ACC/AEB system and vehicle based on machine learning

Abstract

The invention discloses an ACC / AEB system based on machine learning. The ACC / AEB system comprises an environment perception module, a data fusion module, a machine learning and decision controlling module and an execution module. The technical scheme is adopted to obtain control parameters adapted to driving habits of a driver by integrating a convolutional neural network with an ACC / AEB control algorithm and training and learning continuously, also to realize self-learning and self-correction during operation of ACC / AEB, namely, to self-learn operating conditions not encountered and self-correct unsatisfactory operating conditions, to continuously correct a weight value between each neuron and each parameter to output optimal control parameters, to realize intelligent vertical control, and to achieve comfort, safety and robustness.

Description

technical field [0001] The invention belongs to the technical field of advanced driving assistance. More specifically, the present invention relates to an intelligent, self-learning ACC / AEB system for vehicles. In addition, the invention also relates to a vehicle using the system. Background technique [0002] In recent years, the ACC / AEB system, as an active safety system, has been more and more recognized by the main engine manufacturers and customers, and countries all over the world have compulsorily installed this system to reduce driver fatigue and reduce the occurrence of traffic collisions and rear-end accidents . [0003] However, at present, the ACC / AEB system generally adopts the research on the driver's driving behavior parameters in the development process, and then obtains the driving behavior parameters of a sample driver as the main parameters of the driver's ACC / AEB control. Its existing problems are: [0004] First of all, the sample size of the control...

AI Technical Summary

Problems solved by technology

[0004] First of all, the sample size of the control parameters obtained in this way is small and cannot cover everyone's driving behavior and driving habits;

[0005] Secondly, during the development process of ACC / AEB, the developers calibrate the comfort and safety according to the acceleration, deceleration and braking force and other parameters of the test. Such parameters with a small sample size are completely unsuitable for every driver’s driving. Habit;

[0006] Finally, the ACC / AEB system does not have the ability to self-learn and correct errors by itself, and cannot adapt to different drivers and different working conditions through self-learning

Images