Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
DeepMind
Ivaylo Popov, Nicolas Heess, Timothy Lillicrap, Roland Hafner, Gabriel Barth-Maron, Matej Vecerik, Thomas Lampe, Yuval Tassa, Tom Erez, Martin Riedmiller
Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are difficult to solve using traditional control theory or hand-engineered approaches. One example of such a task is to grasp an object and precisely stack it on another. Solving this difficult and practically relevant problem in the real world is an important long-term goal for the field of robotics. Here we take a step towards this goal by examining the problem in simulation and providing models and techniques aimed at solving it. We introduce two extensions to the Deep Deterministic Policy Gradient algorithm (DDPG), a model-free Q-learning based method, which make it significantly more data-efficient and scalable. Our results show that by making extensive use of off-policy data and replay, it is possible to find control policies that robustly grasp objects and stack them. Further, our results hint that it may soon be feasible to train successful stacking policies by collecting interactions on real robots.
Dexterous Manipulation through Imitation Learning: A Survey
Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System（天津智能集群技术与系统重点实验室）；School of Electrical and Information Engineering（电气与信息工程学院）；Shandong University（山东大学）；State Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室）；Division of Robotics, Perception and Learning（机器人、感知与学习 division）；School of Control Science and Engineering（控制科学与工程学院）；Massachusetts Institute of Technology（麻省理工学院）；School of Computer Science（计算机科学学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence（人工智能学院）
Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration
University of California at Berkeley（加州大学伯克利分校）；Technische Universität Berlin（柏林工业大学）
灵巧的多指手可以完成精细的操作行为，这是不可行的简单的机器人抓手。然而，复杂的多指手往往是昂贵和脆弱的。低成本的软手为更传统的设备提供了一种有吸引力的替代方案，但在传感和致动方面存在相当大的挑战，使得它们难以应用于更复杂的操作任务。在本文中，我们描述了一种方法，从示范，可用于训练软机器人手执行灵巧的操作任务的学习。我们的方法使用以对象为中心的演示，其中人类用自己的手演示所需的操作对象的运动，机器人自主学习模仿这些演示使用强化学习。我们提出了一种新的算法，使我们能够混合和选择一个子集的最可行的示范学习模仿的硬件，我们使用的指导政策搜索框架的扩展，使用多个示范学习概括的神经网络政策。我们在RBO Hand 2上展示了我们的方法，学习了转动阀门，操纵算盘和抓握的运动技能。
DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation
DexRobot Co. Ltd.（德克斯机器人有限公司）；University of Michigan（密歇根大学）；Shanghai Jiao Tong University（上海交通大学）；Chongqing University（重庆大学）；East China University of Science and Technology（东华大学）
TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types
School of Computer Science and Engineering, Sun Yat-sen University, China（中山大学计算机科学与工程学院）；Stanford University, USA（斯坦福大学）；Imperial College London, UK（伦敦帝国理工学院）
Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention
State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University（机械系统与振动国家重点实验室，机械工程学院，上海交通大学）；Shanghai Key Laboratory of Intelligent Robotics, Meta Robotics Institute, Shanghai Jiao Tong University, Shanghai 200240, China（智能机器人上海市重点实验室，元机器人研究院，上海交通大学，上海200240，中国）；The University of Tokyo（东京大学）
DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo
NLPR & MAIS, CASIA（中国科学院南京自动化研究所与模式识别与人工智能实验室）；SJTU（上海交通大学）；MBZUAI（马克斯·普朗克研究所）；Beijing Institute of Basic Medical Sciences（北京基础医学研究所）；PKU & Galbot（北京大学与Galbot）；CUHK（香港大学）
EaDex: A Cross-Embodiment Dexterous Manipulation Framework from Low-Cost Demonstrations
Faculty of Robot Science and Engineering, Northeastern University（机器人科学与工程学院，东北大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；School of Automation, Nanjing University of Information Science and Technology（自动化学院，南京信息科学技术大学）
A Dexterous and Compliant Gripper With Soft Hydraulic Actuation for Microgravity Manipulation
Aerospace Engineering Program, University of California, Berkeley（加州大学伯克利分校航空航天工程系）；Department of Mechanical Engineering, University of California, Berkeley（加州大学伯克利分校机械工程系）；Department of Mechanical Engineering, National University of Singapore（新加坡国立大学机械工程系）
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）
