3D Path Planning for UAVs Based on an Improved DOA
TL;DR
The Improved Dhole Optimization Algorithm is proposed, which enhances the original DOA framework by integrating a logistic-map-based chaotic mapping, a dynamic chaotic perturbation mechanism, and an adaptive stage-division strategy, and significantly outperforms the original DOA in terms of convergence speed and final path optimality.
Abstract
Three-dimensional (3D) path planning for Unmanned Aerial Vehicles (UAVs) presents a challenging multi-objective optimization problem that necessitates a balanced trade-off among path length, flight safety, and trajectory smoothness, especially in complex environments such as mountainous or hilly terrains. Traditional and even many meta-heuristic planning algorithms often suffer from premature convergence and suboptimal solution quality when navigating such intricate 3D spaces. To address these limitations, this paper proposes an Improved Dhole Optimization Algorithm (IDOA) that exhibits fast convergence and strong global optimization capabilities. The IDOA enhances the original DOA framework by integrating a logistic-map-based chaotic mapping, a dynamic chaotic perturbation mechanism, and an adaptive stage-division strategy. The algorithm is designed to address the 3D path planning problem for quadrotor UAVs, supporting typical flight maneuvers including climb/descent, obstacle avoidance, and smooth turning in simulated complex hilly terrain. A multi-objective fitness function incorporating path length, safety, and smoothness is designed, which constrains the optimization to generate collision-free, smooth paths that satisfy the quadrotor UAV’s dynamic maneuver constraints. Convergence curves confirm that IDOA significantly outperforms the original DOA in terms of convergence speed and final path optimality. Detailed experimental results show that compared to the original DOA, IDOA achieves a 6.31% improvement in minimum fitness values, a 9.7% reduction in average path length, and a 45.28% reduction in average path curvature when compared to the baseline DOA. These consistent performance improvements demonstrate that IDOA provides an effective and robust solution for offline pre-flight 3D path planning in complex terrain, offering valuable technical support for autonomous UAV navigation in practical application scenarios such as terrain surveying and disaster search and rescue.