Obstacle avoidance strategy determination method and device and storage medium

A strategy determination and obstacle avoidance technology, applied in the computer field, can solve the problem of low security of obstacle avoidance strategy

Active Publication Date: 2020-10-02
知行汽车科技(苏州)股份有限公司
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present application provides a method, device and storage medium for determining an obstacle avoidance strategy, which can solve the problem of lo

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
  • Obstacle avoidance strategy determination method and device and storage medium
  • Obstacle avoidance strategy determination method and device and storage medium
  • Obstacle avoidance strategy determination method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The specific implementation manners of the present application will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0059] First, some terms involved in this application are introduced.

[0060] Inverse reinforcement learning: refers to the process of learning a reward function from expert examples. Reverse reinforcement learning includes, but is not limited to, the following types: apprentice learning, Maximum Margin Planning (MMP), structured classification, and neural reverse reinforcement learning, etc. This application will not list the types of reverse reinforcement learning here.

[0061] Q-Learning: refers to the method of learning the expected value (Expected Utility) (or Q value) corresponding to each operation. The model for learning Q-Learning can be a neural network, and the model obtained i...

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 an obstacle avoidance strategy determination method and a device and a storage medium, and belongs to the technical field of computers. The method comprises the steps: inputting the current environment information of a current driving vehicle into an estimation network, and obtaining a Q value corresponding to each driving operation, wherein the estimation network is obtained through training by using first training data, and the first training data is extracted from a secure data container and an unsecure data container; sorting the driving operations according to thedescending order of the Q values; for the driving operation sorted at the i position, determining whether the driving operation at the i position is a safe driving operation; if the driving operation of the i position is not the safe driving operation, setting i to be i+1 until the driving operation of the i position is the safe driving operation, determining the driving operationof the i position to be an obstacle avoidance strategy of the current running vehicle; thereof the problem that an obstacle avoidance strategy determined based on rules is not high in safety canbe solved, and the safety of the determined obstacle avoidance strategy is improved.

Description

technical field [0001] The present application relates to a method, device and storage medium for determining an obstacle avoidance strategy, and belongs to the field of computer technology. Background technique [0002] With the development of IoT technology, self-driving vehicles support automatic obstacle avoidance. For example: automatically avoid other vehicles, automatically avoid roadblocks, etc. [0003] Existing obstacle avoidance strategies include: avoiding obstacles according to preset rules based on current road information. For example: the road environment at the current moment is that there are many vehicles driving on the left, and the lane change strategy is to change lanes to the right. [0004] However, when the current road environment is very complex, the method of avoiding obstacles based on preset rules may not be able to provide a safer obstacle avoidance strategy. Contents of the invention [0005] The present application provides a method, dev...

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
IPC IPC(8): B60W60/00B60W50/00B60W40/10
CPCB60W60/0015B60W60/0017B60W50/00B60W40/10B60W2050/0028B60W2554/4042B60W2554/4041B60W2552/50
Inventor 乔晓利
Owner 知行汽车科技(苏州)股份有限公司
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