Intelligent decision-making and local trajectory planning method for autonomous vehicle and decision-making system thereof

Abstract

The invention provides an intelligent decision-making and local trajectory planning method for an autonomous vehicle and a decision-making system thereof. The method comprises the following steps: step 1, sampling a given vehicle current position and a given target position point according to road information; step 2, simplifying trajectory calculation through a Frenet coordinate system, interpolating a path corresponding to a future traversal trajectory of the vehicle by using a polynomial, and solving a trajectory set through an initial state and a target state of the vehicle; step 3, carrying out cost evaluation on the track set, performing sorting according to a minimum principle, and sequentially checking whether constraint conditions are met or not according to a sorting result until an optimal track meeting the constraint conditions at the same time is determined; and step 4, after the optimal track is obtained, issuing a driving command for vehicle motion control. According to the method, the complex nonlinear trajectory planning problem is simplified, the trajectory planning difficulty is reduced, a smooth and smooth trajectory is planned, and the vehicle can run more stably.

Description

technical field [0001] The invention relates to an intelligent decision-making and local trajectory planning method and a decision-making system for an automatic driving vehicle. Background technique [0002] With the continuous development of random technology, many well-known companies at home and abroad have invested a large number of high-tech personnel and technologies to develop high-level intelligent driving technology. As one of the core modules of vehicle automatic driving, decision-making system and trajectory planning algorithm have attracted more and more attention from researchers. Usually, the decision-making system of the vehicle is mainly based on the sensors to perceive the environmental information around the vehicle, such as dynamic obstacles, static obstacles, vehicle position, vehicle speed, lane boundary information, etc. Based on these information, the system first plans a safe, reasonable and feasible driving trajectory, and sends the trajectory info...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an intelligent decision-making and local trajectory planning method for an automatic driving vehicle, so as to solve the problems in the prior art that the trajectory planning in a complex environment is complicated and difficult to implement, the uncontrollability is high, the calculation amount is large, and the time-consuming is long technical issues

Images