Work

Optimized 3D path planning for UAVs using a multi-strategy snow avalanches algorithm

Year: 2025

Type: article

Abstract: Unmanned aerial vehicle (UAV) path planning is critical for autonomous flight operations, yet existing algorithms face challenges in balancing optimization accuracy and computational efficiency. In this paper, we proposed a Multi-Strategy Snow Avalanches Algorithm (MSAA) to address the limitations of the original Snow Avalanches Algorithm (SAA), which suffered from low convergence precision and local optima entrapment. The MSAA integrated three key enhancements: a chaos theory-based initialization method to enhance population diversity, a stochastic central learning mechanism for dynamic exploration–exploitation balance, and an improved sine–cosine operator to prevent premature convergence. Ultimately, the MSAA was successfully applied to the challenge of 3D UAV path planning. By integrating cubic B-spline interpolation for smooth trajectory generation, the proposed method achieved impressive results, with mean path error rates of 0.5% in low-dimensional terrains and 0.4% in high-dimensional environments. Experimental validations demonstrated superior convergence speed and computational efficiency compared to benchmark algorithms, confirming its practical value for 3D UAV navigation in complex scenarios.

Source: Journal of King Saud University - Computer and Information Sciences

DOI: 10.1007/s44443-025-00224-x

Authors: Yulong Xu, Yuanbin Mo

Institution: Guangxi Minzu University

Language: English

Topic: Metaheuristic Optimization Algorithms Research

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,990

Funders: National Natural Science Foundation of China, Natural Science Foundation of Guangxi Province