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

An Adaptive Cruise Control Algorithm for Three-axle Heavy Vehicles Based on Deep Reinforcement Learning

A technology of adaptive cruise and reinforcement learning, applied in combustion engines, internal combustion piston engines, mechanical equipment, etc., can solve the problems of rollover and the roll stability of heavy vehicles without considering it, and achieve the effect of improving safety.

Active Publication Date: 2022-03-22
JILIN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Most of the current adaptive cruise control algorithms for heavy-duty vehicles are based on rule-based design and do not consider the roll stability of heavy-duty vehicles. Stability issues such as rollover

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
  • An Adaptive Cruise Control Algorithm for Three-axle Heavy Vehicles Based on Deep Reinforcement Learning
  • An Adaptive Cruise Control Algorithm for Three-axle Heavy Vehicles Based on Deep Reinforcement Learning
  • An Adaptive Cruise Control Algorithm for Three-axle Heavy Vehicles Based on Deep Reinforcement Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0039] Such as figure 1 As shown, the present invention provides a three-axis heavy-duty vehicle adaptive cruise control algorithm based on deep reinforcement learning. Roll stability of commercial vehicles.

[0040] The environmental state information of the vehicle in reinforcement learning is obtained through sensor data, and the output actions include steering wheel angle, brake pedal opening, and accelerator pedal opening in three dimensions. The environmental state information of the vehicle includes the offset of the center of mass of the vehicle relative to the center of the lane. , the distance from the vehicle in front, the speed of the vehicle in front, and the speed of the vehicle in four dimensions. Sensors installed on smart commercial vehicles can provide nec...

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 adaptive cruise control algorithm for a three-axis heavy-duty vehicle based on deep reinforcement learning. Based on the offset of the center line of the lane, the distance between the vehicle in front and the vehicle in front, the speed of the vehicle in front and the vehicle in front; Step 2, input the eigenvalues ​​representing the vehicle state into the reinforcement learning network model to obtain the vehicle control parameters; and according to the vehicle state characteristics Values ​​and corresponding vehicle control parameters determine the reward function; wherein, the vehicle control parameters include: steering wheel angle, brake pedal opening and accelerator pedal opening; step 3, optimize the reinforcement learning network model until the maximum value of the reward function is obtained , to obtain the optimal reinforcement learning network; among them, in the vehicle adaptive cruise state, the steering wheel angle, brake pedal opening and accelerator pedal opening are obtained through the optimal reinforcement learning network.

Description

technical field [0001] The invention belongs to the technical field of vehicle control, in particular to an adaptive cruise control algorithm for a three-axis heavy-duty vehicle based on deep reinforcement learning. Background technique [0002] In the three major fields of perception, decision-making and control of unmanned driving technology, the decision-making of intelligent vehicles has always been the core part and key competitive field of autonomous driving, playing the role of the driver's brain. The adaptive cruise system of heavy-duty vehicles is an important auxiliary driving technology, and its decision-making superiority directly affects the driving safety and driving efficiency of the vehicle. [0003] The ACC decision-making system of traditional intelligent vehicles is based on rule design, artificially stipulates the behavior mode of the vehicle in each scene, and uses certain characteristic variables as the judgment basis for conditional switching. Most of...

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): B60W60/00B60W40/00B60W30/14
CPCB60W60/0016B60W40/00B60W30/14B60W2520/10B60W2554/802B60W2554/4042Y02T10/40
Inventor 赵伟强孙铭牟嘉鹏宗长富
Owner JILIN UNIV