With the continuous development of artificial intelligence and big data,unmanned technology has flourished,and it has become particularly important for unmanned technology in the field of ships.Path planning technology can plan a safe and economical path for unmanned ships from the starting point to the target point.This paper proposes a path planning algorithm based on improved RRT*(Rapidly-Exploring Random Tree)for the path planning of unmanned ships entering and leaving the port.The initial path search time,path length,and number of iterations have been greatly improved.This paper divides path planning into three sub-problems,namely environment representation,path search and path optimization.Firstly,the grid method is used to model the environment,and the improved RRT* algorithm is used to search for the path.Finally,the path is optimized by the greedy pruning strategy and the cubic B-spline function interpolation,and the final feasible route is obtained.(1)This paper proposes a modeling method for unmanned ship environment based on the grid method.From the selection of the grid size to the puffing of the obstacles,so as to increase the accuracy of the environmental map representation.(2)For the RRT* algorithm,the expansion randomness is large,and the initial path speed is slow.Firstly,the target point is enlarged,and the target point problem is transformed into the target area problem,and then the target area is expanded according to the position of the target point.After the initial feasible path is calculated,the sampling area is regenerated based on the initial path,and subsequent sampling is performed in the regenerated area.(3)This paper proposes a path planning method based on improved RRT* algorithm.Since the path generated by RRT* is composed of polyline segments,the final path obtained is relatively meandering.In this paper,the greedy pruning strategy is used to remove redundant nodes from polyline segments,and finally the cubic B-spline function interpolation method is used to smooth the path.Through the simulation experiments,it is verified that the improved RRT* algorithm has a great improvement in the initial path search time,path length,and number of iterations compared with the RRT* algorithm,which verifies the feasibility and effectiveness of the algorithm.The path planning algorithm based on improved RRT* proposed in this paper can be used for the path planning of unmanned ship entering and leaving ports. |