Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

System suitable for driverless decision learning and training

An unmanned and decision-making technology, applied in the field of unmanned decision-making learning and training systems, can solve problems such as high cost, little help, low efficiency, etc., to reduce resources and costs, save costs, and promote convergence speed. Effect

Active Publication Date: 2020-03-27
BEIJING JIAOTONG UNIV
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the existing methods are to design the algorithm framework, use big data for training, or conduct training / verification according to a set of established rules, it is not very helpful for the core of unmanned driving-driving skills or intelligent decision-making algorithms, and The problem of low efficiency and high cost, this application provides a system suitable for unmanned driving decision-making learning and training

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
  • System suitable for driverless decision learning and training
  • System suitable for driverless decision learning and training

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] A server with a GPU graphics accelerator is connected to a computer display screen, and the vehicle simulation system can be composed of commercially available analog steering wheel 4, gear position 5, and brake / throttle 6 modules. Use 3D modeling tools to generate various road scenes, let an experienced driver operate the vehicle simulation module in the generated simulation scene, and send the output information of each vehicle simulation module to the server in real time, and the server will send the current road parameters in the simulation scene etc. correspond to the driver's operating parameters, and are used as input training samples of the machine learning algorithm sub-module 7 built in the server to learn and train the algorithm module.

Embodiment 2

[0060] Two computers are used to form a distributed computing system based on LAN, one of which is used as the main control computer for virtual reality simulation driving, and its corresponding display is a head-mounted VR display device to display various road conditions. The control computer controls a three-axis dynamic chassis 9 to simulate the movement of the vehicle under various road conditions, allowing the driver to obtain a realistic driving experience; the other computer is used as the main processor of the machine learning algorithm sub-module 7 to accept simulated driving The operating parameters, as well as various road condition parameters sent by the main control computer of the virtual reality simulation driving, these parameters are used as the input training samples of the machine to learn and train the algorithm module.

Embodiment 3

[0062] Two servers are used to form a distributed system based on high-speed LAN. One of the servers is used as the main control computer for virtual reality simulation driving, and its corresponding display is a head-mounted VR display device to display various road conditions. At the same time, the The main control computer controls a six-axis dynamic chassis 9 to simulate the movement of the vehicle under various road conditions, allowing the driver to obtain a realistic driving experience; another server with a GPU accelerator card is used as the machine learning algorithm sub-module 7 The main processor accepts the operating parameters of the simulated driving and various road condition parameters sent by the main control computer of the virtual reality simulated driving, takes these parameters as the input training samples of the deep neural network, and uses certain evaluation indicators to evaluate each The driving result is evaluated, and the evaluation result is also ...

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 belongs to the technical field of artificial intelligence, and particularly relates to a system suitable for driverless decision learning and training. As an algorithm framework is designed in an existing method, and big data is used for training, or training / verification is carried out according to a set of formulated rules, the efficiency is low, and the cost is high. The inventionprovides a system suitable for driverless decision learning and training. The system comprises a virtual reality / machine learning unit, wherein the virtual reality / machine learning unit comprises a main processor module; the main processor module is connected with a virtual reality presentation module; the main processor module is connected with a vehicle control electromechanical module; the vehicle control electromechanical module is connected with a steering wheel; the vehicle control electromechanical module is connected with gears; and the vehicle control electromechanical module is connected with an accelerator / brake. The problem of how to quickly train an algorithm in the unmanned driving technology is solved, and the vehicle driving ability, especially artificial intelligence learning, is improved.

Description

technical field [0001] The present application belongs to the technical field of artificial intelligence, and in particular relates to a system suitable for unmanned driving decision-making learning and training. Background technique [0002] The cost of studying unmanned driving is very high. On the one hand, unmanned driving is a comprehensive application of related technologies in multiple fields, such as a series of complex algorithms such as vehicle positioning, object detection, tracking, and path planning. Automated driving laboratories and experimental sites are needed to verify relevant algorithms, otherwise the researched algorithms cannot be verified and truly applied. In particular, the external environment that unmanned vehicles face after they are actually on the road is very complex and changeable. In order to enable unmanned driving to cope with these complex situations, one way is to let the vehicle drive safely under the actual road conditions. Collect dat...

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): G09B9/05
CPCG09B9/05
Inventor 王忠立蔡伯根王剑陆德彪刘江
Owner BEIJING JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com