Automatic driving longitudinal unified planning method and system

Abstract

The invention relates to an automatic driving longitudinal unified planning method and system. The automatic driving longitudinal unified planning method comprises the following steps that (1) expected acceleration is planned in real time in the vehicle running process based on a unified environmental model describing information of the environment around a vehicle; and (2) longitudinal movement of the vehicle is controlled according to the expected acceleration and actual acceleration. According to the automatic driving longitudinal unified planning method, local optimal longitudinal planningbased on environmental constraints, performance indexes and driving behaviors can be achieved, and compared with the prior art, the automatic driving longitudinal unified planning method has the advantages that good applicability to different traffic scenes is achieved, and the optimality of final longitudinal movement is ensured.

Description

technical field [0001] The invention belongs to the technical field of automobiles and relates to an automobile automatic driving system, in particular to a longitudinal planning technology of the automobile automatic driving system. Background technique [0002] The development of vehicle intelligence, networking, electrification, and lightweight technology is considered to be an effective way to alleviate traffic congestion, reduce traffic accidents, reduce energy consumption, and control environmental pollution. It is also an important direction for future automobile development. At present, self-driving car technology has received extensive attention from the industry. Many domestic and foreign universities, enterprises and research institutions are carrying out related work in full swing. [0003] Generally, a complete autonomous driving system includes the following key technologies: environment perception, motion planning, control execution, human-machine co-driving,...

AI Technical Summary

Problems solved by technology

At present, there are many researches on vehicle longitudinal motion planning at home and abroad, including methods for full-speed adaptive cruise, speed profile generation methods, car-following model methods, and traditional artificial potential field methods. The above schemes have their own advantages, but it is still difficult to meet the above All requirements, objectively there is an urgent need for further improvement

Images