Unstructured road vehicle path planning method

Abstract

The invention discloses an unstructured road vehicle path planning method which comprises the following steps: 1, inputting a map containing obstacles and road boundaries, and setting an initial configuration Ns, a target configuration Ng and a target area Ag; 2, setting that the initial open set only comprises an initial configuration Ns; 3, selecting a node with the minimum cost from the open set; 4, judging whether the node Ni exists in the open set or not; 5, judging whether the node Ni searches the target area Ag or not; 6, generating a parking path accurately reaching the target configuration by adopting a linear-arc-linear parking model; 7, judging whether each parking path generated in the step 6 collides with an obstacle or not; and 8, path backtracking. According to the unstructured road vehicle path planning method provided by the invention, the vehicle path can be effectively planned by setting the steps 1 to 8.

Description

Technical field [0001] The invention relates to the field of automatic driving, in particular to an unstructured road vehicle path planning method. Background technique [0002] In recent years, with the development of artificial intelligence technology and the continuous progress of the automobile industry, intelligent vehicle technology has become a hot spot in the academic and industrial circles. Path planning is one of the research focuses of car driverless technology. Its task is to plan a safe and drivable path from the starting point to the target point based on the real-time environmental information received by the environmental perception module and the static environmental information provided by the digital map. . At present, the path planning technologies for smart vehicles can be classified as follows: graph search-based methods, sampling-based methods, interpolation curve-based methods, and numerical optimization-based methods. Each method has its own advantages a...

AI Technical Summary

Problems solved by technology

[0004] Although the improvement methods proposed above for the hybrid A* algorithm can improve the search efficiency of the route and the applicability of the planned route on the vehicle model to a certain extent, as a typical representative of the graph search algorithm, it still has inherent problems. The disadvantage is that the searched path can only reach the vicinity of the target configuration and cannot always accurately reach the specified target position and direction

Secondly, in order to ensure the shortest distance of the search path, the generated paths are often close to obstacles or the edge of the road, without considering the smoothness of the path

Images