Abstract
dc:description.abstractEffective 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.
Degree
thesis:*- Level thesis:degree_level
- Masters
- Department dc:contributor.department
- Computer Science
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Xue, Chunyue
- Advisor dc:contributor.advisor
-
- Gombolay, Matthew
- Committee members dc:contributor.committeemember
-
- Ravichandar, Harish
- van Waveren, Sanne
Subjects
dc:subject × 3Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/76751