Title :
A hierarchical conflict resolution method for multi-agent path planning
Author :
Chen, Kuang-Yuan ; Lindsay, Peter A. ; Robinson, Peter J. ; Abbass, Hussein A.
Author_Institution :
ARC Centre for Complex Syst., Univ. of Queensland, Brisbane, QLD
Abstract :
Prioritisation is an important technique for resolving planning conflicts between agents with shared resources, such as robots moving through a shared space. This paper explores the use of genetic-based machine learning to assign priority dynamically, to improve performance of a team of agents without unduly impacting individual agents´ performance. A decoupled heuristic approach is used for flexibility, whereby individual XCS agents learn to optimise their behaviour first, and then a high-level planner agent is introduced and trained to resolve conflicts by assigning priority. The approach is designed for Partially Observable Markov Decision Process (POMDP) environments and demonstrated on a problem in 3D aircraft path planning.
Keywords :
Markov processes; genetic algorithms; learning (artificial intelligence); multi-agent systems; path planning; 3D aircraft path planning; POMDP environment; XCS agents; decoupled heuristic approach; genetic-based machine learning; hierarchical conflict resolution; high-level planner agent; multiagent path planning; partially observable Markov decision process; planning conflicts; Aircraft navigation; Australia; Learning systems; Machine learning; Motion planning; Orbital robotics; Path planning; Robot motion; Space exploration; Stochastic systems; Learning Classifier System; decoupled path planning approach; hierarchical genetic-based machine learning; path planning problem; robot motion planning problem;
Conference_Titel :
Evolutionary Computation, 2009. CEC '09. IEEE Congress on
Conference_Location :
Trondheim
Print_ISBN :
978-1-4244-2958-5
Electronic_ISBN :
978-1-4244-2959-2
DOI :
10.1109/CEC.2009.4983078
