A hybrid approach based on multi-agent geosimulation and reinforcement learning to solve a UAV patrolling problem

Authors:
Jimmy Perron;Jimmy Hogan;Bernard Moulin;Jean Berger;Micheline Bélanger
Affiliations:
NSim Technology, Quebec, Canada;NSim Technology, Quebec, Canada;Laval University, Québec, QC, Canada;Decision Support Systems Section, DRDC Valcartier, Quebec, QC, Canada;Decision Support Systems Section, DRDC Valcartier, Quebec, QC, Canada
Venue:
Proceedings of the 40th Conference on Winter Simulation
Year:
2008

Citing 7
Cited 1

Reinforcement Learning

Reinforcement Learning
Distributed Value Functions

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Multi-Agent Patrolling with Reinforcement Learning

AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 3
Theoretical Analysis of the Multi-agent Patrolling Problem

IAT '04 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
A Nonlinear Multi-agent System designed for Swarm Intelligence: the Logistic MAS

SASO '07 Proceedings of the First International Conference on Self-Adaptive and Self-Organizing Systems
Self organized UAV swarm planning optimization for search and destroy using SWARMFARE simulation

Proceedings of the 39th conference on Winter simulation: 40 years! The best is yet to come
Multi-agent patrolling: an empirical analysis of alternative architectures

MABS'02 Proceedings of the 3rd international conference on Multi-agent-based simulation II

Evolving large scale UAV communication system

Proceedings of the 14th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we address a dynamic distributed patrolling problem where a team of autonomous unmanned aerial vehicles (UAVs) patrolling moving targets over a large area must coordinate. We propose a hybrid approach combining multi-agent geosimulation and reinforcement learning enabling a group of agents to find near optimal solutions in realistic geo-referenced virtual environments. We present the COLMAS System which implements the proposed approach and show how a set of UAV can automatically find patrolling patterns in a dynamic environment characterized by unknown obstacles and moving targets. We also comment the value of the approach based on limited computational results.