RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation
Comments Accepted to CoRL 2025, Project Page: https://zzongzheng0918.github.io/RoboChemist.github.io/
期刊&会议
CoRL
Conference on Robot Learning · 会议 · Robotics
SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation
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://larg.github.io/socialnav-sub
One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation
机构 * Beijing Academy of Artificial Intelligence, BAAI（北京人工智能研究院） ； Zhejiang University（浙江大学） ； Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院） ； Nanyang Technological University（南洋理工大学） ； FNii, The Chinese University of Hongkong, Shenzhen（Fnii，香港中文大学（深圳）） ； Shanghai Jiao Tong University（上海交通大学） ； Eastern Institute of Technology, Ningbo（宁波工程技术学院）
Comments CoRL 2025 Oral, Project page: https://gzwsama.github.io/OnePoseviaGen.github.io/
TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models
机构 * Beijing Academy of Artificial Intelligence, BAAI（北京人工智能研究院） ； Institute for AI Industry Research (AIR), Tsinghua Univeristy（清华大学人工智能产业研究院） ； Nanyang Technological University（南洋理工大学）
Comments Accepted to CoRL 2025, project page: \url{https://zzongzheng0918.github.io/Torque-Aware-VLA.github.io/}
Text2Touch: Tactile In-Hand Manipulation with LLM-Designed Reward Functions
机构 * School of Computer Science, University of Bristol, 2 Bristol Robotics Laboratory 3 School of Engineering Mathematics and Technology, University of Bristol（1 计算机科学学院，布里斯托尔大学 2 布里斯托尔机器人实验室 3 工程数学与技术学院，布里斯托尔大学）
Comments Accepted at CoRL 2025
O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation
机构 * University of Virginia（弗吉尼亚大学）
Comments Conference on Robot Learning (CoRL) 2025. Project website: https://o3afford.github.io/
COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy Learning
机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Comments Accepted at the Conference on Robot Learning (CoRL), 2025. Project page: https://robin-lab.cs.utexas.edu/COLLAGE
SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
Comments The first two authors contributed equally. Accepted to CoRL 2025
ARCH: Hierarchical Hybrid Learning for Long-Horizon Contact-Rich Robotic Assembly
机构 * Stanford University（斯坦福大学） ； MIT（麻省理工学院） ； University of Michigan（密歇根大学） ； Autodesk Research（Autodesk研究）
Comments The Conference on Robot Learning (CoRL) 2025
FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
机构 * Intuitive Robots Lab（直观机器人实验室） ； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院） ； Microsoft Research（微软研究院）
Comments Published at CoRL 2025
Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees
机构 * Viterbi Faculty of Electrical and Computer Engineering（电气与计算机工程学院） ； Technion–Israel Institute of Technology（技术学院–以色列理工学院）
Comments Accepted to CoRL 2025, Project page: https://sites.google.com/view/ditree. v2: Abstract updated
Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement
机构 * Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） ； Princeton University（普林斯顿大学）
Comments Conference on Robot Learning (CoRL) 2025 (https://planning-from-point-clouds.github.io/)
Reactive In-Air Clothing Manipulation with Confidence-Aware Dense Correspondence and Visuotactile Affordance
机构 * Massachusetts Institute of Technology（麻省理工学院） ； Prosper AI ； Boston Dynamics
Comments Accepted at CoRL 2025. Project website: https://mhtippur.github.io/inairclothmanipulation/
First Order Model-Based RL through Decoupled Backpropagation
机构 * Machines in Motion Laboratory, New York University, USA（纽约大学运动机器实验室） ； LAAS-CNRS, Université de Toulouse, CNRS, Toulouse, France（图卢兹大学LAAS-CNRS） ； Artificial and Natural Intelligence Toulouse Institute, Toulouse, France（图卢兹人工智能与自然智能研究所）
Comments CoRL 2025. Project website: https://machines-in-motion.github.io/DMO/
Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation
机构 * NVIDIA ； Harvard University（哈佛大学） ； Stanford University（斯坦福大学）
Comments Conference on Robot Learning (CoRL) 2025
ClutterDexGrasp: A Sim-to-Real System for General Dexterous Grasping in Cluttered Scenes
机构 * CFCS, School of Computer Science, Peking University（计算机学院，北京大学） ； PKU-AgiBot Lab（北京大学阿吉机器人实验室） ； PKU-PsiBot Lab（北京大学Psi机器人实验室） ； Princeton University（普林斯顿大学）
Comments Accepted at CoRL 2025
Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames
机构 * QUT Centre for Robotics, Queensland University of Technology（昆士兰科技大学机器人中心，昆士兰理工大学） ； University of Adelaide（阿德莱德大学）
Comments Accepted at the Conference on Robot Learning (CoRL), 2025. Videos can be found on our project website: https://affordance-policy.github.io
FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference
机构 * School of Information Computation and Technology, Technical University of Munich (TUM)（技术大学慕尼黑信息计算技术学院） ； Institute of Robotics and Mechatronics, German Aerospace Center (DLR)（德国航空航天中心机器人与机电研究所） ； Department of Informatics, Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院信息学院）
Comments First two authors contributed equally, whose ordering decided via coin-tossing. Accepted for CoRL 2025
Do LLM Modules Generalize? A Study on Motion Generation for Autonomous Driving
机构 * Autolab, Westlake University（自动化实验室，西lake大学） ； Zhejiang University（浙江大学）
Comments CoRL 2025
Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control
机构 * Oregon State University（俄勒冈州立大学）
Comments 17 pages, 6 figures. Accepted as Oral presentation at Conference on Robot Learning (CoRL) 2025
Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference
机构 * University of Utah（犹他大学） ； NVIDIA Research（NVIDIA研究）
Comments Project page: sites.google.com/view/fail2progress. 25 pages, 8 figures. Accepted to the Conference on Robot Learning (CoRL) 2025
Articulated Object Estimation in the Wild
机构 * University of Freiburg（弗赖堡大学） ； University of Stuttgart（斯图加特大学） ； University of Technology Nuremberg（纽伦堡技术大学）
Comments 9th Conference on Robot Learning (CoRL), 2025
MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation
Comments Accepted to CoRL 2025. Project Page: https://gary3410.github.io/MoTo/
Data Retrieval with Importance Weights for Few-Shot Imitation Learning
机构 * Stanford University（斯坦福大学）
Comments Conference on Robot Learning 2025
Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning
机构 * Agency for Defense Development（国防发展局）
Comments Accepted to The Conference on Robot Learning (CoRL) 2025 Project Page: seonsoo-p1.github.io/DMCM
SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition
机构 * Cornell University（康奈尔大学） ； UC San Diego（南加州大学）
Comments Conference on Robot Learning, Oral
Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids
机构 * UC Berkeley（伯克利大学） ； NVIDIA（英伟达） ； UT Austin（奥斯汀大学）
Comments Published at CoRL 2025. Project page can be found at https://toruowo.github.io/recipe/
NeuralSVCD for Efficient Swept Volume Collision Detection
机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Comments CoRL 2025
Generative Visual Foresight Meets Task-Agnostic Pose Estimation in Robotic Table-Top Manipulation
机构 * Southern University of Science and Technology（南方科技大学） ； LimX Dynamics（LimX动力学） ； The University of Hong Kong（香港大学）
Comments 9th Conference on Robot Learning (CoRL 2025), Seoul, Korea
Mechanistic interpretability for steering vision-language-action models
Comments CoRL 2025. Project website: https://vla-mech-interp.github.io/
