Integrated multi-sensor integrated automatic driving intelligent sensing device

Abstract

The integrated multi-sensor integrated automatic driving intelligent sensing device disclosed by the invention can reliably and accurately identify the traffic environment in real time. According to the technical scheme, an intelligent sensing model module tracks and detects static and dynamic obstacles outside a vehicle in real time, element information and behavior information in a scene are obtained, and a sensor data acquisition module transmits sensor acquisition data to a sensor data synchronization module after completing data receiving of all sensors; the method also includes carrying out automatic analysis on a plurality of intelligent sensors, and carrying out time-space registration on target-level detection information; sending the synchronously calibrated data to a sensor data processing module in real time; sending the processed data to a planning control module, and performing real-time track prediction; and enabling the sensor fusion control vehicle execution module to execute sensing data according to the control path planning of the planning control module, recognize trafficability and static and dynamic objects in the whole field of view around the vehicle body, and make decisions of braking and obstacle avoidance.

Description

technical field [0001] The present invention relates to the field of automatic driving intelligent perception, and further relates to an integrated portable automatic driving intelligent perception device based on multi-sensor fusion. Background technique [0002] Unmanned driving is a product of the highly developed artificial intelligence, computer science, and automation technologies. At present, artificial intelligence is divided into three stages: computational intelligence, perceptual intelligence and cognitive intelligence. However, there is a big gap between machines and humans in terms of cognitive abilities such as understanding, thinking, and reasoning. Self-driving cars are the product of the development and integration of automotive electronics, intelligent control, and the Internet. The principle is that the self-driving system uses the perception system to obtain information about the vehicle itself and the external environment, analyzes the information throu...

AI Technical Summary

Problems solved by technology

These common limitations bring about the decline of sensor perception ability, which has always been a difficult point in the industry.

However, this method does not have strict constraints to ensure that the features are aligned with the transformed anchor, and it is difficult to determine whether the transformed features and the anchor are aligned.

When judging the positive or negative of the anchor, simply using the anchor-free or anchor-base method is not enough, because the use of the anchor-free standard will cause the stage2 requirements to be too low, and the use of the anchor-base will cause the stage1 to not return enough Positive samples of

Images