Motivated by recent advances in Deep Learning for robot control, this paper considers two learning algorithms in terms of how they acquire demonstrations. "Human-Centric" (HC) sampling is the standard supervised learning algorithm, where a human supervisor demonstrates the task by teleoperating the robot to provide trajectories consisting of state-control pairs. "Robot-Centric" (RC) sampling is an increasingly popular alternative used in algorithms such as DAgger, where a human supervisor observes the robot executing a learned policy and provides corrective control labels for each state visited. RC sampling can be challenging for human supervisors and prone to mislabeling. RC sampling can also induce error in policy performance because it repeatedly visits areas of the state space that are harder to learn. Although policies learned with RC sampling can be superior to HC sampling for standard learning models such as linear SVMs, policies learned with HC sampling may be comparable with highly-expressive learning models such as deep learning and hyper-parametric decision trees, which have little model error. We compare HC and RC using a grid world and a physical robot singulation task, where in the latter the input is a binary image of a connected set of objects on a planar worksurface and the policy generates a motion of the gripper to separate one object from the rest. We observe in simulation that for linear SVMs, policies learned with RC outperformed those learned with HC but that with deep models this advantage disappears. We also find that with RC, the corrective control labels provided by humans can be highly inconsistent. We prove there exists a class of examples where in the limit, HC is guaranteed to converge to an optimal policy while RC may fail to converge.
FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation
Southern University of Science and Technology(南方科技大学);National University of Singapore(新加坡国立大学);Smart Systems Institute, National University of Singapore(新加坡国立大学智能系统研究院)
Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations
The University of Hong Kong(香港大学);JD.com (JingDong)(京东);Nanyang Technological University (NTU)(南洋理工大学);Southern University of Science and Technology (SUSTech)(南方科技大学);Huawei Technologies(华为技术有限公司);The Chinese University of Hong Kong (CUHK)(香港中文大学)
Generalizing Robot Trajectories from Single-Context Human Demonstrations: A Probabilistic Approach
Robotics Research Centre, School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore(南洋理工大学机器人研究中心,机械与航空航天工程学院);Delta-NTU Corporate Lab, Singapore(Delta-NTU企业实验室)
Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(信息处理国家重点实验室,计算机学院,北京大学);University of Washington(华盛顿大学);Beijing Innovation Center of Humanoid Robotics(北京人形机器人创新中心)
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
Department of Informatics, Graduate School of Informatics, Kyoto University(信息学系,京都大学研究生院);Spatial Robotics Research Center, Fujitsu Limited(空间机器人研究中心,富士通有限公司)
TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation
Shanghai AI Laboratory(上海人工智能实验室);Zhejiang University(浙江大学);The Chinese University of Hong Kong(香港中文大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The University of Hong Kong(香港大学);Feeling AI(FeelAI);Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院)
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
National University of Singapore(新加坡国立大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Institude for Information Research, A STAR(A*STAR信息研究所)
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。
DexViTac: Collecting Human Visuo-Tactile-Kinematic Demonstrations for Contact-Rich Dexterous Manipulation
State Key Laboratory of Intelligent Manufacturing Equipment and Technology(智能制造装备与技术国家重点实验室);Huazhong University of Science and Technology(华中科技大学);Wuhan Huaweike Intelligent Technology Co., Ltd.(武汉华为凯科技有限公司)
Booster Lab: A Data-Centric Pipeline for Learning Deployable Humanoid Locomotion Policies
Department of Automation, Tsinghua University(清华大学自动化系);School of Mechanical and Electronic Control Engineering, Beijing Jiaotong University(北京交通大学机械与电子控制工程学院);Booster Robotics Technology Co., Ltd(北京加速进化科技有限公司)