基于自适应蚁群算法的农用智能机器人路径规划  

Pathplanning of agricultural intelligent robot based on algorithm of self-daptive ant colony

作　　者：李晓静[1,2] 余东满 Li Xiaojing;Yu Dongman(Henan Polytechnic Institute,Nanyang,473009,China;Key Laboratory of Flexible Manufacture,Nanyang,473009,China)

机构地区：[1]河南工业职业技术学院,河南南阳473009 [2]河南省柔性制造重点实验室,河南南阳473009

出　　处：《中国农机化学报》2019年第9期189-193,共5页Journal of Chinese Agricultural Mechanization

摘　　要：针对田间农用智能机器人路径规划问题,结合蚁群算法特点,提出一种基于自适应蚁群算法的路径规划方法,目的是在信息采集、田间巡检、果蔬采摘及作物搬运等操作中,利用所提方法为农用智能机器人搜索出一条距离最短的优化路径,确保其能沿着该优化路径顺利达到指定作物种植区,完成指定工作任务。该方法通过引入自适应调整信息素挥发系数、更改信息素更新机制和限定信息素阈值等策略,对传统蚁群算法进行了优化改进。仿真结果显示,在100 m×100 m作物种植区模型内,改进算法能有效解决农用智能机器人路径规划问题;改进算法规划的最佳路径长度较传统蚁群算法和禁忌搜索算法分别减少3.745 1 m和16.387 6 m;改进算法规划最佳路径所需程序迭代次数较传统蚁群算法和禁忌搜索算法分别减少13代和31代,结果表明,与传统蚁群算法和禁忌搜索算法相比,改进算法具有较强的全局搜索能力和较好的收敛性能。Aiming at the path planning problem of field agricultural intelligent robots, combined with the characteristics of ant colony algorithm, a path planning method based on adaptive ant colony algorithm is proposed. In information acquisition, field inspection, picking fruit and vegetable and crop handling, the proposed method should be utilized to seek an optimized path, by which the shortcut can be selected for agricultural intelligent robot and ensure device could reach the designated spot successfully to execute the specified tasks. The method herein has optimized and improved the traditional ant colony algorithm with some strategies, which contained self-adaptive adjustment of pheromone volatilization coefficient, change of pheromone update mechanism, and limit of pheromone threshold. The simulation results show, in the model of 100 m×100 m crop planting area, the improved algorithm can effectively solve the path planning problem of agricultural intelligent robots;compared with the traditional ant colony algorithm and the tabu search algorithm, the optimal path length, which is obtained by improved ant colony algorithm, has a reduction of 3.745 1 m and 16.387 6 m, respectively. Compared with the traditional ant colony algorithm and the tabu search algorithm, the number of iterations for improved ant colony algorithm is reduced by 13 generations and 31 generations. The results showed that compared with the traditional ant colony algorithm and the tabu search algorithm, the improved ant colony algorithm has better strong global search capability and good convergence performance.

关 键 词：农用 智能机器人 自适应蚁群算法 路径规划 

分 类 号：S126[农业科学—农业基础科学]