Title Of the Talk: Mapping and Resilience in Multi-robot Systems through Information Manipulation
Speaker: Dr Ragesh Ramachandran
Host Faculty: Dr. Vineeth N Balasubramanian
Date & Time: Wednesday, 2nd June 10:30am
Seminar link: https://iith.webex.com/iith/j.php?MTID=m4a44bc1889287324589fe1ea447f422f
The promise of multi-robot systems lies in their ability to perform tasks that a single robot cannot accomplish by itself or to do so robustly. Recent advances in embedded systems technology have enabled the development of multi-robot systems consisting of large numbers of robots with limited sensing, communication, and computational capabilities. These swarms of robots innately produce a large amount of information through their interaction with the environment. The individual robots in the team may also exchange useful information with each other for improved decision-making. Information and communication are thus two key ingredients for autonomy. In this talk, I will introduce the idea of analyzing and solving problems in multi-robot systems by explicitly viewing them through an information manipulation paradigm. I will focus on two broad research areas in multi-robot systems: mapping using robot teams and resilience in multi-robot systems. For the mapping problem, I will introduce and compare three mapping methods we have developed and studied that manipulate sensing information differently. Following this, I will describe a novel multi-robot resilience framework in a multi-robot system by reconfiguring the system's information flow and leveraging heterogeneity. We will conclude with some directions for future work and a discussion of open problems.
Dr Ragesh Kumar Ramachandran is a postdoctoral scholar in Computer Science at the University of Southern California, working with Professor Gaurav Sukhatme in the USC Robotic Embedded Systems Lab. He completed his Ph.D. in Mechanical Engineering under Dr. Spring Berman's guidance at Arizona State University in 2018. His research is centered around multi-robot systems, sensor networks, application of topology and differential geometry in robotics, and inverse problems.
Wednesday, 2nd June 10:30am