Bio particle swarm optimization and reinforcement learning algorithm for path planning of automated guided vehicles in dynamic industrial environments
2024

Path Planning for Automated Guided Vehicles Using BPSO and Reinforcement Learning

publication 15 minutes Evidence: high

Author Information

Author(s): Lin Shiwei, Wang Jianguo, Huang Bomin, Kong Xiaoying, Yang Hongwu

Primary Institution: Jimei University

Hypothesis

The proposed Bio Particle Swarm Optimization (BPSO) algorithm can enhance path planning for automated guided vehicles in dynamic environments.

Conclusion

The BPSO-RL algorithm effectively generates optimal paths for automated guided vehicles while avoiding moving obstacles.

Supporting Evidence

  • The BPSO algorithm outperformed traditional algorithms in terms of iterations and runtime.
  • The integration of Q-learning improved the ability to navigate around moving obstacles.
  • The proposed method showed significant improvements in path planning efficiency.

Takeaway

This study shows how a special algorithm can help robots find the best paths while avoiding obstacles, making them safer and faster.

Methodology

The study uses a combination of Bio Particle Swarm Optimization for global path planning and Q-learning for local path planning.

Limitations

The algorithm may face latency issues in large-scale environments and the Q-learning method does not guarantee complete path generation.

Digital Object Identifier (DOI)

10.1038/s41598-024-84821-2

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication