Georgia Institute of Technology
Towards Genuine Robot Teammates: Inferring and Applying Cognitive State to Enable Novel Human-Autonomy Teaming Capabilities
Abstract
dc:description.abstractWhat makes a teammate? Surprisingly little research has focused on developing robot capabilities that replicate the interactions and inferences commonly observed in human-human teams. This dissertation investigates a broad range of interaction techniques and application domains that leverage personalized information about human users to inform a robot's decision-making and task execution. I model users through two key aspects of cognitive state: their latent cognitive skills and inferred mental models. These models are applied to practical human-robot teaming problems. Additionally, I explore how robot error type impacts user responses and team performance in structured shared decision-making. The findings presented in this dissertation enable novel teaming capabilities that adapt to individuals' prior knowledge and real-time belief states.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Aerospace Engineering
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kolb, Jack
- Advisor dc:contributor.advisor
-
- Feigh, Karen M.
- Committee members dc:contributor.committeemember
-
- Chernova, Sonia
- Ravichandar, Harish
- Adams, Julie A.
- Wagner, Alan
Subjects
dc:subject × 5Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/77880