Multi-Agent Cooperative Pursuit-Evasion Control Using Gene Expression Programming

Ni, Yinjie; Gao, Shuhua; Huang, Sunan; Chen, Xiang; Ren, Qinyuan; Lee, Tong Heng

doi:10.1109/iecon48115.2021.9589599

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, we aim to develop MARL approaches for multi-player pursuit-evasion with enhanced exploration for a heterogeneous swarm of UAVs operating in a fully decentralized manner. While many recent studies on multi-player pursuit-evasion consider a single evading target whether in the framework of MARL [9], [26]- [29] or distributed control [30]- [32], our efforts to address the pursuit of multiple superior evaders, specially in MARL framework, highlights the value of this study. In [33], tackling multiple evaders is attempted in a multiagent pursuit based on application of self-organizing feature map and reinforcement learning.…”

Section: Related Workmentioning

confidence: 96%

Multi-Agent Reinforcement Learning for Dynamic Ocean Monitoring by a Swarm of Buoys

Kouzehgar

Meghjani

Bouffanais

2020

Global Oceans 2020: Singapore – U.S. Gulf Coast

View full text Add to dashboard Cite

Multi-agent pursuit-evasion tasks involving intelligent targets are notoriously challenging coordination problems. In this paper, we investigate new ways to learn such coordinated behaviors of unmanned aerial vehicles (UAVs) aimed at keeping track of multiple evasive targets. Within a Multi-Agent Reinforcement Learning (MARL) framework, we specifically propose a variant of the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) method. Our approach addresses multitarget pursuit-evasion scenarios within non-stationary and unknown environments with random obstacles. In addition, given the critical role played by collective exploration in terms of detecting possible targets, we implement heterogeneous roles for the pursuers for enhanced exploratory actions balanced by exploitation (i.e. tracking) of previously identified targets. Our proposed role-based MADDPG algorithm is not only able to track multiple targets, but also is able to explore for possible targets by means of the proposed Voronoi-based rewarding policy. We implemented, tested and validated our approach in a simulation environment prior to deploying a real-world multi-robot system comprising of Crazyflie drones. Our results demonstrate that a multi-agent pursuit team has the ability to learn highly efficient coordinated control policies in terms of target tracking and exploration even when confronted with multiple fast evasive targets in complex environments.

show abstract