Unmanned vehicle lane changing decision-making method and system based on adversarial imitation learning

A technology of unmanned vehicles and decision-making methods, which is applied in the field of unmanned autonomous vehicles and can solve problems such as weak model generalization ability

Active Publication Date: 2020-08-04
GUANGZHOU UNIVERSITY
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Both end-to-end supervised learning and deep reinforcement learning can train a neural network model to directly map perception data to lane-changing decision output. However, end-to-end supervised learning usually requires a large amount of training data and the model generalization ability is weak. Reinforcement learning needs to artificially design a reward function that meets the task requirements

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
  • Unmanned vehicle lane changing decision-making method and system based on adversarial imitation learning
  • Unmanned vehicle lane changing decision-making method and system based on adversarial imitation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] The present embodiment discloses a decision-making method for changing lanes of unmanned vehicles based on confrontational imitation learning, through which the unmanned vehicles can switch lanes correctly and safely, and the method includes the following steps:

[0082] Step S1. Describe the lane-changing decision-making task of the unmanned vehicle as a partially observable Markov decision process.

[0083] In this embodiment, the lane-changing decision-making task of an unmanned vehicle is described as a partially observable Markov decision process, as follows:

[0084] Step S11, determine state O t Space: including the driving state of the vehicle, the front and rear vehicles in the vehicle lane, and the vehicles closest to the vehicle on the left and right lanes [l,v 0 ,s f ,v f ,s b ,v b ,s lf ,v lf ,s lb ,v lb ,s rf ,v rf ,s rb ,v rb ];

[0085] in:

[0086] l is the lane where the vehicle is located, v 0 is the vehicle’s self-vehicle speed; in th...

Embodiment 2

[0143] This embodiment discloses an unmanned vehicle lane change decision system for implementing the unmanned vehicle lane change decision method based on confrontational imitation learning in Embodiment 1, including:

[0144] A task description module, which is used to describe the lane-changing decision task of an unmanned vehicle as a partially observable Markov decision process;

[0145] The building block of the lane-changing decision model is used to use the anti-imitation learning method to train from the examples provided by the professional driving demonstration to obtain the lane-changing decision model of the unmanned vehicle; wherein, in the training process, the anti-imitation learning method is based on variance reduction Policy gradient learning strategy to simulate professional driving performance;

[0146] The environmental vehicle information acquisition module is used to obtain the current environmental vehicle information during the unmanned driving proces...

Embodiment 3

[0157] This embodiment discloses a storage medium, which stores a program. When the program is executed by a processor, the method for lane-changing decision-making for an unmanned vehicle based on confrontational imitation learning as described in Embodiment 1 is implemented, as follows:

[0158] Describe the lane-changing decision task of unmanned vehicles as a partially observable Markov decision process;

[0159] Use the confrontational imitation learning method to train from the examples provided by professional driving demonstrations to obtain the lane change decision model of unmanned vehicles; in the training process, the confrontational imitation learning method is based on the learning strategy of variance reduction strategy gradient to simulate professional driving Performance;

[0160] During the unmanned driving process of the vehicle, the currently acquired environmental vehicle information is used as the input parameter of the unmanned vehicle lane change decisi...

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 vehicle lane changing decision-making method and system based on adversarial imitation learning. The method comprises the steps that an unmanned vehicle lane changing decision-making task is described as a partially observable Markov decision-making process; training is carried out from examples provided by professional driving teaching by adopting an adversarial imitation learning method to obtain an unmanned vehicle lane changing decision-making model; and in the unmanned driving process of the vehicle, a vehicle lane change decision-making result is obtained through the unmanned vehicle lane change decision-making model by taking currently obtained environmental vehicle information as an input parameter of the unmanned vehicle lane change decision-making model. According to the invention, a lane changing strategy is learned from examples provided by professional driving teaching through adversarial imitation learning; a task reward function does not need to be manually designed, and direct mapping from the vehicle state to the vehicle lane changing decision can be directly established, so that the correctness, robustness and adaptivity of thelane changing decision of the unmanned vehicle under the dynamic traffic flow condition are effectively improved.

Description

technical field [0001] The invention belongs to the technical field of unmanned autonomous vehicles, in particular to a method and system for lane-changing decision-making for unmanned vehicles based on confrontational imitation learning. Background technique [0002] The development of unmanned driving will help improve the level of road traffic intelligence and promote the transformation and upgrading of the transportation industry. Unmanned vehicles are a combination of hardware and software. The hardware includes various types of sensors and controllers, and the software is a comprehensive system that integrates environmental perception, behavior decision-making, motion planning and autonomous control modules. [0003] Lane-changing decision is an important component module of unmanned vehicle decision-making technology, and it is the basis for the execution of subsequent action planning modules. At present, the existing technologies include published patents, and the m...

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): B60W50/00B60W30/12B60W30/18
CPCB60W50/00B60W30/12B60W30/18163Y02T10/40
Inventor 綦科
Owner GUANGZHOU UNIVERSITY
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