Memory parking method, system and device and computer readable storage medium

Abstract

The invention relates to a memory parking method, device and system and a computer readable storage medium. According to the memory parking method, an original parking space map is generated through avehicle-mounted video system in the first parking process of a driver, and an original parking track is recorded. When the vehicle is driven to the position near the parking space again, parking is prepared; it is determined that the current video image is matched with an original parking space map, then a parking space is searched in the video image, a cruise stage route and a parking route areoptimized by a vehicle-mounted processor based on the original parking track and the searched parking space, and finally the vehicle is controlled to park along the cruise stage route and the parkingroute. According to the embodiment of the invention, the actions of generating the original parking space map, searching the parking space, optimizing the route and the like are respectively completedin different time periods, less computing resources are occupied, parking control can also be quickly and accurately realized by adopting a common vehicle-mounted processor, and the cost is effectively reduced while the success rate of automatic parking is ensured.

Description

technical field [0001] The present application relates to the field of intelligent driving, and in particular to a memory parking method for assisting driving, a memory parking system, a memory parking device and a computer-readable storage medium for implementing the method. Background technique [0002] The memory-type unmanned parking system uses the on-board processor to independently learn the predetermined route that the driver drives during the parking process. When the vehicle enters the site again, the system can automatically recognize the surrounding environment of the memorized road section and calculate the location of the vehicle body. Position and angle, so that after receiving the parking command, it will autonomously drive to the memorized parking route, and finally park in the parking space. Therefore, how to make the system always accurately locate the position of the vehicle in the memory environment is the key to ensure that the vehicle can be safely par...

AI Technical Summary

Problems solved by technology

[0003] The existing memory parking system, in order to improve the success rate of parking, uses GPS, RTK and other technologies based on satellite signals for positioning, but these positioning methods are severely limited by the scene, in complex scenes such as underground closed environments, urban canyons or residential areas, etc. Parking is easy to fail

In a closed environment, existing solutions mainly rely on sensors such as lidar to monitor the distance and angle between the vehicle and surrounding obstacles, but lidar is expensive and cannot always work normally in a closed and complex environment

Secondly, there is also a memory parking solution to install sensors in specific scenes, so that vehicles can ensure safe driving by receiving command signals from intelligent infrastructure, but this solution requires additional construction for specific scenes and is subject to strict scene usage restrictions

Images