| Path planning is the key technology for AGVs to achieve autonomous navigation.Path planning in the actual application of the environment is usually unknown or partially known,a single path planning algorithm can not cope with a variety of environments,planning a more ideal path.In this regard,aiming at the indoor complex environment where the overall global environment is known but temporary obstacles may occur at any time,this paper proposes a hybrid path planning algorithm that combines global path planning and local path planning.The main research contents are as follows:Through the comparative analysis of several commonly used environmental modeling algorithms,a simple,efficient,and easy-to-implement raster method is selected as the environmental modeling algorithm for this paper.The appropriate grid cell size is obtained by using the knowledge of plane geometry,and the expansion treatment of irregular obstacles is carried out,which improves the operation efficiency of the whole algorithm,further optimizes the environmental modeling algorithm,and provides a foundation for the implementation of path planning in the later chapters.The principle and defects of the global path planning JPS algorithm are studied,and the Floyd algorithm is used to improve the JPS algorithm,which solves the problems of too many turning points and unsmooth paths in the traditional algorithm.The planned path is more suitable for the actual motion law of the AGV.For the temporary obstacles that appear during the driving of AGV,the artificial potential field method is used to avoid local obstacles.The obstacle trap problem existing in the traditional artificial potential field method is solved by chaining the obstacles in the road boundary and the obstacles in the dense obstacle area;by introducing the distance factor between the AGV and the target point in the repulsive potential field function,the solution The target unreachable problem existing in the traditional artificial potential field method is solved;the method of adding virtual obstacles at suitable positions is adopted to solve the local minimum problem in the traditional artificial potential field method,so that the AGV can successfully avoid the temporary obstacles.reach the target point.For the indoor environment where the overall global environment of AGV in practical applications is known but temporary obstacles may appear at any time,a new hybrid path planning algorithm is proposed.The grid method is used to establish an environmental map model,the improved JPS algorithm is used for global path planning,and an optimal initial path is obtained.At the same time,the on-board sensors are used to continue scanning the surrounding environment information,and the improved artificial potential field method is used to avoid local obstacles and complete the avoidance.After the obstacle,return to the initial optimal path and continue to drive towards the target point.Build an AGV platform,configure ROS and the host computer environment,and conduct AGV hybrid path planning experiments in an indoor environment to verify the feasibility of the improved algorithm. |
