Multi-Objective Path Planning and Energy Efficiency Optimization Methods for Industrial Robot Collaborative Systems

Abstract

This paper reviews multi-objective path planning and energy efficiency methods for collaborative industrial robots, examining algorithms like NSGA-II, NSGA-III, ant colony optimization, and particle swarm optimization. It discusses mathematical models, algorithm pseudocode, and performance evaluations. Hybrid strategies outperform others, with ant colony optimization reducing energy use by 21.6% and achieving conflict-free paths. Dynamic factors like payload and joint velocities affect system efficiency. Results show trade-offs: aggressive time optimization may increase energy by 35%, while moderate improvements need only 8-12% more time. The study identifies gaps in real-time adaptability, scalability for large multi-robot systems, human-robot collaboration, and uncertainty handling. Future work should develop edge-friendly algorithms, distributed planning, robust conflict resolution, and energy-efficient scheduling for Industry 4.0 and 5.0.