Visible to the public A POMDP-based Robot-Human Trust Model for Human-Robot Collaboration

TitleA POMDP-based Robot-Human Trust Model for Human-Robot Collaboration
Publication TypeConference Paper
Year of Publication2022
AuthorsTilloo, Pallavi, Parron, Jesse, Obidat, Omar, Zhu, Michelle, Wang, Weitian
Conference Name2022 12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER)
Keywordsbelief probability, Collaboration, Computational modeling, Data models, Human Behavior, human factors, human-robot collaboration, Manufacturing industries, Markov processes, object detection, pomdp, pubcrawl, resilience, Resiliency, Robot Trust, Robotics, Service robots, Trust
AbstractTrust is a cognitive ability that can be dependent on behavioral consistency. In this paper, a partially observable Markov Decision Process (POMDP)-based computational robot-human trust model is proposed for hand-over tasks in human-robot collaborative contexts. The robot's trust in its human partner is evaluated based on the human behavior estimates and object detection during the hand-over task. The human-robot hand-over process is parameterized as a partially observable Markov Decision Process. The proposed approach is verified in real-world human-robot collaborative tasks. Results show that our approach can be successfully applied to human-robot hand-over tasks to achieve high efficiency, reduce redundant robot movements, and realize predictability and mutual understanding of the task.
NotesISSN: 2642-6633
DOI10.1109/CYBER55403.2022.9907660
Citation Keytilloo_pomdp-based_2022