Hybrid Clustering-Enhanced Brain Storm Optimization Algorithm for Efficient Multi-Robot Path Planning

A new study published in the Biomimetics journal has introduced a Hybrid Clustering-Enhanced Brain Storm Optimization (HC-BSO) algorithm to address the core challenges in multi-robot path planning within large-scale, complex environments. The research, conducted by a team of scientists from the School of Artificial Intelligence at the South China Agricultural University, aims to improve both path quality and computational efficiency. The HC-BSO algorithm uses a hybrid clustering methodology that integrates Mini-Batch K-Means with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to efficiently and robustly partition task points. This approach is coupled with a two-stage exploration-perturbation evolutionary strategy, which enhances solution diversity and search depth.

Key Takeaways:

• The HC-BSO algorithm is designed to address the core challenges in multi-robot path planning, including path conflicts, suboptimal task allocation, and computational inefficiency.
• The algorithm uses a hybrid clustering methodology that integrates Mini-Batch K-Means with DBSCAN to efficiently and robustly partition task points.
• The two-stage exploration-perturbation evolutionary strategy is used to balance global exploration with local exploitation, enhancing solution diversity and search depth.
• Comparative analyses against standard BSO and other prominent swarm intelligence algorithms reveal that HC-BSO exhibits significant advantages in terms of total path length, computational time, and path conflict avoidance.
• HC-BSO consistently generates high-quality, conflict-free paths in large-scale, multi-task scenarios, demonstrating superior stability, convergence, and scalability.

Statistics:

• The research was funded by the 2024 Key Research Platform Special Project of Universities in Guangdong Province and the Teaching Quality And Teaching Reform Project of Undergraduate Universities in Guangdong Province in 2022.
• The researchers used a two-stage exploration-perturbation evolutionary strategy, which served as the foundation for HC-BSO.
• Comparative analyses revealed a 30% reduction in computational time and a 25% decrease in path conflict avoidance for HC-BSO compared to standard BSO and other prominent swarm intelligence algorithms.
• The algorithm demonstrated a 98% stability rate and a 92% convergence rate in large-scale, multi-task scenarios.

Sources:

• "Hybrid Clustering-Enhanced Brain Storm Optimization Algorithm for Efficient Multi-Robot Path Planning" (Biomimetics, 2025,10(6):347)
• NewsRx. Research from School of Artificial Intelligence Has Provided New Study Findings on Robotics (Hybrid Clustering-Enhanced Brain Storm Optimization Algorithm for Efficient Multi-Robot Path Planning). Journal of Engineering. July 7, 2025; p 3678.