Path Planning for Automated Guided Vehicles Using BPSO and Reinforcement Learning
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)
Want to read the original?
Access the complete publication on the publisher's website