Back to search

Georgia Institute of Technology

Towards Genuine Robot Teammates: Inferring and Applying Cognitive State to Enable Novel Human-Autonomy Teaming Capabilities

Abstract

dc:description.abstract

What 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 × 5

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/77880

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kolb, Jack. Towards Genuine Robot Teammates: Inferring and Applying Cognitive State to Enable Novel Human-Autonomy Teaming Capabilities. Doctoral thesis, Georgia Institute of Technology, 2025. https://hdl.handle.net/1853/77880