【摘要】 为解决传统蚁群算法收敛速度慢，产生避障路径结果不理想等情况，提出一种静态障碍物环境下的新型贪婪改进蚁群算法。建立算法模型，配置算法参数组合，利用贪婪算法的思想，改变蚁群算法的路径选择方式，使算法拥有极快的收敛速度；改进信息素更新规则，使其随迭代次数进行动态更新，避免算法陷入早熟；改进启发式判断法则。实验结果表明，改进算法在不同复杂程度的环境中可较快获得最优路径，对比其它算法具有更好的性能，验证了算法的可行性。更多还原

【Abstract】 To solve the problems of slow convergence and undesirable obstacle avoidance results of ant colony algorithm in path planning, an improved ant colony optimization algorithm in static environment was proposed. The algorithm model was established based on greedy algorithm and the parameters were experimentally configured. The ant colony algorithm path selection method was changed and algorithm convergence speed was greatly accelerated. The rules of updating pheromone were improved which were dynamically updated with the number of iterations, and algorithms were avoided being brought into premature. The heuristic decision rule was changed. Experimental results show that the optimal path of improved ant colony algorithm is obtained faster in environments of different complexity. It has better performance compared with other algorithms, and the feasibility of the algorithm is verified.更多还原