Human-Robot Teaming under Suboptimality
Author(s)
Xue, Chunyue
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Effective human-robot teaming requires robot agents to adapt to their human partner's strengths and preferences quickly. However, humans and agents can be suboptimal in real-world collaboration due to a lack of information or biases. In this work, we aim to maximize human-robot team performance under suboptimality by adopting a POMDP-based adaptive approach that allows the robot to infer people's preferences and trust in the robot in a decision-making game. Our results show that 1) user preferences and team performance can vary with different robot intervention styles, and 2) our proposed approach can maximize users’ subjective references and objective performance.
Sponsor
Date
2023-08-30
Extent
Resource Type
Text
Resource Subtype
Thesis