Online Simultaneous Semi-Parametric Dynamics Model Learning

被引:9
作者
Smith, Joshua [1 ]
Mistry, Michael [1 ]
机构
[1] Univ Edinburgh, Sch Informat, Edinburgh EH8 9YL, Midlothian, Scotland
来源
IEEE ROBOTICS AND AUTOMATION LETTERS | 2020年 / 5卷 / 02期
基金
英国工程与自然科学研究理事会; 欧盟地平线“2020”;
关键词
Dynamics; calibration and identification; model learning for control; robust; adaptive control of robotic systems;
D O I
10.1109/LRA.2020.2970987
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Accurate models of robots dynamics are critical for control, stability, motion optimization, and interaction. Semi-Parametric approaches to dynamics learning combine physics-based Parametric models with unstructured Non-Parametric regression with the hope to achieve both accuracy and generalizability. In this letter, we highlight the non-stationary problem created when attempting to adapt both Parametric and Non-Parametric components simultaneously. We present a consistency transform designed to compensate for this non-stationary effect, such that the contributions of both models can adapt simultaneously without adversely affecting the performance of the platform. Thus, we are able to apply the Semi-Parametric learning approach for continuous iterative online adaptation, without relying on batch or offline updates. We validate the transform via a perfect virtual model as well as by applying the overall system on a Kuka LWR IV manipulator. We demonstrate improved tracking performance during online learning and show a clear transference of contribution between the two components with a learning bias towards the Parametric component.
引用
收藏
页码:2039 / 2046
页数:8
相关论文
共 16 条
[1]  
[Anonymous], ROBOTICS SCI SYSTEMS
[2]  
[Anonymous], 2017, ARXIV170103940
[3]  
[Anonymous], ARXIV190611909
[4]   ESTIMATION OF INERTIAL PARAMETERS OF MANIPULATOR LOADS AND LINKS [J].
ATKESON, CG ;
AN, CH ;
HOLLERBACH, JM .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 1986, 5 (03) :101-119
[5]   The real-time motion control core of the Orocos project [J].
Bruyninckx, H ;
Soetens, P ;
Koninckx, B .
2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-3, PROCEEDINGS, 2003, :2766-2771
[6]  
Camoriano R, 2016, IEEE INT CONF ROBOT, P544, DOI 10.1109/ICRA.2016.7487177
[7]   Incremental Local Online Gaussian Mixture Regression for Imitation Learning of Multiple Tasks [J].
Cederborg, Thomas ;
Li, Ming ;
Baranes, Adrien ;
Oudeyer, Pierre-Yves .
IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010), 2010, :267-274
[8]  
Garofalo G, 2013, IEEE INT C INT ROBOT, P2364, DOI 10.1109/IROS.2013.6696688
[9]   Using Model Knowledge for Learning Inverse Dynamics [J].
Nguyen-Tuong, Duy ;
Peters, Jan .
2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2010, :2677-2682
[10]   Model Learning with Local Gaussian Process Regression [J].
Nguyen-Tuong, Duy ;
Seeger, Matthias ;
Peters, Jan .
ADVANCED ROBOTICS, 2009, 23 (15) :2015-2034