基于改进蝙蝠算法和三次样条插值的机器人路径规划

为更好地解决移动机器人路径规划问题, 改进蝙蝠算法的寻优性能, 拓展其应用领域, 提出了一种具有反向学习和正切随机探索机制的蝙蝠算法. 在全局搜索阶段的位置更新中引入动态扰动系数, 提高算法全局搜索能力; 在局部搜索阶段, 融入正切随机探索机制, 增强算法局部寻优的策略性, 避免算法陷入局部极值. 同时, 加入反向学习选择策略, 进一步平衡蝙蝠种群多样性和算法局部开采能力, 提高算法的收敛精度. 然后, 把改进算法与三次样条插值方法相结合去求解机器人全局路径规划问题, 定义了基于路径结点的编码方式, 构造了绕避障碍求解最短路径的方法和适应度函数. 最后, 在简单和复杂障碍环境下分别对单机器人和多机器人系统进行了路径规划对比实验. 实验结果表明, 改进后算法无论在最优解还是平均解方面都要优于其他几种对比算法, 对于求解机器人全局路径规划问题具有较好的可行性和有效性.

Robot Path Planning Based on Improved Bat Algorithm and Cubic Spline Interpolation

In order to better solve the problem of mobile robot path planning, improve the optimization performance of bat algorithm and expand its application field, a bat algorithm with reverse learning and tangent random exploration mechanism is proposed. The dynamic perturbation coefficient is introduced into the position update in the global search stage to improve the global search ability of the algorithm. In the local search phase, the tangent random exploration mechanism is incorporated to enhance the strategy of local optimization and avoid the algorithm falling into local extremum. At the same time, the reverse learning selection strategy is added to further balance the diversity of bat population and local mining ability of the algorithm, and improve the convergence accuracy of the algorithm. Then, the improved algorithm and cubic spline interpolation method are combined to solve the robot global path planning problem, the coding method based on path node is defined, the method and the fitness function for solving the shortest path without collision with obstacles are constructed. Finally, the path planning experiments of single robot and multi-robot system are carried out in simple and complex obstacle environment. The experimental results show that the improved algorithm is superior to other comparison algorithms in terms of the optimal solution and the average solution, which is feasible and effective for solving the robot global path planning problem.