Title: Distributed Heterogeneous Multi-robot Task Allocation in Communication-limited Environments

Date: Thursday, March 9, 2023

Time: 3:00 PM – 5:00PM ET

Location: Teams Meeting (Meeting ID: 254 190 980 836 Passcode: 9QM7Ve )

Shengkangc Chen

Robotics PhD Student

School of Electrical and Computer Engineering

Georgia Institute of Technology

Committee:

Dr. Fumin Zhang (Co-Advisor) – School of Electrical and Computer Engineering, Georgia Institute of Technology

Dr. Ronald C. Arkin (Co-Advisor) – School of Interactive Computing, Georgia Institute of Technology

Dr. Seth A. Hutchinson – School of Interactive Computing, Georgia Institute of Technology

Dr. Mathew C. Gombolay – School of Interactive Computing, Georgia Institute of Technology

Dr. Jason L. Williams –  Robotics and Autonomous Systems Group, CSRIO Data61

Abstract: 

In this proposal, I plan to develop a novel distributed approach to heterogeneous multi-robot task allocation in a communication-limited environment. To achieve this goal, I propose a distributed task allocation algorithm and a game-theoretic framework. The distributed task allocation algorithm aims to achieve a balance between low assignment conflicts and high total task utility. In the game-theoretic framework, I formulate the task allocation problem as a game where each robot is 'individually rational' and tries to select tasks that can maximize its own payoff (task utility) independently. Since each robot makes task selection independently, robots can still perform task allocation when communication is not reliable. I will develop a distributed decision-making algorithm that can reach a pure Nash equilibrium in the multi-robot task allocation game.