Automatic driving vehicle planning method and system

Abstract

The embodiment of the invention relates to an automatic driving vehicle planning method and system. The method comprises the following steps that: obtaining a road network topological structure, real-time traffic flow, road quality and vehicle electric quantity; adopting a search algorithm to obtain a first preset quantity of global planning paths; selecting an initial path; according to obstacleinformation and a vehicle state pattern, generating a second preset quantity of alternative paths under a parallel state; evaluating the alternative paths, and selecting the state pattern; according to the prediction operation trajectory of the obstacle and the state pattern, generating a third preset quantity of feasible trajectories in parallel; and evaluating the feasible trajectories to obtainthe driving trajectory of the vehicle. By use of the method, global path planning, local behavior planning and motion planning are blended from a system, and a situation that each module is subjectedto isolated distribution and logical levels are in shortage is avoided; ways of blending from top to bottom and from bottom to top on an information flow are adopted to improve system robustness; anda parallel behavior hypothesis and blending evaluation way is adopted to improve system adaptation.

Description

technical field [0001] The present invention relates to the field of automatic driving, in particular to an automatic driving vehicle planning method and system. Background technique [0002] With the development of artificial intelligence technology and modern manufacturing industry, autonomous driving technology has gradually entered people's daily life, subtly changing the way people travel. Autonomous driving technology has great application prospects in both military and civilian applications. For military use, it can be used not only as an unmanned transportation platform, but also as an unmanned demolition vehicle, unmanned combat platform, unmanned patrol and surveillance vehicle, etc.; in civilian use, it can not only bring convenience to human life, but also reduce The incidence of traffic accidents and the improvement of road traffic efficiency. [0003] Autonomous driving technology can be divided into four modules: perception, positioning, planning and control...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to address the defects of the prior art, to provide an automatic driving vehicle planning method and system, which integrates the global path planning, local behavior planning and motion planning from the system, and avoids the isolated distribution of each module and the lack of logical hierarchy; From the perspective of information flow, top-down and bottom-up integration methods are adopted to improve the robustness of the system; parallel behavior assumptions and fusion evaluation methods are adopted to improve the adaptability of the system to overcome the poor adaptability of the existing serial mode of behavior planning The problem

Images