Abstract
Cooperative multi-agent decision-making is a ubiquitous problem with many real-world applications. In many practical applications, it is desirable to design a multi-agent team with a heterogeneous composition where the agents can have different capabilities and levels of risk tolerance to address diverse requirements. While heterogeneity in multi-agent teams offers benefits, new challenges arise including how to find optimal heterogeneous team compositions and how to dynamically distribute tasks among agents in complex operations. In this work, we develop an artificial intelligence framework for multi-agent heterogeneous teams to dynamically learn task distributions among agents through reinforcement learning. The framework extends Decentralized Partially Observable Markov Decision Processes (Dec-POMDP) to be compatible to model various types of heterogeneity. We demonstrate our approach with a benchmark problem on a disaster relief scenario. The effect of heterogeneity and risk aversion in agent capabilities and decision-making strategies on the performance of multi-agent teams in uncertain environments is analyzed. Results show that a well-designed heterogeneous team outperforms its homogeneous counterpart and possesses higher adaptivity in uncertain environments.
Highlights
R ECENT developments in autonomy offer opportunities that might lead to a paradigm shift in several domains
We developed an artificial intelligence framework for multi-agent heterogeneous teams to dynamically learn task distribution and maximize the performance in complex operations through reinforcement learning
The proposed framework HT Dec-POMDP is compatible to model various sources of heterogeneity within a team, captures aspects of intelligence that produce collaborative teaming, and provides the opportunity to quantitatively investigate the effects of heterogeneity and risk aversion on task allocation in multi-agent systems
Summary
R ECENT developments in autonomy offer opportunities that might lead to a paradigm shift in several domains. A multi-agent system design is beneficial in many aspects, when a system is composed of multiple entities that are distributed functionally or spatially. Collaboration enables the agents to work as a team and complete activities that they are not able to accomplish individually. Instead of agents being centrally controlled, a decentralized multi-agent team can improve performance, robustness, and scalability by planning and performing actions in parallel. Date of publication July 14, 2021; date of current version July 28, 2021. This work was supported through the Automotive Research Center, University of Michigan, Ann Arbor, MI, USA. Distribution A: Approved for public release; distribution unlimited. This letter was recommended for publication by Associate Editor P. Vincze upon evaluation of the reviewers’ comments. (Corresponding author: Haochen Wu.)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
