基于改进鱼群算法的牧场巡检机器人路径规划研究

摘要/Abstract

摘要： 针对传统人工鱼群算法（AFSA）在牧场巡检路径规划的过程中易陷入局部最优解、规划的最优路径较长等问题，提出一种改进人工鱼群算法融合遗传算法(GA)得到的遗传鱼群算法（GFSA）。GFSA在AFSA基础上通过优化视野和步长，加快算法在求解过程中的收敛速度和精度；通过设计分段式拥挤度因子、引入遗传算法中的变异操作，避免算法在迭代过程中过早聚集在局部最优解周围。将GFSA搭载在牧场巡检机器人上进行实验验证。结果显示，在消融实验中，GFSA规划的路径长度均低于对比算法，其最优路径长度中位数为23.2m；在多算法对比实验中，与对比算法相比，GFSA的路径最短且转弯幅度小；在不同障碍物率地图的路径规划中，GFSA的最优路径长度初始值、增长斜率均小于对比算法，具有更好的鲁棒性和适应性。

关键词: 遗传算法, 人工鱼群算法, 牧场, 巡检机器人, 路径规划

Abstract: To address the issues of traditional Artificial Fish Swarm Algorithm (AFSA) in pasture inspection path planning, such as easily falling into local optima and resulting in relatively long optimal paths, an improved Artificial Fish Swarm Algorithm integrated with Genetic Algorithm (GA) is proposed, named Genetic Fish Swarm Algorithm (GFSA). GFSA enhances AFSA by optimizing the vision and step length to accelerate convergence speed and accuracy during the solving process. Additionally, it avoids premature convergence around local optima during iterations by designing a segmented crowding factor and incorporating mutation operations from GA. GFSA was implemented on a pasture inspection robot for experimental validation. The results show that in ablation experiments, the path lengths planned by GFSA were consistently shorter than those of the comparison algorithms, with a median optimal path length of 23.2m. In multi-algorithm comparison experiments, GFSA achieved the shortest paths and smaller turning angles compared to the other algorithms. In path planning on maps with different obstacle rates, GFSA's initial value and growth slope of the optimal path length were both lower than those of the comparison algorithms, demonstrating better robustness and adaptability.

Key words: GA , AFSA , ranch, inspection robots , planning

中图分类号:

S951

高金喆, 寇志伟, 许寒琪, 段轲赫, 马佳音. 基于改进鱼群算法的牧场巡检机器人路径规划研究[J]. 中国农机化学报.

Gao Jinzhe, Kou Zhiwei, Xu Hanqi, Duan Kehe, Ma Jiayin. Algorithm design for laser-based ranch inspection robot positioning and mapping[J]. Journal of Chinese Agricultural Mechanization.

参考文献

[1] 陈仪坤,步丹璐.农业信息基础设施建设对涉农企业价值的影响——基于“宽带中国”战略的准自然实验[J].农业技术经济,1-19[2024-05-25].

Chen Y K, Bu D L. Agricultural information infrastructure construction and agricultural enterprises’ values: a quasi-natural experiment based on the “broadband China” strategy[J]. Journal of Agrotechnical Economics, 1-19[2024-05-25].

[2] Ma Y, Feng W, Mao Z, et al. Path planning of UUV based on HQPSO algorithm with considering the navigation error[J]. Ocean Engineering, 2022, 244: 110048.

[3] 王杰,经俊森,陈正伟,等.基于Harris和卡尔曼滤波的农业机器人田间稳像算法[J].农业机械学报,2023,54(01):30-36+53.

Wang J, Jing J S, Chen Z W et al. Field image stabilization algorithm for agricultural robot based on Harris and Kalman filter[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023,54(01):30-36+53.

[4] Yi H, Wang J, Hu Y, et al. Mechanism isomorphism identification based on artificial fish swarm algorithm[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2021, 235(21): 5421-5433.

[5] Merci A, Anthierens C, Thirion-Moreau N, et al. A simulator of underwater glider missions for path planning[J]. Ocean Engineering, 2023, 269: 113514.

[6] [1]常见,任雁.基于改进遗传算法的机器人路径规划[J].组合机床与自动化加工技术,2023,(02):23-27.

Chang J, Ren Y. Robot Path planning based on improved genetic algorithm[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2023,(02):23-27.

[7] 高明,唐洪,等.机器人集群路径规划技术研究现状[J].国防科技大学学报,2021,43(01):127-138.

Gao M, Tang H, et al. Survey of path planning technologies for robots swarm[J]. Journal of National University of Defense Technology, 2021,43(01):127-138.

[8] Tian Q, Wang T, Wang Y, et al. A two-level optimization algorithm for path planning of bionic robotic fish in the three-dimensional environment with ocean currents and moving obstacles[J]. Ocean Engineering, 2022, 266: 112829.

[9] Zhang Y, Chen P, Chen L, et al. A path planning method for the autonomous ship in restricted bridge area based on anisotropic fast marching algorithm[J]. Ocean Engineering, 2023, 269: 113546.

[10] Xue H. A quasi-reflection based SC-PSO for ship path planning with grounding avoidance[J]. Ocean engineering, 2022, 247: 110772.

[11] Yan Z, Zhang J, Zeng J, et al. Three-dimensional path planning for autonomous underwater vehicles based on a whale optimization algorithm[J]. Ocean engineering, 2022, 250: 111070.

[12] Zhang L, Zhang Y, Li Y. Mobile robot path planning based on improved localized particle swarm optimization[J]. IEEE Sensors Journal, 2020, 21(5): 6962-6972.

[13] Zhao L, Wang F, Bai Y. Route planning for autonomous vessels based on improved artificial fish swarm algorithm[J]. Ships and Offshore Structures, 2023, 18(6): 897-906.

[14] Li S, Li W, Wang Z, et al. Research and implementation of parallel artificial fish swarm algorithm based on ternary optical computer[J]. Mobile Networks and Applications, 2022, 27(4): 1397-1407.

[15] 金秀章,于静,刘岳.基于人工鱼群-径向基神经网络的NO_x预测模型[J].动力工程学报,2021,41(07):551-557.

Jin X Z, Yu J, Liu Y. NO_x prediction model based on artificial fish swarm-radical basis function neural network[J]. Journal of Chinese Society of Power Engineering, 2021,41(07):551-557.

[16] 靳荔成,刘一萱,白瑞峰,等.面向校园多机器人协同巡查的路径规划虚拟仿真实验设计[J].实验技术与管理,2023,40(03):93-99.

Jin L C, Liu Y X, Bai R F, et al. Design of virtual simulation experiment of path planning for multi-robot cooperative patrol in campus[J]. Experimental Technology and Management, 2023, 40(3): 93-99.

[17] 毕桂.染色体重组鱼群算法的机器人导航路径规划[J].机械设计与制造,2021(6):197-201.

Bi G. Robot navigation path planning based on chromosome recombination fish swarm algorithm[J]. Machinery Design & Manufacture, 2021(6): 197-201.

[18] Zhao L, Bai Y, Wang F, et al. Path planning for autonomous surface vessels based on improved artificial fish swarm algorithm: a further study[J]. Ships and Offshore Structures, 2023, 18(9): 1325-1337.

[19] Lyridis D V. An improved ant colony optimization algorithm for unmanned surface vehicle local path planning with multi-modality constraints[J]. Ocean Engineering, 2021, 241: 109890.

[20] Xi L, Zhang F. An adaptive artificial-fish-swarm-inspired fuzzy C-means algorithm[J]. Neural Computing and Applications, 2020, 32(22): 16891-16899.