Abstract

Mobile robot becomes more significant in human life and industry, whereas navigation of robot in the dynamic environment results a challenging problem and it need to be solved in an efficient way. Path planning gained more attention in recent decades and puts its practical usage in different industries. Path planning for the mobile robot is to determine feasible path to reach target location in workspace. A more challenging problem with mobile robot is solving path planning issue by avoiding obstacles in an optimize way. Various methods are designed to perform path planning mechanism, but it faced complexity in finding the solution to reach the target. Hence, an efficient Mayfly Deer Hunting Optimization (MDHO) algorithm is designed in this research to move the mobile robots to reach target location in the environment using multi-objective function. However, multi-objective function is designed by considering the factors, like path length, path smoothness, and the obstacle avoidance. The path that satisfies the objective constraints is selected as optimal path to reach the target of mobile robot. The proposed model attains minimum path length, maximal path smoothness, and maximum fitness as 1159.0 m, 0.913, and 3.5418 by considering fixed obstacles and multiple targets.

摘要

移动机器人在人类生活和工业中变得越来越重要，而机器人在动态环境中的导航是一个具有挑战性的问题，需要以有效的方式解决。路径规划在近几十年来受到更多关注，并在不同行业中得到实际应用。移动机器人的路径规划就是在工作空间中确定到达目标位置的可行路径。移动机器人的一个更具挑战性的问题是通过以优化的方式避开障碍物来解决路径规划问题。设计了各种方法来执行路径规划机制，但在寻找达到目标的解决方案时面临着复杂性。因此，本研究设计了一种高效的 Mayfly Deer Hunting Optimization (MDHO) 算法，使用多目标函数使移动机器人移动到环境中的目标位置。然而，多目标函数是通过考虑路径长度、路径平滑度和避障等因素设计的。选择满足目标约束的路径作为移动机器人到达目标的最优路径。通过考虑固定障碍物和多个目标，所提出的模型获得最小路径长度、最大路径平滑度和最大适应度为1159.0 m、0.913和3.5418。选择满足目标约束的路径作为移动机器人到达目标的最优路径。通过考虑固定障碍物和多个目标，所提出的模型获得最小路径长度、最大路径平滑度和最大适应度为1159.0 m、0.913和3.5418。选择满足目标约束的路径作为移动机器人到达目标的最优路径。通过考虑固定障碍物和多个目标，所提出的模型获得最小路径长度、最大路径平滑度和最大适应度为1159.0 m、0.913和3.5418。