FPGA-Based Parallel Metaheuristic PSO Algorithm and Its Application to Global Path Planning for Autonomous Robot Navigation

Abstract

This paper presents a field-programmable gate array (FPGA)-based parallel metaheuristic particle swarm optimization algorithm (PPSO) and its application to global path planning for autonomous robot navigating in structured environments with obstacles. This PPSO consists of three parallel PSOs along with a communication operator in one FPGA chip. The parallel computing architecture takes advantages of maintaining better population diversity and inhibiting premature convergence in comparison with conventional PSOs. The collision-free discontinuous path generated from the PPSO planner is then smoothed using the cubic B-spline and system-on-a-programmable-chip (SoPC) technology. Experimental results are conducted to show the merit of the proposed FPGA-based PPSO path planner and smoother for global path planning of autonomous mobile robot navigation.