Global path planning method and device

Abstract

The invention provides a global path planning method comprising steps of: obtaining a plurality of sampling points including a start point and an end point and selecting a vertex from the sampling points; when the expected total cost of the optimal point in a vertex queue is less than the expected total cost of the optimal side in a side queue, expanding the optimal point until the expected totalcost of the optimal point in the expanded vertex queue is not less than the expected total cost of the optimal edge in the side queue; determining a communicating path from the start point to the endpoint; calculating the paid cost of the communicating path and using the same as the long axis of an ellipse; using the distance between the start point and the end point as the focal length of the ellipse; determining a short axis according to the long axis and the focal length; determining a search space according to the long axis, the focal length and the short axis; calculating the positionalparameter of the search space; performing position transformation on the search space based on the positional parameter; re-acquiring the sampling points in the search space subjected to the positiontransformation, and iteratively obtaining a target path in the target search space. Therefore, the method increases the calculation speed and satisfies the kinematic constraints.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a global path planning method and device. Background technique [0002] With the development of artificial intelligence technology, autonomous driving technology has become a new direction for the development of the automobile industry. Self-driving vehicles can improve the safety of the traffic environment, make full use of traffic resources, and reduce emissions. The development of self-driving vehicles will fully drive the development of social productivity. [0003] Existing global path planning algorithms are generally divided into two categories: resolution-complete algorithms and probability-complete algorithms. [0004] The resolution-complete algorithm discretizes the state space, and performs path search on the basis of the discrete processing results. If there is a solution in the state space, in general, the resolution-complete method can search for a relati...

AI Technical Summary

Problems solved by technology

[0010] The purpose of the embodiment of the present invention is to provide a global path planning method and device to solve the problems existing in the existing calculation

Images