Developing robot controllers capable of achieving dexterous nonprehensile manipulation, such as pushing an object on a table, is challenging. The underactuated and hybrid-dynamics nature of the problem, further complicated by the uncertainty resulting from the frictional interactions, requires sophisticated control behaviors. Reinforcement Learning (RL) is a powerful framework for developing such robot controllers. However, previous RL literature addressing the nonprehensile pushing task achieves low accuracy, non-smooth trajectories, and only simple motions, i.e. without rotation of the manipulated object. We conjecture that previously used unimodal exploration strategies fail to capture the inherent hybrid-dynamics of the task, arising from the different possible contact interaction modes between the robot and the object, such as sticking, sliding, and separation. In this work, we propose a multimodal exploration approach through categorical distributions, which enables us to train planar pushing RL policies for arbitrary starting and target object poses, i.e. positions and orientations, and with improved accuracy. We show that the learned policies are robust to external disturbances and observation noise, and scale to tasks with multiple pushers. Furthermore, we validate the transferability of the learned policies, trained entirely in simulation, to a physical robot hardware using the KUKA iiwa robot arm. See our supplemental video: https://youtu.be/vTdva1mgrk4.
Rearrangement with Nonprehensile Manipulation Using Deep Reinforcement Learning
Hong Kong University of Science and Technology（香港科技大学）；HKUST Robotics Institute（香港科技大学机器人研究所）；HKUST Institute for Advanced Study（香港科技大学高等研究院）；KTH Royal Institute of Technology（瑞典皇家理工学院）
Towards Multi-Object Nonprehensile Transportation via Shared Teleoperation: A Framework Based on Virtual Object Model Predictive Control
State Key Laboratory of Robotics and System, Harbin Institute of Technology（哈尔滨工业大学机器人技术与系统国家重点实验室）；Advanced Manufacturing Laboratory, Huawei Technologies（华为技术有限公司先进制造实验室）
Keep it Upright: Model Predictive Control for Nonprehensile Object Transportation with Obstacle Avoidance on a Mobile Manipulator
Technical University of Munich（慕尼黑工业大学）；University of Toronto Institute for Aerospace Studies（多伦多大学航空航天研究所）；University of Toronto Robotics Institute（多伦多大学机器人研究所）；Munich Institute of Robotics and Machine Intelligence（慕尼黑机器人与机器智能研究所）；Vector Institute for Artificial Intelligence（矢量人工智能研究所）
Learning Tri-mode Grasping for Ambidextrous Robot Picking
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）
DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
Center on Frontiers of Computing Studies, School of Computer Science, Peking University（前沿计算研究教育部重点实验室，计算机学院，北京大学）；Galbot；Inst. for Artificial Intelligence, Peking University（人工智能研究所，北京大学）；State Key Laboratory of General Artificial Intelligence, Peking University（通用人工智能国家重点实验室，北京大学）
Uni-PNP: Unified Prehensile and Non-prehensile Policy Learning for Generalizable Object Pose Reaching
Peking University（北京大学）；Galbot；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）；Tsinghua University（清华大学）
Learning Goal-Directed Object Pushing in Cluttered Scenes With Location-Based Attention
Humanoid Robots Lab, University of Bonn, Germany（波恩大学人形机器人实验室）；School of Informatics, The University of Edinburgh, Edinburgh, UK（爱丁堡大学信息学院）；The Alan Turing Institute, London, UK（艾伦·图灵研究所）；The Lamarr Institute, Bonn, Germany（波恩兰马尔研究所）；The Center for Robotics, University of Bonn, Germany（波恩大学机器人中心）
