ICON Seminar in Control: Prof. Keith LeGrand (Purdue AAE)
| Event Date: | November 4, 2022 |
|---|---|
| Speaker: | Prof. Keith LeGrand |
| Speaker Affiliation: | Purdue University |
| Time: | 2-2:30 pm |
| Location: | HAMP 1252 (in-person)
Zoom: https://purdue-edu.zoom.us/j/99326083199?pwd=TjhqaE1TYkZ2RG1RMkt6S1JZbGk1UT09 |
| Contact Name: | Yu She |
| Contact Email: | yushe@purdue.edu |
| Priority: | No |
| School or Program: | College of Engineering |
| College Calendar: | Show |
Location: HAMP 1252 (in-person) and Zoom (online) https://purdue-edu.zoom.us/j/99326083199?pwd=TjhqaE1TYkZ2RG1RMkt6S1JZbGk1UT09
Agenda: 2:00pm-3:15pm (Seminar + Q&A); 3:15pm-4:00pm (Networking). Snacks and coffee will be provided.
Random Finite Set Information Theoretic Sensor Control for Autonomous Multi-sensor Multi-object Surveillance
Abstract
Through automatic control, intelligent sensors can be manipulated to obtain the most informative measurements about objects in their environment. In object tracking applications, sensor actions are chosen based on the predicted improvement in estimation accuracy, or information gain. Although random finite set (RFS) theory provides a formalism for measuring information gain for multi-object tracking problems, predicting the information gain for unknown future measurements remains computationally challenging. This talk provides a gentle introduction to RFS theory and its application to multi-sensor multi-object tracking and presents new results in RFS information-driven control. The information-driven control policy presented in this work accounts for noisy measurements, missed detections, spurious measurements, object appearance/disappearance, and potentially overlapping sensor fields-of-view. Additionally, this work introduces a novel approach for incorporating negative information, such as the absence of detections, and soft evidence, such as from natural language statements, in multi-sensor multi-object tracking and control problems. The effectiveness of the approach is demonstrated through a multi-sensor ground vehicle tracking problem using real video data from a low Earth orbiting satellite.
Bio
Keith LeGrand is an Assistant Professor of Aeronautics and Astronautics at Purdue University. He received the Ph.D. degree in Aerospace Engineering at Cornell University, where he worked in the Laboratory for Intelligent Systems and Controls (LISC). Prior to that, he was a Senior Member of Technical Staff at Sandia National Laboratories in Albuquerque, New Mexico where he conducted research in inertial navigation, space systems, and multi-object tracking. He received his B.S. and M.S. degrees in Aerospace Engineering from the Missouri University of Science and Technology. He is the recipient of the U.S. DoD National Defense Science and Engineering Graduate (NDSEG) Fellowship (2021) and multiple best paper awards at the International FUSION Conference. His research interests include multi-sensor multi-object tracking; space domain awareness; and information theory.
Seminar Photoes
2022-11-04 14:00:00 2022-11-04 14:30:00 America/Indiana/Indianapolis ICON Seminar in Control: Prof. Keith LeGrand (Purdue AAE) Title: Random Finite Set Information Theoretic Sensor Control for Autonomous Multi-sensor Multi-object Surveillance HAMP 1252 (in-person) Zoom: https://purdue-edu.zoom.us/j/99326083199?pwd=TjhqaE1TYkZ2RG1RMkt6S1JZbGk1UT09