Incremental Skill Learning of Stable Dynamical Systems

被引:0
作者
Saveriano, Matteo [1 ]
Lee, Dongheui [1 ,2 ]
机构
[1] German Aerosp Ctr DLR, Inst Robot & Mechatron, Wessling, Germany
[2] Tech Univ Munich, Human Ctr Assist Robot, Munich, Germany
来源
2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) | 2018年
关键词
TASK;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Efficient skill acquisition, representation, and on-line adaptation to different scenarios has become of fundamental importance for assistive robotic applications. In the past decade, dynamical systems (DS) have arisen as a flexible and robust tool to represent learned skills and to generate motion trajectories. This work presents a novel approach to incrementally modify the dynamics of a generic autonomous DS when new demonstrations of a task are provided. A control input is learned from demonstrations to modify the trajectory of the system while preserving the stability properties of the reshaped DS. Learning is performed incrementally through Gaussian process regression, increasing the robot's knowledge of the skill every time a new demonstration is provided. The effectiveness of the proposed approach is demonstrated with experiments on a publicly available dataset of complex motions.
引用
收藏
页码:6574 / 6581
页数:8
相关论文
共 30 条
[1]  
[Anonymous], 2008, Springer Handbook of robotics
[2]  
Blocher C, 2017, INT CONF UBIQ ROBOT, P124
[3]   A survey of iterative learning control [J].
Bristow, Douglas A. ;
Tharayil, Marina ;
Alleyne, Andrew G. .
IEEE CONTROL SYSTEMS MAGAZINE, 2006, 26 (03) :96-114
[4]   Learning variable impedance control [J].
Buchli, Jonas ;
Stulp, Freek ;
Theodorou, Evangelos ;
Schaal, Stefan .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2011, 30 (07) :820-833
[5]   Learning-based control strategy for safe human-robot interaction exploiting task and robot redundancies [J].
Calinon, Sylvain ;
Sardellitti, Irene ;
Caldwell, Darwin G. .
IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010), 2010, :249-254
[6]  
Calinon S., 2018, HUMANOID ROBOTICS RE
[7]   On learning, representing, and generalizing a task in a humanoid robot [J].
Calinon, Sylvain ;
Guenter, Florent ;
Billard, Aude .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2007, 37 (02) :286-298
[8]   A tutorial on task-parameterized movement learning and retrieval [J].
Calinon, Sylvain .
INTELLIGENT SERVICE ROBOTICS, 2016, 9 (01) :1-29
[9]   On-line learning and modulation of periodic movements with nonlinear dynamical systems [J].
Gams, Andrej ;
Ijspeert, Auke J. ;
Schaal, Stefan ;
Lenarcic, Jadran .
AUTONOMOUS ROBOTS, 2009, 27 (01) :3-23
[10]  
Hoffmann H, 2009, IEEE INT CONF ROBOT, P1534