基于INGO算法的移动机器人自主避障方法

Autonomous obstacle avoidance method of mobile robot based on INGO algorithm

针对移动机器人在避障过程中存在的避障效率差、寻优速度慢、易陷入局部极值等问题,提出一种基于改进北方苍鹰优化(INGO)算法的避障方法。首先,采用Tent混沌映射策略生成初始种群,从而提高初始解集的质量;其次,引入一种基于Levy飞行的搜索策略,以提升搜索效率;同时,为了平衡勘探和开发过程,设计了非线性收敛因子和心形搜索策略,从而降低算法陷入局部极值的概率,提高算法的寻优速度。通过仿真实例,验证算法性能。结果表明:相较对比算法,INGO算法在简单任务场景下路径长度减少3.19%~3.80%、运行时间缩短5.59%~17.68%;在复杂任务场景下,路径长度减少3.91%~4.84%、运行时间缩短14.71%~17.88%。实验验证了INGO算法的可行性,能够有效提升移动机器人的避障能力。

To solve the problems of poor obstacle avoidance efficiency,slow optimizing speed and easy to fall into local extreme value in the process of autonomous obstacle avoidance of mobile robots,an autonomous obstacle avoidance method based on improved northern goshawk optimization(INGO)is proposed.Firstly,Tent chaotic mapping strategy is used to generate the initial population,thereby improving the quality of the initial solution set.Secondly,a search strategy based on Levy flight is introduced to improve the search efficiency.At the same time,in order to balance the exploration and development process,the nonlinear convergence factor and heart⁃shaped search strategy are designed to reduce the probability of the algorithm falling into the local extreme value and improve the optimizing speed of the algorithm.Performance of the algorithm is verified by simulation examples.The results show that INGO decreases the path length by 3.19%~3.80%and the running time by 5.59%~17.68%in simple task scenarios compared with the comparison algorithm.In complex task scenarios,the path length is decreased by 3.91%~4.84%,and the running time is decreased by 14.71%~17.88%.Experiment verifies the feasibility of INGO algorithm,which can effectively improve the obstacle avoidance ability of mobile robots.