Multi-Robot Task Allocation Games in Dynamically Changing Environments with Application to Trash Collection

Overview

Abstract

In this talk, we will discuss a multi-robot task allocation problem where our main objective is to develop a distributed algorithm that allows a large team of robots to optimally assign tasks. Applications of multi-robot task allocation can be found in many engineering areas such as fleet management, environmental surveillance, resource retrieval, etc.  The main technical challenge in our problem stems from the fact that the environment where robots are performing their assigned tasks is dynamically changing. Therefore the task allocation algorithm should enable the robots to learn and self-organize to attain the optimal task allocation in such environment. 

We explain how a game theory model can be applied in designing a task allocation algorithm, which defines how the robots select tasks to perform and how they repeatedly revise their task selections in response to changes in the environment. We also describe how we can benefit from tools in feedback control theory in establishing performance guarantees of the algorithm. We apply and implement the task allocation algorithm in a multi-robot trash collection application. Using physics simulations, we design experiments and demonstrate the performance of our algorithm such as its responsiveness to changing environments and resilience to failure of individual robots.

Brief Biography

Shinkyu Park is an assistant professor of Electrical and Computer Engineering. Prior to joining KAUST, he was Associate Research Scholar at Princeton University engaged in cross-departmental robotics projects. He received the Ph.D. degree in electrical engineering from the University of Maryland College Park in 2015. Later he held Postdoctoral Researcher positions at the National Geographic Society (2016) and Massachusetts Institute of Technology (2016-2019). Park’s research focuses on the design and control of multi-robot systems. His past research projects include designing animal-borne sensor networks to monitor wild animal groups in their natural habitats. He also created a fleet of urban autonomous surface vessels capable of transporting people, providing deliveries, and trash removal services through urban canal networks. His current research interests are in robotics, multi-robot control/coordination, feedback control theory, and game theory.