Title: Methods and Models for Robots to Support Variable Human Task Performance

Date: Wednesday, Jun 10th, 2026

Time: 2:00 - 4:00 PM EDT

Location: Klaus 2456 (Classroom Wing)

Virtual Link: https://gatech.zoom.us/j/97929362994

Manisha Natarajan

Robotics PhD Student

School of Interactive Computing

Georgia Institute of Technology

Committee:

Dr. Matthew Gombolay (Advisor) - School of Interactive Computing, Georgia Institute of Technology

Dr. Sonia Chernova - School of Interactive Computing, Georgia Institute of Technology

Dr. Karen Feigh- School of Aerospace Engineering, Georgia Institute of Technology

Dr. Henny Admoni - The Robotics Institute, Carnegie Mellon University

Dr. Laurel Riek - Department of Computer Science and Engineering, University of California San Diego  

Abstract:

Robots are increasingly deployed in high-stakes collaborative settings where success depends not only on what a robot can do but on how well it can work with people. Human-robot teams hold tremendous potential, yet team performance often degrades due to miscalibrated trust, errors in judgment, and failures in mutual understanding. This dissertation argues that effective robot teammates must model human variability: what people know, how they act, when they trust, and which strategies they pursue. I further argue that the value of such modeling is not uniform but is governed by the structure of the collaborative task itself. 

To support this claim, I present five contributions that span the problem of inferring and adapting to humans, from predicting agent motion under partial observability, to tracking how user capabilities evolve, and deciding when and how a robot should intervene or offer support. These contributions examine robotic teammates across a spectrum of collaborative roles: as passive observers, as partners with explicit divisions of labor, as reactive collaborators that intervene dynamically, and as mutual collaborators engaged in joint decision-making. Collectively, my work contributes novel algorithms and empirical insights for designing intelligent, adaptive robot teammates that can support appropriate reliance, improve coordination, and enhance team performance.