End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control
Bosch Corporate Research(博世企业研究中心);University Of Lincoln(林肯大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)
Moritz Reuss, Niels van Duijkeren, Robert Krug, Philipp Becker, Vaisakh Shaj, Gerhard Neumann
备注:
Accepted for publication at Robotics: Science and System XVIII (RSS), year 2022. Paper length is 13 pages (i.e. 9 pages of technical content, 1 page of the Bibliography/References and 3 pages of Appendix)
It is well-known that inverse dynamics models can improve tracking performance in robot control. These models need to precisely capture the robot dynamics, which consist of well-understood components, e.g., rigid body dynamics, and effects that remain challenging to capture, e.g., stick-slip friction and mechanical flexibilities. Such effects exhibit hysteresis and partial observability, rendering them, particularly challenging to model. Hence, hybrid models, which combine a physical prior with data-driven approaches are especially well-suited in this setting. We present a novel hybrid model formulation that enables us to identify fully physically consistent inertial parameters of a rigid body dynamics model which is paired with a recurrent neural network architecture, allowing us to capture unmodeled partially observable effects using the network memory. We compare our approach against state-of-the-art inverse dynamics models on a 7 degree of freedom manipulator. Using data sets obtained through an optimal experiment design approach, we study the accuracy of offline torque prediction and generalization capabilities of joint learning methods. In control experiments on the real system, we evaluate the model as a feed-forward term for impedance control and show the feedback gains can be drastically reduced to achieve a given tracking accuracy.
PRISMA Lab, department of Electrical Engineering and Information Technology of the University of Naples Federico II(PRISMA实验室,那不勒斯费德里科二世大学电气工程与信息科技系);Inria, CNRS, Université de Lorraine(Inria、CNRS、洛林大学);ABB Corporate Research Center(ABB企业研究中心)
A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation
Beijing Institute of Control Engineering(北京控制工程研究所);Tsinghua University(清华大学);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);City University of Hong Kong(香港城市大学);Qian Xuesen Laboratory of Space Technology(钱学森空间技术实验室);Beijing Aerospace Automatic Control Institute(北京航天自动控制研究所)
DexTele: A Dual-Arm Dexterous Teleoperation System Based on Motion Retargeting and Adaptive Force Control
School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen(人工智能学院,香港中文大学(深圳));School of Computing, University of Portsmouth(计算学院,朴茨茅斯大学)
Plug, Play and Comply: Plugin-Based Compliant Control in ROS 2
College of Information Science and Technology, Eastern Institute of Technology(信息科学与技术学院,东方理工学院);Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology(浙江省工业智能与数字孪生重点实验室,东方理工学院)
Interaction-Aware Whole-Body Control for Compliant Object Transport
Department of Electrical Engineering, the University of Texas at Arlington(电气工程系,德克萨斯大学阿灵顿分校);Department of Mechanical Engineering, Carnegie Mellon University(机械工程系,卡内基梅隆大学)
A Null Space Compliance Approach for Maintaining Safety and Tracking Performance in Human-Robot Interactions
Department of Electrical and Computer Engineering, Western University(电气与计算机工程系,西方大学);School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(人工智能与自动化学院,华中科技大学)
Impedance and Stability Targeted Adaptation for Aerial Manipulator with Unknown Coupling Dynamics
Robotics Research Center, International Institute of Information Technology Hyderabad (IIIT-H)(印度海得拉巴国际信息技术学院机器人研究中心);The University of Manchester(曼彻斯特大学);Southeast University(东南大学)
Residual Compliant Policy: Learning Compliant Policies from Few Demonstrations
University of Pennsylvania(宾夕法尼亚大学);Technical University of Darmstadt(达姆施塔特工业大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);German Research Center for AI (DFKI)(德国人工智能研究中心);Robotics Institute Germany (RIG)(德国机器人研究所)
AllTact Fin Ray: A Compliant Robot Gripper with Omni-Directional Tactile Sensing
Department of Mechanical Engineering, Tsinghua University(清华大学机械工程系);Tsinghua-Berkeley Shenzhen Institute(清华大学-伯克利深圳研究院);Institute of Data and Information, Shenzhen International Graduate School, Tsinghua University(清华大学数据与信息研究所、深圳国际研究生院)
本文提出 AllTact Fin Ray 柔顺机器人夹爪,通过相机捕捉指体形变,并提出基于边缘特征重建全局形变与动态参考图像亮度差异计算接触几何的新方法,实现了全向触觉感知,在接触检测、力估计和精确操作等任务中验证了有效性。