Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning
机构 * Stanford University（斯坦福大学） ； Swiss Re（瑞士再保险集团） ； NVIDIA Research（NVIDIA研究）
Comments Conference on Robot Learning (CoRL) 2025 (Oral)
期刊&会议
CoRL
Conference on Robot Learning · 会议 · Robotics
AnyPlace: Learning Generalized Object Placement for Robot Manipulation
机构 * University of Toronto（多伦多大学） ； Vector Institute（向量研究所） ； Shanghai Jiao Tong University（上海交通大学） ； Wilfrid Laurier University（威尔弗里德·劳里埃大学） ； Acceleration Consortium（加速联盟） ； Georgia Institute of Technology（佐治亚理工学院）
Comments Accepted at CoRL 2025
Generalist Robot Manipulation beyond Action Labeled Data
机构 * ETH Zurich, Switzerland（苏黎世联邦理工学院，瑞士）
Comments Accepted at Conference on Robot Learning 2025
EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
机构 * Georgia Institute of Technology（佐治亚理工学院）
Comments Accepted at 39th Conference on Neural Information Processing Systems (NeurIPS 2025) and Oral at Conference on Robot Learning (CoRL 2025)
From Space to Time: Enabling Adaptive Safety with Learned Value Functions via Disturbance Recasting
机构 * University of California San Diego（加州大学圣地亚哥分校）
Comments The first three authors contributed equally. This work has been accepted for publication at the Conference on Robot Learning
Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
机构 * University of Toronto（多伦多大学）
Comments Accepted to the CoRL 2025 Eval&Deploy Workshop
CUPID: Curating Data your Robot Loves with Influence Functions
机构 * Stanford University（斯坦福大学） ； University of Cambridge（剑桥大学） ； NVIDIA Research（NVIDIA研究） ； Toyota Research Institute（丰田研究机构）
Comments Project page: https://cupid-curation.github.io. 27 pages, 15 figures. Accepted to the Conference on Robot Learning (CoRL) 2025
Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures
Comments Conference on Robot Learning (CoRL 2025)
DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation
机构 * Stanford University（斯坦福大学） ； University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）
Comments Accepted to CoRL 2025
PrioriTouch: Adapting to User Contact Preferences for Whole-Arm Physical Human-Robot Interaction
机构 * Cornell University（康奈尔大学） ； Toyota Research Institute（丰田研究中心）
Comments Conference on Robot Learning (CoRL)
Constrained Style Learning from Imperfect Demonstrations under Task Optimality
机构 * ETH Zurich（苏黎世联邦理工学院）
Comments This paper has been accepted to CoRL 2025
ComposableNav: Instruction-Following Navigation in Dynamic Environments via Composable Diffusion
机构 * Department of Computer Science, The University of Texas at Austin（德克萨斯大学计算机科学系） ； Army Research Laboratory（陆军研究实验室） ； Sony AI（索尼人工智能）
Comments Conference on Robot Learning (CoRL) 2025 Project site: https://amrl.cs.utexas.edu/ComposableNav/
The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio
机构 * University of California, Berkeley（加州大学伯克利分校）
Comments Conference on Robot Learning 2025
UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
机构 * Yonsei University（延世大学）
Comments CoRL 2025. Project Page: https://kimhanjung.github.io/UniSkill/
ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
机构 * Thomas Lord Department of Computer Science, University of Southern California（南加州大学计算机科学系） ； Amazon Robotics（亚马逊机器人技术） ； Kim Jaechul School of Artificial Intelligence, KAIST（韩国科学技术院人工智能学院）
Comments CoRL 2025 Oral
Affordance-Based Disambiguation of Surgical Instructions for Collaborative Robot-Assisted Surgery
机构 * Nagoya University, Japan（名古屋大学）
Comments To be presented at the 1st Workshop on Intelligent Cobodied Assistance and Robotic Empowerment (iCARE). 2025 Conference on Robot Learning (CoRL)
exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation
机构 * Shanghai Jiao Tong University（上海交通大学） ； Shanghai Innovation Institute（上海创新研究院）
Comments Accepted at CoRL 2025
Object Recognition and Force Estimation with the GelSight Baby Fin Ray
机构 * Massachusetts Institute of Technology（麻省理工学院）
Comments Presented at CoRL 2023 as part of the workshop, "Learning for Soft Robots: Hard Challenges for Soft Systems" (website: https://sites.google.com/view/corl-2023-soft-robots-ws)
Meta-Optimization and Program Search using Language Models for Task and Motion Planning
机构 * TU Berlin（柏林技术大学）
Comments 8 pages main text, 11 pages appendix, accepted at the 9th Annual Conference on Robot Learning (CoRL 2025)
Force-Modulated Visual Policy for Robot-Assisted Dressing with Arm Motions
机构 * Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） ； Department of Engineering Design, Indian Institute of Technology, Madras（印度理工学院Madras分校工程设计系）
Comments CoRL 2025
Geometric Red-Teaming for Robotic Manipulation
机构 * Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） ； National Institute of Standards and Technology（国家标准与技术研究院）
Comments Accepted at the 9th Annual Conference on Robot Learning (CoRL 2025, Oral)
Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop
机构 * UC Berkeley（伯克利大学）
Comments CoRL 2025, project page: https://www.eyerobot.net/
Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use
机构 * University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； UT Austin（德克萨斯大学奥斯汀分校） ； Columbia University（哥伦比亚大学）
Comments Accepted to CoRL 2025. Project page: https://tool-as-interface.github.io. 17 pages, 14 figures
GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation
机构 * Department of Automation, Tsinghua University（自动化系，清华大学）
Comments Accepted to CoRL 2025. Project page: [this https URL](https://bagh2178.github.io/GC-VLN/)
Self-supervised Learning Of Visual Pose Estimation Without Pose Labels By Classifying LED States
机构 * Dalle Molle Institute for Artificial Intelligence (IDSIA)（达摩研究院（IDSIA））
Comments accepted at CoRL 2025
LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation
机构 * National University of Defense Technology（国防科技大学） ； Peking University（北京大学） ； Shenzhen University（深圳大学）
Comments CoRL 2025
Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration
机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； NVIDIA（英伟达）
Comments CoRL 2025
ObjectReact: Learning Object-Relative Control for Visual Navigation
机构 * University of Adelaide, Australia（澳大利亚阿德莱德大学） ； IIIT Hyderabad, India（印度海得拉巴IIIT） ； MBZUAI, UAE（阿联酋MBZUAI）
Comments CoRL 2025; 23 pages including appendix
Joint Model-based Model-free Diffusion for Planning with Constraints
机构 * Georgia Institute of Technology（佐治亚理工学院）
Comments The first two authors contributed equally. Last three authors advised equally. Accepted to CoRL 2025
Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination
机构 * Georgia Institute of Technology（佐治亚理工学院）
Comments 22 pages, 8 figures, equal authorship between Kevin Fu and Shalin Anand Jain Manuscript accepted for publication at the 9th Conference on Robot Learning (CoRL 2025), Seoul, Korea
