Abstract

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.

Original languageEnglish (US)
Title of host publication2016 IEEE 55th Conference on Decision and Control, CDC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5171-5176
Number of pages6
ISBN (Electronic)9781509018376
DOIs
StatePublished - Dec 27 2016
Event55th IEEE Conference on Decision and Control, CDC 2016 - Las Vegas, United States
Duration: Dec 12 2016Dec 14 2016

Publication series

Name2016 IEEE 55th Conference on Decision and Control, CDC 2016

Other

Other55th IEEE Conference on Decision and Control, CDC 2016
Country/TerritoryUnited States
CityLas Vegas
Period12/12/1612/14/16

ASJC Scopus subject areas

  • Artificial Intelligence
  • Decision Sciences (miscellaneous)
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Intent aware shared control in off-nominal situations'. Together they form a unique fingerprint.

Cite this