Intelligent vehicle planning control method based on reinforcement learning and model prediction

Abstract

The invention discloses an intelligent vehicle planning control method based on reinforcement learning and model prediction. Comprising the following steps: acquiring and calculating road boundary information and obstacle information under a vehicle body coordinate system through a vehicle-mounted laser radar sensor; acquiring and calculating by using a vehicle-mounted GPS sensor to obtain a global reference road point under a vehicle body coordinate system; building a virtual scene where the intelligent vehicle is located; under the virtual scene of the intelligent vehicle, based on the road boundary information, the obstacle information and the global reference road point under the vehicle body coordinate system, a path generation module is used for carrying out path planning on the intelligent vehicle, and a planned path of the intelligent vehicle is obtained; and the tracking control module is used for tracking the planning path of the intelligent vehicle, so that planning control of the intelligent vehicle is realized. Network training of a planning part is improved, the path planning effect of the intelligent vehicle when positioning is not accurate is ensured, and the stability and comfort of vehicle body movement are improved.

Description

technical field [0001] The invention belongs to a smart car planning control method in the field of smart car automatic driving, and specifically relates to a smart car planning control method based on reinforcement learning and model prediction in a weak GPS environment. Background technique [0002] With the development of the economy and the improvement of the technical level of the automobile industry in recent years, the number of automobiles has continued to increase, leading to the aggravation of traffic accidents, traffic congestion, exhaust emissions, driver drowsiness and other problems. Unmanned vehicles have the advantages of energy saving, environmental protection, comfort and high efficiency. They are an important trend in the future development of automobiles and are highly valued by countries all over the world. [0003] Path planning and tracking control are key technologies for autonomous driving. For the path planning module, its planning effect is heavil...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem of inaccurate positioning of smart cars in the background technology, the present invention proposes a smart car planning and control method based on reinforcement learning and model prediction, and improves the existing planning and control algorithms to improve the smart car's Stability and comfort when positioning is imprecise

Images