Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for determining overtaking decision in autonomous driving based on social preference

A technology for automatic driving and determining methods, applied in the direction of control devices, etc., can solve problems such as less consideration of the longitudinal driving behavior of overtaken vehicles, and achieve the effect of improving overtaking efficiency and overtaking safety

Active Publication Date: 2022-02-08
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the autonomous overtaking problem of intelligent vehicles, the existing autonomous overtaking systems rarely consider the longitudinal driving behavior and changes of the overtaken vehicle during the process of being overtaken, which leads to the inability of the host vehicle to monitor the overtaken vehicle in real time during the process of overtaking the overtaken vehicle. Make corresponding adjustments to overtaking behavior in the longitudinal driving behavior

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
  • Method and system for determining overtaking decision in autonomous driving based on social preference
  • Method and system for determining overtaking decision in autonomous driving based on social preference
  • Method and system for determining overtaking decision in autonomous driving based on social preference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, this embodiment provides a method for determining an overtaking decision for automatic driving based on social preferences. The method for determining an overtaking decision for automatic driving is applied to the parallel driving phase of the overtaking process. The method for determining an overtaking decision for automatic driving includes:

[0057] Step 101: Obtain target road information at the current stage; the target road information includes host vehicle position information, host vehicle speed information, overtaken vehicle position information, and overtaken vehicle speed information; both the host vehicle and the overtaken vehicle are driving on the target road .

[0058] Step 102: Input the current stage target road information into a social preference prediction model to determine the social preference of the overtaken vehicle in the current stage.

[0059] Step 103: Based on the social preference of the overtaken vehicle in the...

Embodiment 2

[0075] The present invention aims to provide a design method for an autonomous overtaking decision-making system based on social preferences, by integrating the driving experience and driving behavior of human drivers into the overtaking decision-making model (also called an overtaking decision-making module) of the autonomous overtaking system, and based on A semi-model-based modified Q-learning algorithm was developed for Markov decision process to address the problem of vehicle interaction during overtaking.

[0076] See figure 2 , an embodiment of the present invention provides a design method for an autonomous overtaking decision-making system based on social preferences, including:

[0077] Step 1, define the state lattice space. In the embodiment of the present invention, aiming at the problem of autonomous overtaking on the straight road, in order to facilitate the calculation and modeling in the process of overtaking, the straight road under study is established as ...

Embodiment 3

[0130] See Figure 5 , a social preference-based automatic driving overtaking decision-making system provided in this embodiment is applied to the parallel driving stage in the overtaking process, and the automatic driving overtaking decision-making system includes:

[0131] The data acquisition module 501 is used to acquire target road information at the current stage; the target road information includes host vehicle position information, host vehicle speed information, overtaken vehicle position information, and overtaken vehicle speed information; both the host vehicle and the overtaken vehicle travel on the target path.

[0132] A social preference determination module 502, configured to input the current stage target road information into a social preference prediction model to determine the social preference of the overtaken vehicle in the current stage.

[0133] A state transition model determining module 503, configured to determine a state transition model of the ov...

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 a method and system for determining an overtaking decision for automatic driving based on social preference, which is applied to the parallel driving stage in the overtaking process, including: inputting the acquired target road information in the current stage into a social preference prediction model to determine the overtaking decision in the current stage The social preference of the overtaking vehicle; based on the social preference of the overtaken vehicle in the current stage, determine the state transition model of the overtaken vehicle in the current stage; combine the target road information in the current stage, the social preference of the overtaken vehicle in the current stage, and the state of the overtaken vehicle in the current stage The transfer models are all input into the overtaking decision model to determine the overtaking decision of the host vehicle at the current stage; the overtaking decision includes lane keeping, performing lane change and giving up overtaking; wherein, the algorithm used in the overtaking decision model is a semi-model-based An improved Q‑learning algorithm for . The invention can output accurate overtaking decision, and improve overtaking efficiency and overtaking safety.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a method and system for determining an overtaking decision for automatic driving based on social preference. Background technique [0002] With the continuous increase of car ownership and the continuous advancement of autonomous driving technology, intelligent driving systems have gradually entered the public eye, among which autonomous overtaking systems have increasingly attracted the attention of researchers at home and abroad. At present, there are still some defects in the research on the autonomous overtaking system at home and abroad, especially in the parallel driving phase of two vehicles when overtaking. [0003] In typical driving scenarios for drivers, overtaking behavior is one of the most risky and challenging driving methods. Aiming at the autonomous overtaking problem of intelligent vehicles, the existing autonomous overtaking systems rarely co...

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): B60W30/18B60W60/00B60W50/00
CPCB60W30/18163B60W60/001B60W50/00B60W2050/0031
Inventor 吕超王昊阳鲁洪良于洋龚建伟臧政
Owner BEIJING INSTITUTE OF TECHNOLOGYGY