TY - GEN
T1 - Intent aware shared control in off-nominal situations
AU - Maske, Harshal
AU - Chowdhary, Girish
AU - Pagilla, Prabhakar
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/12/27
Y1 - 2016/12/27
N2 - We propose a new shared control technique that takes into account the operator's intent to quickly relinquish control to the operator in off-nominal conditions. Human-machine shared control is an emerging area of research in which the autonomous control is utilized to augment the operator's performance. Existing work has established that shared control can improve cycle times in nominal conditions, that is, when the operating environment satisfies the assumptions made in the design of the optimal augmenting controller. However, these methods can be too slow to relinquish control in off-nominal cases, when the operator needs to deviate from the nominally optimal trajectory due to unforeseen obstacles or other uncertainties. In this paper, we attempt to address this gap by mathematically quantifying operator intent. The resulting technique provides autonomous control augmentation to the operator when they are attempting to drive the system along the suggested optimal trajectory, but offers little hindrance to the operator when they are attempting to deal with off-nominal conditions. Theoretical results show that the performance of the presented intent aware shared control technique is at least as good as existing techniques, and that it results in improved obstacle reaction time. Human interaction experiments on the Zermelo's navigation problem in the presence of a random pop-up obstacle show a significant reduction in obstacle collision with our method when compared to existing work.
AB - We propose a new shared control technique that takes into account the operator's intent to quickly relinquish control to the operator in off-nominal conditions. Human-machine shared control is an emerging area of research in which the autonomous control is utilized to augment the operator's performance. Existing work has established that shared control can improve cycle times in nominal conditions, that is, when the operating environment satisfies the assumptions made in the design of the optimal augmenting controller. However, these methods can be too slow to relinquish control in off-nominal cases, when the operator needs to deviate from the nominally optimal trajectory due to unforeseen obstacles or other uncertainties. In this paper, we attempt to address this gap by mathematically quantifying operator intent. The resulting technique provides autonomous control augmentation to the operator when they are attempting to drive the system along the suggested optimal trajectory, but offers little hindrance to the operator when they are attempting to deal with off-nominal conditions. Theoretical results show that the performance of the presented intent aware shared control technique is at least as good as existing techniques, and that it results in improved obstacle reaction time. Human interaction experiments on the Zermelo's navigation problem in the presence of a random pop-up obstacle show a significant reduction in obstacle collision with our method when compared to existing work.
UR - http://www.scopus.com/inward/record.url?scp=85010767453&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85010767453&partnerID=8YFLogxK
U2 - 10.1109/CDC.2016.7799060
DO - 10.1109/CDC.2016.7799060
M3 - Conference contribution
AN - SCOPUS:85010767453
T3 - 2016 IEEE 55th Conference on Decision and Control, CDC 2016
SP - 5171
EP - 5176
BT - 2016 IEEE 55th Conference on Decision and Control, CDC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 55th IEEE Conference on Decision and Control, CDC 2016
Y2 - 12 December 2016 through 14 December 2016
ER -