A method and system for detecting a drivable area of ​​a vehicle, and an automatic driving vehicle using the system

Abstract

The present application discloses a vehicle drivable area detection method, an automatic driving assistance system and an automatic driving vehicle. The method includes: using a neural network to process image data acquired by a camera device to obtain a first probability distribution of obstacles; Obtain the second probability distribution of the obstacle according to the echo time and echo width of the radar echo signal; obtain the drivable area of ​​the vehicle represented by probability according to the first probability distribution of the obstacle and the second probability distribution of the obstacle , the probability represents the probability that the vehicle is impassable. The automatic driving assistance system includes a camera, at least one radar, and a processor, and the system is configured to implement the technical solution of the method. The automatic driving vehicle includes the above-mentioned automatic driving assistance system. The method of the present application fuses the two sensors of the camera device and the radar, and fuses the obstacle distribution information obtained based on the two sensors, and expresses the drivable area of ​​the vehicle in the form of probability after fusion. Therefore, the obstacle information around the vehicle can be obtained comprehensively, and the detection blind spot caused by the blind spot of the camera device or the detection range of the radar can be avoided.

Description

technical field [0001] The present application relates to the field of automatic driving, in particular, to a detection method and system for a vehicle drivable area and an automatic driving vehicle using the system. Background technique [0002] With the rapid development of 5G communication and Internet of Vehicles technology, autonomous driving technology has become a research hotspot. The core technologies in the field of autonomous driving include intelligent environment perception, automatic navigation and positioning, driving behavior decision-making, and intelligent path planning control. In automatic driving technology, the detection of the vehicle's drivable area is the basic requirement for automatic driving. The vehicle must identify which areas are drivable and which are undrivable before subsequent path planning can be performed. In some specific automatic driving assistance functions (such as parking), the recognition of the drivable area is particularly impo...

AI Technical Summary

Problems solved by technology

[0003] The existing technology generally uses sensors to obtain and analyze the surrounding information of the vehicle, so as to obtain the drivable environment around the vehicle; however, the existing technology is often not accurate enough for the identification of the drivable area. Therefore, a new vehicle drivable area detection is needed method, which can more accurately identify the driving environment around the vehicle and the drivable area

Images