Learning to reach arbitrary goals from sparse feedback requires agents to infer a rich notion of reachability across state--goal pairs. Goal-conditioned reinforcement learning (GCRL) tackles this challenge by learning policies that generalize across goals, but this generalization becomes increasingly difficult as the underlying dynamics become high-dimensional, hybrid, or contact-dependent. To address this issue, physics-informed GCRL (Pi-GCRL) introduces optimal-control-inspired inductive biases into goal-conditioned value learning. While Pi-GCRL methods have proven effective in navigation and object-free goal-reaching domains, their reliability in contact-rich tasks remains unclear, where contact interactions induce hybrid dynamics, mode-dependent controllability, and nonsmooth value landscapes. In this work, we show that these structural properties can cause existing Pi-GCRL methods to degrade when applied naively to contact-rich manipulation. Motivated by this analysis, we introduce contact-aware and hierarchical formulations that apply physics-informed inductive biases selectively across the manipulation problem. Our results provide a principled step toward extending Pi-GCRL to contact-rich manipulation.
Hierarchical Experience-informed Navigation for Multi-modal Quadrupedal Rebar Grid Traversal
Georgia Institute of Technology(佐治亚理工学院);School of Mechanical Engineering, Georgia Institute of Technology(佐治亚理工学院机械工程学院);SkyMul Inc(SkyMul公司);School of Electrical and Computer Engineering, Georgia Institute of Technology(佐治亚理工学院电气与计算机工程学院)
Physics-Informed Neural Optimal Control for Precision Immobilization Technique in Emergency Scenarios
Institute of Power Machinery and Vehicular Engineering, Zhejiang University(浙江大学动力机械及车辆工程研究所);Zhejiang Key Laboratory of Intelligent Vehicle Comprehensive Safety(浙江省智能车辆综合安全重点实验室)
Generative Models From and For Sampling-Based MPC: A Bootstrapped Approach For Adaptive Contact-Rich Manipulation
Oxford Robotics Institute, University of Oxford, UK(牛津大学机器人研究所);Robotics and AI Institute (RAI), Boston, USA(机器人与人工智能研究所);Cornell University, Ithaca, NY, USA(康奈尔大学)
ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
College of Connected Computing, Vanderbilt University(范德堡大学连接计算学院);School of Computer Science, The University of Sydney(悉尼大学计算机学院);Australian Centre for Robotics, The University of Sydney(悉尼大学澳大利亚机器人中心)
GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots
Dynamic Robot Systems Group, Oxford Robotics Institute, University of Oxford(牛津大学机器人研究所动态机器人系统组);Sony AI(索尼人工智能);Dyson Institute of Engineering and Technology(戴森工程与技术研究所)
Adaptive Motion Planning via Contact-Based Intent Inference for Human-Robot Collaboration
Department of Mechanical Engineering, Texas A&M University(机械工程系,德克萨斯A&M大学);Department of Civil and Environmental Engineering, Texas A&M University(土木与环境工程系,德克萨斯A&M大学)
Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steering
Artificial and Mechanical Intelligence, Italian Institute of Technology(意大利理工学院人工智能与机械智能部门);Machine Learning and Optimisation, University of Manchester(曼彻斯特大学机器学习与优化部门);Dipartimento di Automatica e Informatica, Politecnico di Torino(都灵politecnico自动化与信息学院);Rehab Technologies Lab, Italian Institute of Technology(意大利理工学院康复技术实验室)
TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation
TARS Robotics;National University of Singapore(新加坡国立大学);Shanghai Jiao Tong University(上海交通大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Fudan University(复旦大学)
HIRE: History-Conditioned Interaction Reasoning and High-Rate Execution for Visually Aliased Precision Manipulation
MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所多模态人工智能系统实验室);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Zhongguancun Academy(中关村学院);Noematrix;Shanghai Jiao Tong University(上海交通大学)
Phy-Tac: Toward Human-Like Grasping via Physics-Conditioned Tactile Goals
Department of Mechanical Engineering, The Hong Kong Polytechnic University (PolyU)(香港理工大学机械工程系);Research Institute for Smart Ageing (RISA), PolyU(PolyU智能老龄化研究所以);Ningbo Institute of Digital Twin, Eastern Institute of Technology (EIT)(宁波数字孪生研究所,东部技术研究所);Department of Mechanical and Energy Engineering, Southern University of Science and Technology(南方科技大学机械与能源工程系)
FoLD: Force-Informed Learning for Dexterous Articulated Object Manipulation
University of Science and Technology of China(中国科学技术大学);Institute of AI for Industries, Chinese Academy of Sciences(中国科学院人工智能产业研究院);Shenzhen University(深圳大学)
TLA: Tactile-Language-Action Model for Contact-Rich Manipulation
Samsung Research China - Beijing(三星中国研究院北京);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Beijing Academy of Artificial Intelligence(北京人工智能研究院)
State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology(华中科技大学机械科学与工程学院智能制造装备与技术国家重点实验室);Electric Power Research Institute, Guangdong Power Grid Co Ltd.(广东电网有限责任公司电力科学研究院)
本文针对仅触觉操作的手中6自由度物体位姿精化难题,提出基于SE(3)的物理信息滑动窗口粒子滤波,结合多触觉帧融合等技术,在Allegro Hand V5实验中取得优于基线的位姿精化效果。
Tongji University(同济大学);Shanghai Research Institute for Intelligent Autonomous Systems(上海自主智能无人系统研究院);Purdue University(普渡大学);Nanyang Technological University, Singapore(新加坡南洋理工大学)
KineDex: Learning Tactile-Informed Visuomotor Policies via Kinesthetic Teaching for Dexterous Manipulation
Tongji University(同济大学);Tsinghua University(清华大学);Shanghai Jiao Tong University(上海交通大学);University of Hong Kong(香港大学);Shanghai Qi Zhi Institute(上海启智研究院);Shanghai AI Lab(上海人工智能实验室)
QuietWalk: Physics-Informed Reinforcement Learning for Ground Reaction Force-Aware Humanoid Locomotion Under Diverse Footwear
Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences(宁波材料技术与工程研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Zhejiang Key Laboratory of Precision Actuation and Intelligent Robotics(浙江精密作动与智能机器人重点实验室);School of Engineering, Westlake University(西湖大学工程学院)
Tac-Man: Tactile-Informed Prior-Free Manipulation of Articulated Objects
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Beijing Institute for General Artificial Intelligence(北京人工智能研究院);Department of Automation, Tsinghua University(清华大学自动化系);College of Engineering, Peking University(北京大学工程学院);PKU-Wuhan Institute for Artificial Intelligence(北大-武汉人工智能研究院)