Automatic parking method based on hierarchical planning and auxiliary system

Abstract

The invention relates to an automatic parking method based on hierarchical planning. Sensing modules arranged around a vehicle obtain information about obstacles in an ambient environment; a parking space size and a parking space type as well as obstacle existence in the parking space are deduced; when the parking space size meets the need and no object exists in the parking space, initial planning based on numerical optimization is carried out; when the initial planning does not meet the parking need, A* search planning and secondary value optimization planning are carried out based on current vehicle pose and parking space information and environmental obstacle information; and after successful planning, a trajectory control point is sent to a vehicle-mounted controller and the vehicle-mounted controller controls a vehicle steering wheel, an accelerator pedal and a brake pedal, so that the vehicle is parked in the target parking space. In addition, the invention also relates to an auxiliary automatic parking system comprising a sensing module, an HMI display module, a path planning module, and a vehicle path tracking module. Compared with the prior art, the automatic parking method and the auxiliary system have advantages of strong environmental adaptability and accurate trajectory calculation.

Description

technical field [0001] The invention relates to an automatic parking assistant system for an intelligent car, in particular to an automatic parking method and an assistant system based on layered planning. Background technique [0002] Parking is never an easy task for a driver. Due to the limited viewing angle of the driver in the cockpit, it is impossible to intuitively control the surrounding conditions of the rear and side of the car body. During the parking process, difficult operations such as backing up and turning are often required, and bumps may occur if you are not careful. , causing property damage and even safety accidents. And along with the rising day by day of urban land price, urban parking spaces are also increasingly narrow, for drivers, manual parking is more difficult than before. If parking is not good enough, it may disrupt the normal use of public parking resources and may even cause traffic jams. In addition, inexperienced drivers may be reluctant...

AI Technical Summary

Problems solved by technology

Usually each geometric operation method is only suitable for a certain type or type of environment, and the adaptability is poor

The search-based A* algorithm is very suitable for unmanned vehicle path planning on unstructured roads, and has its unique algorithm advantages in parking conditions. The path planning method for unmanned vehicles is more likely to fail in search, and requires high-precision discretization of the surrounding environment map, which greatly affects the real-time performance of the algorithm, and is not applicable in the parking environment

Images