Title: Multi-Robot Filtering and Smoothing with High-Dimensional Data

Date: Wednesday, February 7th, 2024

Time: 9:00am-11:00am EST

Location: Virtual

Zoom: https://gatech.zoom.us/j/95706025974

Tony Lin

Robotics Ph.D. Student

School of Electrical and Computer Engineering

Georgia Institute of Technology

Committee:

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

Dr. Samuel Coogan (Co-Advisor) – School of Electrical and Computer Engineering, School of Civil and Environmental Engineering, Georgia Tech

Dr. Seth Hutchinson – School of Interactive Computing, Georgia Tech

Dr. Ye Zhao – School of Mechanical Engineering, Georgia Tech

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

Abstract:

Multi-robot state estimation is a difficult and fundamental problem that is a requirement for realizing higher-level autonomous functionality such as navigation and control. Such estimation strategies benefit from communication and inter-robot perception in order to share or reduce uncertainty amongst team members. However, distributed methods are difficult to employ with multi-hypothesis methods (particle filters) and with high-dimensional information (image streams) from which a noise model may not be known. This dissertation focuses on developing distributed filtering and smoothing strategies for multi-hypothesis methods that can incorporate high-dimensional sensing measurements in order to estimate the pose and image sequences collected by a team of robots.