Title
Everybody Needs Somebody Sometimes: Validation Of Adaptive Recovery In Robotic Space Operations
Abstract
This letter assesses an adaptive approach to fault recovery in autonomous robotic space operations, which uses indicators of opportunity, such as physiological state measurements and observations of past human assistant performance, to inform future selections. We validated our reinforcement learning approach using data we collected from humans executing simulated mission scenarios. We present a method of structuring human-factors experiments that permits collection of relevant indicator of opportunity and assigned assistance task performance data, as well as evaluation of our adaptive approach, without requiring large numbers of test subjects. Application of our reinforcement learning algorithm to our experimental data shows that our adaptive assistant selection approach can achieve lower cumulative regret compared to existing nonadaptive baseline approaches when using real human data. Our work has applications beyond space robotics to any application where autonomy failuresmay occur that require external intervention.
Year
DOI
Venue
2019
10.1109/LRA.2019.2894381
IEEE ROBOTICS AND AUTOMATION LETTERS
Keywords
Field
DocType
Human-centered robotics, space robotics and automation, learning and adaptive systems
Resource management,Task analysis,Regret,Experimental data,Control engineering,Human–computer interaction,Space exploration,Engineering,Structuring,Robot,Reinforcement learning
Journal
Volume
Issue
ISSN
4
2
2377-3766
Citations 
PageRank 
References 
0
0.34
0
Authors
7
Name
Order
Citations
PageRank
Steve McGuire141.78
P. Michael Furlong241.42
Terry Fong312324.05
Christoffer R. Heckman41210.78
Daniel Szafir523023.05
simon j julier61463118.53
Nisar Ahmed741236.29