Preceding vehicle following method based on deep convolutional neutral network

A neural network and deep convolution technology, applied in the field of following vehicles based on deep convolutional neural networks, can solve the cumbersome visual ranging and controller design process of the adaptive cruise system, cannot meet different personal driving habits, and cannot be fine-tuned Control parameters and other issues to achieve the effect of avoiding visual distance measurement and controller design process, reducing theoretical basis requirements, and universal application range

Active Publication Date: 2017-09-26
ZHEJIANG LEAPMOTOR TECH CO LTD
View PDF6 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention mainly solves the problems of cumbersome visual distance measurement and controller design process in the prior art self-adaptive cruise system, as well as the inability to fine-tune the control parameters according to the driver's driving habits, and cannot meet the different driving habits of individuals. Car-Following Method for Deep Convolutional Neural Networks

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Preceding vehicle following method based on deep convolutional neutral network
  • Preceding vehicle following method based on deep convolutional neutral network
  • Preceding vehicle following method based on deep convolutional neutral network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] In this embodiment, a car following method based on a deep convolutional neural network, such as figure 1 shown, including the following steps:

[0045] S1. Establish a training sample library; the specific process includes:

[0046] S11. Use the experimental vehicle to collect driving training data in different locations, climates, and weathers. The training data includes the visual data of the forward-looking camera and the corresponding driving manipulation data. The manipulation data includes the sensor data of the accelerator pedal and the automatic pedal;

[0047] S12. Synchronizing the visual data and the manipulation data;

[0048] S13. Screen the data of the car-following operation part, discretize the data, generate data samples, and complete the establishment of the training sample library.

[0049]S2. Establish a deep convolutional neural network; a deep convolutional neural network is generally composed of convolution, pooling, and full connection operati...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a preceding vehicle following method based on a deep convolutional neutral network and solves the problems that a self-adaptive cruise system in the prior art has tedious visual ranging and controller design processes, cannot fine adjust control parameters according to driving habits of drivers and cannot meet different personal driving habits. Driving behavior data are trained, and under the condition of given visual sensing input, accurate control of vehicle accelerators and automatic pedals under multiple work conditions is realized by imitating human drivers according to feature description of the surroundings by the deep convolutional neutral network. All that is required is to fine adjust the deep neutral network parameters with different work condition training samples instead of designing the controller structure and adjusting the controller gain under different work conditions. The tedious visual ranging and controller design processes are avoided, and the vehicle following behavior of the drivers is simulated by adjusting the deep neutral network parameters.

Description

technical field [0001] The invention relates to the technical field of automobile control, in particular to a method for following a preceding vehicle based on a deep convolutional neural network. Background technique [0002] Adaptive Cruise Control (ACC) is one of the important functions of the vehicle's advanced driver assistance system. Existing systems of this type control the speed of the self-vehicle to maintain the distance from the vehicle in front (or maintain the set speed) based on the distance and relative movement information between the self-vehicle and the vehicle in front output by the vision or radar sensing system. This type of system first converts the original perception data of the vision system or radar system into the input of the corresponding controller, such as the distance between vehicles and the relative speed of the vehicle. Regardless of the radar or vision system, it is difficult to avoid measurement errors (false reporting of obstacles, etc....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 缪其恒王江明许炜
Owner ZHEJIANG LEAPMOTOR TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap