Title: Bayesian Learning: Paving to Way to Trustworthy Robots

Date: Friday, May 24, 2024

Time: 11:00AM – 1:00PM EDT

Location: Teams Meeting (Meeting ID: 247 204 698 775 Passcode: CKj5bt)

Yingke Li

Robotics PhD Candidate

School of Electrical and Computer Engineering

Georgia Institute of Technology

Committee:

Dr. Fumin Zhang (Advisor) – School of Electrical and Computer Engineering, Georgia Institute of Technology

Dr. Enlu Zhou – School of Industrial and Systems Engineering, Georgia Institute of Technology

Dr. Matthieu Bloch – School of Electrical and Computer Engineering, Georgia Institute of Technology

Dr. Seth Hutchinson – School of Interactive Computing, Georgia Institute of Technology

Dr. Diyi Yang – Computer Science Department, Stanford University

Abstract: 

Operating under challenging real-world scenarios requires robots to possess a level of “trustworthiness”, enabling them to interact effectively with complex environments and autonomously execute tasks with minimal human intervention. However, factors such as noisy observations, dynamic environmental conditions, ambiguous human instructions, and evolving human-robot team structures render any deterministic approaches fragile over extended real-world operations. This thesis aims to establish the trustworthiness of robots through a probabilistic lens, more specifically, paving the way to trustworthy robots with Bayesian learning. As an embodiment of common sense reasoning, Bayesian learning provides a formal and consistent way to reasoning in the presence of uncertainty, which empowers robots to address a variety of uncertainties encountered when they navigate in unknown, unstructured, and dynamic environments, especially with the presence of human partners. However, while promising and intuitive, integrating Bayesian learning into robotic techniques poses significant challenges. As such, this dissertation centers on seamlessly incorporating Bayesian learning into various robotic techniques by rigorously addressing the associated challenges in inference and action, culminating in a harmonious framework that advances the development of trustworthy robots in real-world scenarios.