Everybody Needs Somebody Sometimes: Validation of Adaptive Recovery in Robotic Space Operations

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 learnin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE robotics and automation letters Jg. 4; H. 2; S. 1216 - 1223
Hauptverfasser: McGuire, Steve, Furlong, P. Michael, Fong, Terry, Heckman, Christoffer, Szafir, Daniel, Julier, Simon J., Ahmed, Nisar
Format: Journal Article
Sprache:Englisch
Veröffentlicht: 2230 Support IEEE 01.04.2019
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Adaptation models
Algorithms
Autonomy
Computer simulation
Cybernetics, Artificial Intelligence and Robotics
Human performance
Human-centered robotics
learning and adaptive systems
Machine learning
Monitoring
NASA
Recovery
Resource management
Robotics
Robots
Space missions
space robotics and automation
Task analysis
Learning And Adaptive Systems
Task Analysis
Human-Centered Robotics
Space Robotics And Automation
Nasa
Adaptation Models
Robots
Resource Management
Space Missions
Monitoring
ISSN:2377-3766, 2377-3766
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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 failures may occur that require external intervention.
Bibliographie:2230 Support
2230
NIHMS1522439
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2019.2894381