Programming by demonstration for shared control with an application in teleoperation

被引：21

作者：

Zeestraten M.J.A. ^{[1
]}

Havoutis I. ^{[2
]}

Calinon S. ^{[1
,3
]}

机构：

[1] Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genova

[2] Oxford Robotics Institute, Department of Engineering Science, University of Oxford, Oxford

[3] Idiap Research Institute, Martigny

来源：

IEEE Robotics and Automation Letters | 2018年 / 3卷 / 03期

基金：

欧盟地平线“2020”;

关键词：

Learning and adaptive systems; probability and statistical methods; shared control; teleoperation;

D O I：

10.1109/LRA.2018.2805105

中图分类号：

学科分类号：

摘要：

Shared control strategies can improve task performance in teleoperation. In such systems, automation guides or corrects a human operator. The amount of correction or guidance that is provided is denoted the level of automation. As the variety of teleoperation tasks is large, manually specifying the underlying automation is time consuming. In this letter, we present an approach to program this automated system by demonstration. Our approach determines the level of automation online, by combining the confidence of automation and teleoperator. We present particular implementations of our approach for haptic shared control and state shared control. The method is evaluated in a user study. Although the subjects indicated they preferred the learned shared control strategies, teleoperation performance did not improve our metric (task execution time). © 2016 IEEE.

引用

页码：1848 / 1855

页数：7

共 27 条

[1]

Passenberg C., Peer A., Buss M., A survey of environment-, operator-, and task-adapted controllers for teleoperation systems, Mechatronics, 20, 7, pp. 787-801, (2010)

[2]

Boessenkool H., Abbink D.A., Heemskerk C.J.M., Van Der Helm T.F.C., Wildenbeest J.G.W., A task-specific analysis of the benefit of haptic shared control during telemanipulation, IEEE Trans. Haptics, 6, 1, pp. 2-12, (2013)

[3]

Perez-Del Pulgar C.J., Smisek J., Munoz V.F., Schiele A., Using learning from demonstration to generate real-time guidance for haptic shared control, Proc. IEEE Int. Conf. Syst., Man, Cybern., pp. 3205-3210, (2016)

[4]

Rosenberg L.B., Virtual fixtures: Perceptual tools for telerobotic manipulation, Proc. IEEE Int. Symp. Virtual Reality, pp. 76-82, (1993)

[5]

Abbott J.J., Marayong P., Okamura A.M., Haptic virtual fixtures for robot-assisted manipulation, Proc. Int. Symp. Robot. Res., pp. 49-64, (2007)

[6]

Van Oosterhout J., Et al., Haptic shared control in tele-manipulation: Effects of inaccuracies in guidance on task execution, IEEE Trans. Haptics, 8, 2, pp. 164-175, (2015)

[7]

Billard A.G., Calinon S., Dillmann R., Learning from humans, Handbook of Robotics, pp. 1995-2014, (2016)

[8]

Abbink D.A., Mulder M., Boer E.R., Haptic shared control: Smoothly shifting control authority, Cogn., Technol.Work, 14, 1, pp. 19-28, (2012)

[9]

Park S., Howe R.D., Torchiana D.F., Virtual fixtures for robotic cardiac surgery, Proc. Med. Image Comput. Comput.-Assisted Intervention, pp. 1419-1420, (2001)

[10]

Raiola G., Lamy X., Stulp F., Co-manipulation with multiple probabilistic virtual guides, Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., pp. 7-13, (2015)

← 1 2 3 →