Robotics Engineering Colloquium Speaking Series: Nathaniel Dennler

Wednesday, December 9, 2026
12:00 p.m. to 1:00 p.m.
Location
Floor/Room #
UH 520

Optimizing at Deployment-Time from User Interaction

Nathan Dennler

Abstract: For a robot to meaningfully assist people, the robot needs to understand what that person is trying to accomplish and execute the behaviors that help the user achieve that goal. However, it is challenging for everyday users to express their goals and preferences in a way that is conducive to the optimization of robot behavior. For example, users cannot easily articulate an explicit numerical value that describes how good a robot’s behavior is, let alone its gradient with respect to the robot’s actions.

Fortunately, users naturally produce observable behaviors, like gaze, speech, or movement that hint at the user’s underlying goals. Moreover, these behaviors can be intentionally elicited during interaction with the robot. My work develops algorithms that allow robots to probabilistically estimate user goals from such observable behaviors to support robot optimization.

This talk will cover algorithms that address each stage of the optimization problem. First, I will discuss how robots can aggregate common behaviors across many users to understand which goals are worth pursuing, defining the input space of the optimization. Next, I will explain how robots can infer personalized constraints on top of this space by interacting with individual users. Third, I will describe how humans can actively guide robot behaviors during the optimization process at deployment time. To conclude, I will discuss future directions for optimizing robot behavior so that robots can more effectively adapt to the people they assist.

Bio: Nathan is a postdoctoral researcher at the MIT Computer Science & Artificial Intelligence Laboratory working with Prof. Andreea Bobu. Nathan’s research develops algorithms and methods that enable robots to efficiently adapt to users’ preferences. 

Previously, Nathan received a Ph.D. in Computer Science at the University of Southern California, where he was an NSF GRFP Fellow advised by Prof. Maja Matarić and Prof. Stefanos Nikolaidis. Nathan also holds a B.Eng. in Robotics Engineering and a B.S. in Computer Science from Worcester Polytechnic Institute.