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

A deep reinforcement learning method for unmanned driving that integrates human-like driving behavior

An unmanned driving and reinforcement learning technology, which is applied in the direction of position/direction control, autonomous decision-making process, vehicle position/route/height control, etc., can solve the problem of inability to have decision-making robustness, and achieve improved human-like characteristics , the effect of preserving robustness

Active Publication Date: 2022-08-05
SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is more focused on realizing functions rather than achieving high driving performance. Due to the uncertainty of the data source of driverless cars, this kind of solution that relies on accurate environmental judgment cannot be robust enough to deal with the real road environment. sex

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
  • A deep reinforcement learning method for unmanned driving that integrates human-like driving behavior
  • A deep reinforcement learning method for unmanned driving that integrates human-like driving behavior
  • A deep reinforcement learning method for unmanned driving that integrates human-like driving behavior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of the components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the invention unless specifically stated otherwise.

[0059] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0060] Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods, and apparatus should be considered part of the specification.

[0061] In all examples shown and discussed herein, any specific value should be construed as illustrative only and not as limiting. Accordingly, other instances of the exemplary embodiment may...

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 discloses an unmanned deep reinforcement learning method integrating human-like driving behavior, comprising: establishing human-like driving rules through prior knowledge, and the human-like driving rules are used to reflect human driving logic; Driving is a continuous and stateful process. Based on the constraints of the human-like driving rules, a posteriori constraints on the driverless strategy are used to shape the constraint results into reward and punishment functions, and deep reinforcement learning is used to explore driverless vehicles that meet the set standards. Strategy. The present invention can output an unmanned driving strategy with human-like logic, and has better control performance and training efficiency.

Description

technical field [0001] The present invention relates to the technical field of unmanned vehicles of vehicles, and more particularly, to an unmanned deep reinforcement learning method integrating human-like driving behavior. Background technique [0002] Unmanned driving is an inevitable trend of future vehicle development and an effective way to avoid human driving errors and improve traffic efficiency. The rapid development of existing communication, electronic and computer technology has laid a solid foundation for the development of driverless technology. The Institute of Electrical and Electronics Engineers (IEEE) predicts that by 2040, 75% of vehicles will be driverless cars. The market for driverless vehicles will grow 10 times faster than other vehicles, and the emergence of driverless vehicles will reduce the traffic accident rate to 10%. [0003] Among the many tasks faced by artificial intelligence, unmanned driving is a very challenging scene. It must be able to...

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 Patents(China)
IPC IPC(8): G05D1/00G06N3/04
CPCG05D1/0088G06N3/045
Inventor 徐坤吕迪李慧云
Owner SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
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