Abstract

This talk will focus on our lab’s work to understand how multiple robots can coordinate, cooperate, and collaborate when communication between robots is unreliable and/or unavailable. We will cover problems and results related to task allocation, path and motion planning algorithms, swarm behavior design, and distributed learning across swarms of robots. Applications include solving problems in which communication between robots is challenging, very challenging, and/or nonexistent. A recent result that we are excited to talk about is something we call the “path-based sensor,” a Shannon information theoretic approach to searching for an event causing phenomenon when observations are limited to the granularity of (entire) robot paths; for example, searching for lethal robot-destroying hazards in a communication denied environment.

Bio: Michael Otte is an assistant professor in the Department of Aerospace Engineering at the University of Maryland College Park (MD) and director of the Motion and Teaming Lab. He also holds affiliations with the UMD Department of Computer Science, the Maryland Robotics Center (MRC), the MATRIX Lab, and the Artificial Intelligence Interdisciplinary Institute at Maryland (AIM). He is a Senior member of IEEE and AIAA , Associate Editor of the International Journal of Robotics Research (IJRR), and served as a Co-Chair of the International Workshop on Robot Algorithmic Foundations of Robotics (WAFR’22) and Program Chair of the International Conference on Distributed Autonomous Robotic Systems (DARS’24). Dr. Otte was previously a National Science Foundation Postdoctoral Associate in the U.S. Naval Research Laboratory (NRL), a visiting Scholar at the U.S. Air Force Research Laboratory (AFRL), and a Postdoctoral Associate at the Massachusetts Institute of Technology (MIT). He received his M.S. and Ph.D. from the University of Colorado Boulder (CU) in Computer Science.