Obstacle Avoidance for Multi-agent Path Planning Based on Vectorized Particle Swarm Optimization

• Published in: Intelligent and Evolutionary Systems Vol. 8; pp. 61 - 74
• Main Authors: Biswas, Sumana, Anavatti, Sreenatha G., Garratt, Matthew A.
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2016; Springer International Publishing
• Series: Proceedings in Adaptation, Learning and Optimization
• Subjects: Artificial intelligence; Multi-agent systems; Obstacle avoidance; Particle swarm optimization; Path planning
• ISBN: 9783319490489; 3319490486
• ISSN: 2363-6084; 2363-6092
• DOI: 10.1007/978-3-319-49049-6_5

This paper deals with an approach to path planning by obstacle avoidance for multi-agent systems. An effective framework is presented based on the Particle Swarm Optimization (PSO) method; an evolutionary computation (EC) technique that uses the dynamics of the swarm to search the solutions for the optimization problems. It describes the path replanning technique and obstacle avoidance for autonomous multi-agent systems. A simultaneous replanning concept is incorporated into the path planning to avoid both static and dynamic obstacles. This proposed algorithm reduces the computational time of the path planning. In the dynamic environment, the numerical results show that the Simultaneous Replanning Vectorized Particle Swarm Optimization (SRVPSO) algorithm is effective and also efficient for multi-agent systems.