机器人 / 具身智能 - arXivDaily 专题

1707.00318 2017-11-03 cs.RO 80%

Sampling-based Planning of In-Hand Manipulation with External Pushes

Nikhil Chavan-Dafle, Alberto Rodriguez

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

Comments International Symposium on Robotics Research 2017, Puerto Varas, Chile

1702.07252 2017-11-01 cs.RO 80%

Experimental Validation of Contact Dynamics for In-Hand Manipulation

Roman Kolbert, Nikhil Chavan-Dafle, Alberto Rodriguez

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

Comments International Symposium on Experimental Robotics, ISER 2016, Tokyo, Japan

1703.10261 2017-04-05 cs.RO 80%

Planning and Resilient Execution of Policies For Manipulation in Contact with Actuation Uncertainty

Calder Phillips-Grafflin, Dmitry Berenson

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

Comments This work was presented at the 12th International Workshop on the Algorithmic Foundations of Robotics (WAFR) in San Francisco in December 2016

1610.04871 2016-11-28 cs.RO 80%

Probabilistic Articulated Real-Time Tracking for Robot Manipulation

Cristina Garcia Cifuentes, Jan Issac, Manuel Wüthrich, Stefan Schaal, Jeannette Bohg

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

Comments 8 pages, 7 figures. Revision submitted to IEEE Robotics and Automation Letters (RA-L). Fixed wrong order of bars in boxplots; further argumentation

cs/0601054 2009-12-01 cs.RO 80%

Control of a Lightweight Flexible Robotic Arm Using Sliding Modes

Victor Etxebarria, Arantza Sanz, Ibone Lizarraga

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

Journal ref International Journal of Advanced Robotics Systems, Vol.2No2. (2005)

2607.02417 2026-07-03 cs.RO cs.CV cs.LG 新提交 80%

LIME: Learning Intent-aware Camera Motion from Egocentric Video

LIME: 从自我中心视频学习意图感知的相机运动

Boyang Sun, Jiajie Li, Yung-Hsu Yang, Chenyangguang Zhang, Tim Engelbracht, Sunghwan Hong, Cesar Cadena, Marc Pollefeys, Hermann Blum

机构 * ETH Zurich（苏黎世联邦理工学院）； Microsoft（微软）； University of Bonn（波恩大学）

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

AI总结提出LIME模型，从自我中心视频中挖掘多意图相机运动监督，结合自回归观察增益输出与连续流匹配位姿头，实现语言条件相机运动生成。

2606.30940 2026-07-01 cs.RO cs.AI cs.LG 新提交 80%

Motion Planning in Compressed Representation Spaces

压缩表示空间中的运动规划

Lukas Lao Beyer, Sertac Karaman

机构 * MIT LIDS（麻省理工学院信息与决策系统实验室）

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

AI总结提出一种生成式框架，通过高压缩率自编码器学习离散层级化潜在空间，并在其中直接搜索进行运动规划，兼顾灵活性与效率，无需任务特定训练。

Comments To appear in the Proceedings of the 43rd International Conference on Machine Learning

2606.12402 2026-06-11 cs.RO cs.AI cs.CV 新提交 80%

DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?

DIRECT: 在具身规划器中何时何地分配测试时计算？

Jadelynn Dao, Milan Ganai, Yasmina Abukhadra, Ajay Sridhar, Mozhgan Nasr Azadani, Katie Luo, Clark Barrett, Jiajun Wu, Chelsea Finn, Marco Pavone

机构 * Stanford University（斯坦福大学）； University of Waterloo（滑铁卢大学）； NVIDIA（英伟达）

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

AI总结提出DIRECT路由框架，根据多模态场景上下文按提示分配计算资源，优化成功-成本帕累托前沿，实验表明不同缩放轴带来不同能力增益，在物理机器人上以更低延迟匹配或超越更强模型。

2503.15481 2026-04-14 cs.RO cs.AI cs.LG 80%

Learning to Play Piano in the Real World

在现实世界中学习演奏钢琴

Yves-Simon Zeulner, Simon Crämer, Sandeep Selvaraj, Roberto Calandra

机构 * LASR Lab, TU Dresden（德累斯顿工业大学 LASR 实验室）

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

AI总结本文提出首个结合学习方法的现实世界钢琴演奏机器人系统，通过Sim2Real2Sim方法在现实世界中准确演奏多首钢琴曲，达到0.881的平均F1分数。

2604.07395 2026-04-10 cs.RO cs.AI cs.CV 80%

A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring

一种物理代理循环用于语言引导的抓取与执行状态监控

Wenze Wang, Mehdi Hosseinzadeh, Feras Dayoub

机构 * Australian Institute for Machine Learning (AIML), Adelaide University（澳大利亚阿德莱德大学澳大利亚机器学习研究所）

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

AI总结本文提出一种物理代理循环，通过事件接口和执行监控层提升语言引导抓取的鲁棒性和可解释性，验证了其在视觉模糊和执行失败场景中的有效性。

Comments Project page: https://wenzewwz123.github.io/Agentic-Loop/

2603.15888 2026-03-20 cs.AI cs.CV cs.RO 80%

AsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal Feedback

AsgardBench -- 评估基于视觉的交互式规划在最小反馈下的表现

Andrea Tupini, Lars Liden, Reuben Tan, Yu Wang, Jianfeng Gao

机构 * Microsoft（微软）

专题命中机器人操作：embodied AI(abstract)；manipulation(abstract)；navigation(abstract)；分类 cs.RO、cs.AI、cs.CV

AI总结 AsgardBench旨在评估基于视觉的高阶动作序列生成和交互式规划，重点在于执行过程中基于视觉观察而非导航或低级操作的计划适应。通过限制代理输入为图像、动作历史和轻量级成功/失败信号，该基准测试强调条件分支和计划修复。

Comments 19 figures, 6 tables, including appendix

2510.06754 2026-03-13 cs.RO cs.CV cs.LG 80%

UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene

UniFField: 一种通用的统一神经特征场，用于任何场景中的视觉、语义和空间不确定性

Christian Maurer, Snehal Jauhri, Sophie Lueth, Georgia Chalvatzaki

机构 * TU Darmstadt（图宾根大学）； Robotics Institute（机器人研究所）

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

AI总结 UniFField是一种通用的统一神经特征场，能够整合视觉、语义和几何特征，预测不确定性，适用于任何场景中的鲁棒决策。

Comments ICRA 2026 Project website: https://sites.google.com/view/uniffield

2407.03035 2026-02-10 cs.RO cs.AI cs.LG 80%

NLP Sampling: Combining MCMC and NLP Methods for Diverse Constrained Sampling

NLP采样：结合MCMC和NLP方法进行多样化的受限采样

Marc Toussaint, Cornelius V. Braun, Joaquim Ortiz-Haro

机构 * Learning & Intelligent Systems Lab, TU Berlin（柏林技术大学学习与智能系统实验室）； Machines in Motion Lab, New York University（纽约大学运动机器实验室）

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

AI总结本文提出NLP采样框架，结合MCMC和NLP方法，解决多样化的受限采样问题，并通过实验验证其有效性。

2511.07418 2025-11-11 cs.RO cs.AI cs.CV cs.DC cs.GR 80%

Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields

Zhao-Heng Yin, Pieter Abbeel

机构 * UC Berkeley EECS（伯克利大学电子工程与计算机科学系）

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

Comments Code: https://github.com/zhaohengyin/lightning-grasp

2412.14680 2024-12-30 cs.CV cs.AI cs.RO 80%

A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space

Yonghao He, Hu Su, Haiyong Yu, Cong Yang, Wei Sui, Cong Wang, Song Liu

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

2412.10410 2024-12-17 cs.AI cs.LG cs.RO 80%

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents

Shaofei Cai, Bowei Zhang, Zihao Wang, Haowei Lin, Xiaojian Ma, Anji Liu, Yitao Liang

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

2403.17124 2024-12-10 cs.RO cs.AI cs.CL cs.LG 80%

Grounding Language Plans in Demonstrations Through Counterfactual Perturbations

Yanwei Wang, Tsun-Hsuan Wang, Jiayuan Mao, Michael Hagenow, Julie Shah

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

Comments ICLR 2024 Spotlight

Journal ref In International Conference on Learning Representations (ICLR) (2024)

2311.12871 2024-05-10 cs.CV cs.AI cs.CL cs.LG 80%

An Embodied Generalist Agent in 3D World

Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, Siyuan Huang

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

Comments ICML 2024. The first four authors contribute equally. Project page: https://embodied-generalist.github.io

2312.01097 2023-12-05 cs.CV cs.LG cs.RO 80%

Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty

Cheng-Fu Yang, Haoyang Xu, Te-Lin Wu, Xiaofeng Gao, Kai-Wei Chang, Feng Gao

专题命中机器人操作：embodied AI(abstract)；manipulation(abstract)；navigation(abstract)；分类 cs.RO、cs.CV、cs.LG

2309.15110 2023-09-27 cs.CV cs.AI cs.RO 80%

Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow

Zhenyu Jiang, Hanwen Jiang, Yuke Zhu

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

Comments Project website: https://ut-austin-rpl.github.io/Doduo

2308.07775 2023-08-16 cs.RO cs.AI cs.LG cs.SY eess.SY 80%

Hierarchical generative modelling for autonomous robots

Kai Yuan, Noor Sajid, Karl Friston, Zhibin Li

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

2109.13751 2023-05-22 cs.CV cs.AI cs.LG cs.NE 80%

StereoSpike: Depth Learning with a Spiking Neural Network

Ulysse Rançon, Javier Cuadrado-Anibarro, Benoit R. Cottereau, Timothée Masquelier

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

2303.03378 2023-03-07 cs.LG cs.AI cs.RO 80%

PaLM-E: An Embodied Multimodal Language Model

Danny Driess, Fei Xia, Mehdi S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zeng, Igor Mordatch, Pete Florence

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

2203.00054 2022-12-07 cs.LG cs.AI cs.CL cs.RO 80%

LISA: Learning Interpretable Skill Abstractions from Language

Divyansh Garg, Skanda Vaidyanath, Kuno Kim, Jiaming Song, Stefano Ermon

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

Comments NeurIPS 2022. Website: https://div99.github.io/LISA/

2206.11733 2022-06-24 cs.LG cs.AI cs.RO 80%

Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision

Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Karteek Alahari

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

2007.13202 2020-11-10 cs.LG cs.AI cs.RO 80%

CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs

Rohan Chitnis, Tom Silver, Beomjoon Kim, Leslie Pack Kaelbling, Tomas Lozano-Perez

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

Comments CoRL 2020

2008.03787 2020-08-11 cs.RO cs.AI cs.LG 80%

Neural Manipulation Planning on Constraint Manifolds

Ahmed H. Qureshi, Jiangeng Dong, Austin Choe, Michael C. Yip

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

Comments This is the preprint version of the paper published at IEEE Robotics and Automation Letters 2020

Journal ref in IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6089-6096, Oct. 2020

1812.05905 2019-09-16 cs.LG cs.AI cs.RO stat.ML 80%

Soft Actor-Critic Algorithms and Applications

Tuomas Haarnoja, Aurick Zhou, Kristian Hartikainen, George Tucker, Sehoon Ha, Jie Tan, Vikash Kumar, Henry Zhu, Abhishek Gupta, Pieter Abbeel, Sergey Levine

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

Comments arXiv admin note: substantial text overlap with arXiv:1801.01290

1908.03343 2019-08-12 cs.LG cs.AI cs.RO 80%

Fully Convolutional Search Heuristic Learning for Rapid Path Planners

Yuka Ariki, Takuya Narihira

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

Comments 11 pages, 4 figures

1905.11358 2019-07-31 cs.CV cs.AI cs.LG 80%

Straight to Shapes++: Real-time Instance Segmentation Made More Accurate

Laurynas Miksys, Saumya Jetley, Michael Sapienza, Stuart Golodetz, Philip H. S. Torr

专题命中机器人操作：manipulation(abstract)；navigation(abstract)；robotic(abstract)；分类 cs.AI、cs.CV、cs.LG

Comments Technical report, 27 pages (12 main, 15 supplementary), 17 figures, 14 tables

1. 机器人操作 22146 篇

Sampling-based Planning of In-Hand Manipulation with External Pushes

Experimental Validation of Contact Dynamics for In-Hand Manipulation

Planning and Resilient Execution of Policies For Manipulation in Contact with Actuation Uncertainty

Probabilistic Articulated Real-Time Tracking for Robot Manipulation

Control of a Lightweight Flexible Robotic Arm Using Sliding Modes

LIME: Learning Intent-aware Camera Motion from Egocentric Video

Motion Planning in Compressed Representation Spaces

DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?

Learning to Play Piano in the Real World

A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring

AsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal Feedback

UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scene

NLP Sampling: Combining MCMC and NLP Methods for Diverse Constrained Sampling

Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields

A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space

GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents

Grounding Language Plans in Demonstrations Through Counterfactual Perturbations

An Embodied Generalist Agent in 3D World

Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty

Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow

Hierarchical generative modelling for autonomous robots

StereoSpike: Depth Learning with a Spiking Neural Network

PaLM-E: An Embodied Multimodal Language Model

LISA: Learning Interpretable Skill Abstractions from Language

Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision

CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs

Neural Manipulation Planning on Constraint Manifolds

Soft Actor-Critic Algorithms and Applications

Fully Convolutional Search Heuristic Learning for Rapid Path Planners

Straight to Shapes++: Real-time Instance Segmentation Made More Accurate