218 / 2024-03-13 14:41:42

Adaptive Hybrid A* Based on Two-Layer Dichotomy for Path Planning of Unmanned Mining Trucks in Open-pit Mines

path planning,unmanned mining trucks,open-pit mines,dichotomy,Hybrid A*

4、智能化装备技术 > 1、智能矿山装备技术

Planning a global reference path under final pose constraints is necessary for unmanned mining trucks to ensure the seamless execution of the loading process. However, irregular mountain shapes in large-scale mining areas lead to a substantial increase in the complexity of determining appropriate node expansion parameters of path planning. Furthermore, conventional methods which utilize fixed parameters in node expansion exhibit a dramatic rise in path length and computation time due to diverse obstacle distribution in open-pit mines. To address this challenge, we propose a novel Adaptive Hybrid A* based on Two-Layer Dichotomy(2D-AHA*) which effectively determines near-optimal parameters in the node expansion process. Firstly, we employ a clustering method on the original grid map to generate convex polygonal obstacles, constructing a new grid map for obstacle detection and thus reducing unnecessary node searches caused by U-shape obstacles. Subsequently, a two-stage dichotomy process is proposed to optimize steering angle and step length respectively, which yields near-optimal successor nodes and accelerates the node expansion process. To evaluate the effectiveness and computational efficiency of the proposed method, we conduct field experiments at an open-pit mine. The results demonstrate that our proposed method outperforms other conventional methods in terms of path length and computation time.