A method and device for calculating obstacle heading angle based on time synchronization

Abstract

The invention discloses a method and device for calculating the course angle of an obstacle based on time synchronization. Wherein, the method includes: obtaining a heading angle calculation model, wherein the heading angle calculation model is obtained by training the historical data of the heading angle yaw value; sensing obstacles through a sensing device to obtain heading angle perception data; according to the heading angle The angle perception data and the heading angle calculation model are used to generate a first heading angle calculation result; and the verification operation of the synchronization time stamp is performed on the heading angle calculation result to obtain a second heading angle calculation result. The invention solves the problem that in the perception detection algorithm of the prior art, it is difficult to calculate the yaw angle of obstacles using image perception, and the result is also difficult to be accurate; it is not easy to calculate the yaw angle of obstacles accurately by using the traditional point cloud clustering algorithm , and stability cannot be guaranteed. Secondly, the calculation of the obstacle heading angle also involves the own vehicle heading angle output by the inertial navigation of the own vehicle, the calibration results of the inertial navigation and perception sensors, and the time synchronization of the sensors, which is a technical problem involving systematic problems of software, hardware and algorithms. .

Description

technical field [0001] The present invention relates to the field of intelligent driving, in particular to a method and device for calculating an obstacle heading angle based on time synchronization. Background technique [0002] With the continuous development of intelligent technology, more and more intelligent devices are used in people's life, work and study. The use of intelligent technology has improved the quality of people's life and increased the efficiency of people's study and work. [0003] At present, in the field of automatic driving, automatic intelligent driving using multi-directional perception is the mainstream driving design concept, but in the field of intelligent driving in the existing technology, although the calculation of the heading angle of the vehicle is an important calculation of the driving force of the automatic driving of the vehicle parameters, but in the unmanned driving perception system, the heading angle of obstacles is usually not accu...

AI Technical Summary

Problems solved by technology

[0004] First of all, in the perceptual detection algorithm, it is difficult to calculate the yaw angle of obstacles using image perception, and the results are difficult to be accurate; it is not easy to calculate the yaw angle of obstacles accurately by using traditional point cloud clustering algorithms, and the stability cannot be guaranteed.

Secondly, the calculation of the obstacle heading angle also involves the own vehicle heading angle output by the own vehicle inertial navigation, the calibration results of the inertial navigation and perception sensors, and the time synchronization of the sensors, which is a systematic issue involving software, hardware and algorithms.

[0005] For the above problems, no effective solution has been proposed

Images