Bio particle swarm optimization and reinforcement learning algorithm for path planning of automated guided vehicles in dynamic industrial environments

Abstract

Automated guided vehicles play a crucial role in transportation and industrial environments. This paper presents a proposed Bio Particle Swarm Optimization (BPSO) algorithm for global path planning. The BPSO algorithm modifies the equation to update the particles' velocity using the randomly generated angles, which enhances the algorithm's searchability and avoids premature convergence. It is compared with Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Transit Search (TS) algorithms by benchmark functions. It has great performance in unimodal optimization problems, and it gains the best fitness value with fewer iterations and average runtime than other algorithms. The Q-learning method is implemented for local path planning to avoid moving obstacles and combines with the proposed BPSO for the safe operations of automated guided vehicles. The presented BPSO-RL algorithm combines the advantages of the swarm intelligence algorithm and the Q-learning method, which can generate the globally optimal path with fast computational speed and support in dealing with dynamic scenarios. It is validated through computational experiments with moving obstacles and compared with the PSO algorithm for AGV path planning.