克利昂大学) AGH University of Krakow(克拉科夫AGH大学)

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.AI;robotics(journal_ref)

AI总结 UNCOM提出了一种新的混合框架,通过整合语音、手势和场景上下文信息,实现桌面上场景中自然人类命令的解析,无需预定义对象模型或特定任务训练数据,展示了系统的鲁棒性。

Journal ref Proc. IEEE International Conference on Advanced Robotics and its Social Impacts (ARSO), 2026, pp. 163-168

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.14766 2026-06-16 cs.CV cs.AI cs.MA 新提交 66%

XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems

XMedFusion:面向自主医疗系统的知识引导多模态感知与推理框架

Hamza Riaz, Arham Haroon, Maha Baig, Muhammad Dawood Rizwan, Muhammad Naseer Bajwa, Muhammad Moazam Fraz

机构 * National University of Sciences and Technology (NUST)(巴基斯坦国立科技大学) University of Oxford(牛津大学)

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.AI、cs.CV;robotics(comments)

AI总结 提出XMedFusion模块化AI框架,通过视觉感知、知识图谱构建和检索引导生成等智能体协同,增强放射学报告生成的视觉基础与临床发现捕捉能力,在公共数据集上显著优于基线模型。

Comments Accepted at the 2026 International Conference on Robotics and Automation in Industry (ICRAI)

Journal ref 2026 International Conference on Robotics and Automation in Industry (ICRAI), pp. 1-6, May 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
1601.04037 2026-06-04 cs.RO cs.AI cs.SY eess.SY math.DS math.OC 66%

Funnel Libraries for Real-Time Robust Feedback Motion Planning

用于实时鲁棒反馈运动规划的 funnel 库

Anirudha Majumdar, Russ Tedrake

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.AI;robotics(comments)

AI总结 本文提出利用预计算的 funnel 库实现实时鲁棒反馈运动规划,通过凸优化计算 funnel 并在运行时安全组合运动计划,验证了在复杂环境中高动态机器人系统鲁棒性和安全性。

Comments International Journal of Robotics Research (To Appear)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.02463 2026-06-02 cs.CV cs.AI 66%

MASER: Modality-Adaptive Specialist Routing for Embodied 3D Spatial Intelligence

MASER: 面向具身3D空间智能的模态自适应专家路由

Hilton Raj, Vishnuram AV

机构 * Boston University(波士顿大学)

专题命中 机器人数据与评测 :embodied agent(abstract,comments);分类 cs.AI、cs.CV

AI总结 提出MASER框架,通过训练共享VLM骨干的五个模态适配器并学习基于问题选择最佳适配器的神经路由策略,解决具身代理在3D环境中多模态推理时忽略问题语义的问题。

Comments Accepted to CVPR 2026 Foundation Models Meet Embodied Agents Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.04811 2026-04-07 cs.RO cs.CV cs.HC 66%

AnyUser: Translating Sketched User Intent into Domestic Robots

AnyUser: 将草图用户意图翻译成家用机器人

Songyuan Yang, Huibin Tan, Kailun Yang, Wenjing Yang, Shaowu Yang

机构 * College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院) National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University(湖南大学国家机器人视觉感知与控制技术工程研究中心)

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.CV;robotics(comments)

AI总结 AnyUser通过相机图像上的自由形式草图(可选语言)实现直观的家庭任务指令,利用多模态输入生成无需先验地图或模型的可执行机器人动作,通过大量评估验证其在不同模拟家庭场景中的高准确性和真实环境中的可靠性。

Comments Accepted to IEEE Transactions on Robotics (T-RO)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03736 2026-04-01 cs.RO cs.LG cs.SY eess.SY 66%

Crossing the Sim2Real Gap Between Simulation and Ground Testing to Space Deployment of Autonomous Free-flyer Control

跨越仿真与地面测试到空间部署的自主自由飞行器控制的模拟与现实差距

Kenneth Stewart, Samantha Chapin, Roxana Leontie, Carl Glen Henshaw

机构 * U.S. Naval Research Laboratory Naval Center for Space Technology(美国海军研究实验室海军空间技术中心)

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.LG;robotics(journal_ref)

AI总结 本文通过NASA Astrobee在国际空间站的实测,展示了基于强化学习的自主控制方法,验证了仿真到现实的训练管道,为未来在轨服务、组装和制造等任务提供可行性证明。

Comments published at iSpaRo 2025

Journal ref 2025 International Conference on Space Robotics (iSpaRo)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21119 2026-02-25 cs.RO cs.AI 66%

Cooperative-Competitive Team Play of Real-World Craft Robots

现实世界工艺机器人的协作-竞争团队合作

Rui Zhao, Xihui Li, Yizheng Zhang, Yuzhen Liu, Zhong Zhang, Yufeng Zhang, Cheng Zhou, Zhengyou Zhang, Lei Han

机构 * Tencent Robotics X Laboratory(腾讯机器人实验室) Tsinghua University(清华大学)

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.AI;robotics(comments)

AI总结 本文提出了一种针对现实世界工艺机器人协作与竞争任务的强化学习方法,通过引入OODSI技术提升仿真到现实的迁移性能。

Comments Accepted by 2026 IEEE International Conference on Robotics and Automation (ICRA 2026), Vienna, Austria

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.13440 2026-02-17 cs.CV cs.RO 66%

Learning on the Fly: Replay-Based Continual Object Perception for Indoor Drones

实时学习:基于回放的连续物体感知用于室内无人机

Sebastian-Ion Nae, Mihai-Eugen Barbu, Sebastian Mocanu, Marius Leordeanu

机构 * National University of Science and Technology Politehnica Bucharest, Romania(罗马尼亚布加勒斯特多项技术大学) Institute of Mathematics ``Simion Stoilow'' of the Romanian Academy, Romania(罗马尼亚科学院模拟昂斯数学研究所) NORCE Norwegian Research Center, Norway(挪威NORCE研究中心)

专题命中 机器人数据与评测 :robotics(abstract,comments);分类 cs.RO、cs.CV

AI总结 本研究提出基于回放的连续学习方法,通过室内无人机视频数据集评估,证明在有限内存预算下FAR方法能有效提升物体感知性能。

Comments Accepted at European Robotics Forum (ERF) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00935 2025-12-16 cs.RO cs.LG 66%

Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis

通过潜在空间可达性分析超越碰撞回避的安全性泛化

Kensuke Nakamura, Lasse Peters, Andrea Bajcsy

机构 * Carnegie Mellon University(卡内基梅隆大学) Delft University of Technology(代尔夫特理工大学)

专题命中 机器人数据与评测 :world model(abstract);分类 cs.RO、cs.LG;robotics(journal_ref)

AI总结 本文提出潜在安全过滤器,通过潜在空间可达性分析,使机器人能自动计算安全动作,防止难以手动编写但可通过高维观测识别的故障。

Comments 9 figures, 7 tables, RSS 2025

Journal ref Proceedings of Robotics: Science and Systems, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13969 2025-11-14 cs.RO cs.AI 66%

Hypothesis on the Functional Advantages of the Selection-Broadcast Cycle Structure: Global Workspace Theory and Dealing with a Real-Time World

Junya Nakanishi, Jun Baba, Yuichiro Yoshikawa, Hiroko Kamide, Hiroshi Ishiguro

机构 * Graduate School of Engineering Science, The University of Osaka(大阪大学工学研究科) AI Lab, CyberAgent Inc.(CyberAgent公司) Faculty/School of Law, Kyoto University(京都大学法学院)

专题命中 机器人数据与评测 :robotics(abstract,journal_ref);分类 cs.RO、cs.AI

Journal ref Frontiers in Robotics and AI, 2025, Vol. 12, Article 1607190

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.23875 2025-11-03 cs.RO cs.AI cs.MA 66%

GenSwarm: Scalable Multi-Robot Code-Policy Generation and Deployment via Language Models

Wenkang Ji, Huaben Chen, Mingyang Chen, Guobin Zhu, Lufeng Xu, Roderich Groß, Rui Zhou, Ming Cao, Shiyu Zhao

机构 * Department of Artificial Intelligence, Westlake University(人工智能系,西湖大学) School of Automation Science and Electrical Engineering, Beihang University(自动化科学与电气工程学院,北航) Institute of Engineering and Technology, University of Groningen(工程与技术学院,格罗宁根大学) Department of Computer Science, Technical University of Darmstadt(计算机科学系,德累斯顿技术大学) School of Electrical and Electronic Engineering, The University of Sheffield(电子与电气工程学院,谢菲尔德大学)

专题命中 机器人数据与评测 :robotics(abstract,comments);分类 cs.RO、cs.AI

Comments This article has been accepted for publication in npj Robotics

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22672 2025-10-29 cs.CV cs.CL cs.RO 66%

Look and Tell: A Dataset for Multimodal Grounding Across Egocentric and Exocentric Views

Anna Deichler, Jonas Beskow

机构 * KTH Royal Institute of Technology(皇家理工学院)

专题命中 机器人数据与评测 :embodied agent(abstract);分类 cs.RO、cs.CV;embodied AI(comments)

Comments 10 pages, 6 figures, 2 tables. Accepted to the NeurIPS 2025 Workshop on SPACE in Vision, Language, and Embodied AI (SpaVLE). Dataset: https://huggingface.co/datasets/annadeichler/KTH-ARIA-referential

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.16538 2025-10-21 cs.CV cs.RO 66%

Leveraging Vision-Language Models for Open-Vocabulary Instance Segmentation and Tracking

Bastian Pätzold, Jan Nogga, Sven Behnke

机构 * Autonomous Intelligent Systems, University of Bonn(博恩大学自主智能系统中心) Lamarr Institute for Machine Learning and AI(拉马尔人工智能与机器学习研究所) Center for Robotics, University of Bonn(博恩大学机器人中心)

专题命中 机器人数据与评测 :robotics(abstract,comments);分类 cs.RO、cs.CV

Comments IEEE Robotics and Automation Letters (RA-L), November 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09912 2025-10-14 cs.CV cs.AI 66%

SpectralCA: Bi-Directional Cross-Attention for Next-Generation UAV Hyperspectral Vision

D. V. Brovko

专题命中 机器人数据与评测 :navigation(abstract,comments);分类 cs.AI、cs.CV

Comments The work consists of three chapters, includes 12 figures, 4 tables, 31 references, and 1 appendix. A version of this work has been accepted for presentation at the 2025 IEEE 8th International Conference on Methods and Systems of Navigation and Motion Control

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02587 2025-10-14 cs.CV cs.RO 66%

BEVCALIB: LiDAR-Camera Calibration via Geometry-Guided Bird's-Eye View Representations

Weiduo Yuan, Jerry Li, Justin Yue, Divyank Shah, Konstantinos Karydis, Hang Qiu

机构 * University of Southern California(南加州大学) University of California, Riverside(加州大学河滨分校)

专题命中 机器人数据与评测 :robotic(abstract);分类 cs.RO、cs.CV;robot learning(journal_ref)

Journal ref 9th Conference on Robot Learning (CoRL 2025), Seoul, Korea

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.01793 2025-10-06 cs.LG cs.AI 66%

STORI: A Benchmark and Taxonomy for Stochastic Environments

Aryan Amit Barsainyan, Jing Yu Lim, Dianbo Liu

专题命中 机器人数据与评测 :world model(abstract,comments);分类 cs.AI、cs.LG

Comments v2. New mathematical formulation and renamed notation; added additional experiments and a detailed analytical case study on error behaviors in world models under different stochasticity types; link to code repository for reproducibility: https://github.com/ARY2260/stori

详情

展开后加载摘要…

URL PDF HTML 收藏