【摘要】 矿用无人运输车在现代矿山智能运输系统中应用广泛，但由于矿山环境的复杂性，其路径规划问题面临诸多挑战。为了提高矿用无人运输车在复杂地形中的路径规划效率与精度，提出一种蚁群优化（ACO）与遗传算法（GA）相结合的混合优化算法，并引入Petri网进行多任务调度和资源管理，为矿用无人运输车路径规划提供更高效的调度方案。为了验证算法的有效性，对改进ACO-GA算法与传统算法构建栅格地图进行仿真对比。实验结果表明，改进ACO-GA算法在路径最优性等方面均优于传统算法。更多还原

【Abstract】 Unmanned mining transport vehicles are widely used in modern mine intelligent transportation systems, but due to the complexity of the mine environment, their path planning problems face many challenges. In order to improve the efficiency and accuracy of path planning of mine unmanned transport vehicles in complex terrain, a hybrid optimization algorithm which combines ant colony optimization(ACO) and genetic algorithm(GA) was proposed, and Petri net was introduced for multi-task scheduling and resource management, so as to provide a more efficient scheduling scheme for the path planning of mine unmanned transport vehicles. In order to verify the effectiveness of the algorithm, the improved ACO-GA algorithm was simulated and compared with the traditional algorithm by constructing a raster map. Experimental results show that the improved ACO-GA algorithm is better than the traditional algorithm in terms of path optimality.更多还原