Related Experiment Video
Updated: Jul 16, 2026
10:09
Operation of the Collaborative Composite Manufacturing (CCM) System
Published on: October 1, 2019
A Bi-Level Hybrid Framework for Multi-Target Path Planning of AGV Based on Particle Swarm Optimization and
Tursun Mamat1,2, Zhaolong Liu1,2, Qiuju Yang3
1Engineering Research Center for Intelligent Transportation, School of Transportation and Logistics Engineering, Xinjiang Agricultural University, 311 Nongda East Road, Urumqi 830052, China.
Sensors (Basel, Switzerland)
|July 15, 2026
Summary
This study introduces a novel bi-level framework for Automated Guided Vehicle (AGV) path planning, integrating Particle Swarm Optimization (PSO) and Bidirectional Rapidly Exploring Random Tree (Bi-RRT). The approach enhances planning efficiency and obstacle avoidance in complex logistics settings.
Area of Science:
- Robotics and Automation
- Artificial Intelligence
- Operations Research
Background:
- Multi-target path planning for AGVs is crucial in complex logistics.
- Existing methods struggle to balance planning efficiency, obstacle avoidance, and trajectory smoothness.
Purpose of the Study:
- To propose a novel bi-level collaborative framework for efficient and smooth multi-target AGV path planning.
- To enhance AGV performance in complex and cluttered logistics environments.
Main Methods:
- Integration of Particle Swarm Optimization (PSO) with Bidirectional Rapidly Exploring Random Tree (Bi-RRT).
- Development of a five-dimensional particle encoding for adaptive sampling and parameter optimization.
- Implementation of expansion-failure-driven adaptive sampling, local-density suppression, and directional dispersion.
- Utilizing a greedy heuristic for multi-target scheduling and cubic B-spline interpolation for trajectory smoothing.
Main Results:
- The proposed framework demonstrates improved planning efficiency in complex environments.
- Stable performance is maintained across varying obstacle densities.
- Enhanced search performance in cluttered environments through adaptive sampling mechanisms.
Conclusions:
- The bi-level collaborative framework effectively addresses challenges in multi-target AGV path planning.
- The integration of PSO and Bi-RRT offers a robust solution for logistics automation.
- The framework shows significant potential for real-world applications in complex warehouse environments.