Faculty Lecture Series:
Minimalist Multi-Agent Filtering and Guidance
| Date: | March 06, 2013 |
|---|---|
| Time: | 2:00 pm |
| Room: | ECS 141 |
| Speaker: | Leonardo Bobadilla Department of Computer Science University of Illinois at Urbana-Champaign |
| Description: | This talk presents methods for solving fundamental robotics tasks such as navigation, patrolling, coverage, and tracking without system identification, geometric map building or precise state estimation. Instead, we follow a minimalist approach that takes advantage of the wild motions of bodies in their environment. Bodies move within regions connected by gates that enforce specific flows or provide simple sensor feedback. This methodology leads to robust, low-cost systems that use efficient algorithms. The approach is demonstrated in several experimental setups: 1) Flow manipulation of simple mechanical devices; 2) Patrolling, disentanglement, and navigation of inexpensive mobile robots; and 3) Low-cost platform for tracking and counting mobile bodies. |
| Biography: | Leonardo Bobadilla received the B.E. degree in Computer Engineering in 2005 and the M.Sc. degree in Statistics in 2008 both from the National University of Colombia. He is currently working towards the Ph.D. degree at the Department of Computer Science, University of Illinois at Urbana-Champaign (UIUC). His research interests include Robotics, Artificial Intelligence, and Cyber-Physical Systems. In particular, he is interested in the design and deployment of inexpensive systems for solving common robotics tasks such as navigation, patrolling, and tracking. He has received several awards including an Illinois Student Undergraduate Research (ISUR) Graduate Mentor Award 2012-2013 and the Top 10 Computer Engineering in Colombia (ECAES) Award. |
| Image: |  |
