Opposition-Based Learning Equilibrium Optimizer with Application in Mobile Robot Path Planning

The objective of mobile robot path planning (MRPP) is to devise the shortest obstacle-free path for autonomous mobile robots based on a given terrain. Numerous MRPP methods have been extensively researched. This paper presents a novel approach called Opposition-based Learning Equilibrium Optimizer (OEO) for generating smooth paths for mobile robots. The fundamental idea behind OEO is to introduce an opposition-based learning mechanism while maintaining the overall framework of the basic EO algorithm. This modification alleviates the susceptibility of the basic EO algorithm to local optima. The OEO algorithm is employed to provide smooth paths for autonomous mobile robots, and the results are compared with several classical metaheuristic algorithms. Comparative analysis across different environments demonstrates that the proposed OEO-based path planning method consistently yields the shortest and most collision-free paths with superior stability.