Generation method and device for decision network model of vehicle automatic driving

An automatic driving and network model technology, applied in the computer field, can solve the problems of weak vehicle decision-making model learning ability, inability to adapt to different routes and scenarios, and low efficiency of decision-making model training, so as to improve learning ability and generalization Ability, the effect of rapid training

Active Publication Date: 2017-09-15
SHENZHEN INST OF ADVANCED TECH
View PDF4 Cites 60 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method and device for generating a decision-making network model for automatic driving of vehicles, aiming at solving the problem that the training efficiency of the decision-making model for automatic driving of vehicles is low, and the learning ability of the vehicle decision-making model is relatively weak and cannot be improved. Adapt to different routes and scenarios

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
  • Generation method and device for decision network model of vehicle automatic driving
  • Generation method and device for decision network model of vehicle automatic driving
  • Generation method and device for decision network model of vehicle automatic driving

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] figure 1 It shows the implementation process of the method for generating the decision network model for automatic driving of vehicles provided by Embodiment 1 of the present invention. For the convenience of description, only the parts related to the embodiment of the present invention are shown, and the details are as follows:

[0024] In step S101, according to the vehicle state information collected at each test time, the preset vehicle action set and the preset reward-reward function, a sample triplet corresponding to each test time is generated.

[0025] The present invention is applicable to an interactive platform established based on a racing simulation platform or a racing simulator (for example, TORCS, The open racing car simulation), on which an interactive driving test of an unmanned vehicle is performed. In the current interactive test process, the vehicle status information is collected through multiple preset sensors on the vehicle. The vehicle status in...

Embodiment 2

[0048] figure 2 The structure of the device for generating the decision network model for automatic driving of vehicles provided by Embodiment 2 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, including:

[0049] The sample generation module 21 is configured to generate a sample triplet corresponding to each test time according to the vehicle state information collected at each test time, the preset vehicle action set and the preset reward-reward function.

[0050] In the embodiment of the present invention, after collecting the vehicle state information at the current test moment, according to the preset reward reward value function, traverse the preset vehicle action set to find the action that can obtain the maximum reward value, that is, the maximum reward value action, A sample triplet is composed of the vehicle state information, the maximum reward value action, and the r...

Embodiment 3

[0059] image 3 The structure of the device for generating a decision network model for automatic driving of vehicles provided by Embodiment 3 of the present invention is shown, which includes:

[0060] The sample generation module 31 is configured to generate a sample triplet corresponding to each test time according to the vehicle state information collected at each test time, a preset vehicle action set and a preset reward-reward function.

[0061] In the embodiment of the present invention, after collecting the vehicle state information at the current test moment, according to the preset reward reward value function, traverse the preset vehicle action set to find the action that can obtain the maximum reward value, that is, the maximum reward value action, A sample triplet is composed of the vehicle state information, the maximum reward value action, and the reward value of the maximum reward value action.

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 is applicable to the field of computer technology and provides a generation method and device for a decision network model of vehicle automatic driving. The method comprises the steps that a sample triad corresponding to each test moment is generated according to vehicle state information collected at each test moment, a preset vehicle movement set and a preset return function, all the sample triads are stored as sample data in a pre-established experience database, and all the sample data is subjected to clustering analysis; training samples are uniformly collected from each cluster obtained after clustering analysis of the experience database according to a preset sampling scale value, and a return accumulated value of each training sample is calculated; and according to all the training samples, the return accumulated value of each training sample and a preset deep learning algorithm, training is performed to obtain the decision network model of vehicle automatic driving. Therefore, the training efficiency of the decision network model and the generalization ability of the decision network model are effectively improved.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a method and device for generating a decision network model for automatic driving of vehicles. Background technique [0002] With the development of the economy and the advancement of urbanization, the global car ownership and road mileage are gradually increasing, resulting in a series of problems that cannot be properly solved by traditional cars, such as traffic congestion, accidents, pollution, and shortage of land resources. Self-driving car technology is seen as an effective solution to these problems, and its development has attracted much attention. [0003] Driverless cars, that is, driving on the road through their own assisted driving system without a driver, have the ability to perceive the environment. At present, the control method of the assisted driving system is mainly rule-based control decision-making, that is, according to the known driving expe...

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): G06N5/02G06N99/00
CPCG06N5/022G06N20/00
Inventor 夏伟李慧云
Owner SHENZHEN INST OF ADVANCED TECH
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