Heavy commercial vehicle rollover prevention driving decision method based on deep reinforcement learning

A reinforcement learning and anti-rollover technology, applied in the field of anti-rollover driving decision-making and anti-rollover driving decision-making of heavy commercial vehicles, can solve the problems of low effectiveness, reliability and adaptability
CN112580148AActive Publication Date: 2021-03-30SOUTHEAST UNIV
3 Cites 8 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Current Assignee / Owner
SOUTHEAST UNIV
Publication Date
2021-03-30

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an anti-rollover driving decision method for a heavy commercial vehicle based on deep reinforcement learning. The method comprises the steps: firstly, establishing a three-lanevirtual environment model including a straight lane and a bent lane for a high-grade road; secondly, acquiring road state information and vehicle motion information; finally, modeling the anti-rollover driving decision problem as a Markov decision process, and establishing an anti-rollover driving decision model of the heavy commercial vehicle by using a depth deterministic strategy gradient algorithm to obtain anti-rollover driving decision strategies under different traffic environments and driving conditions, thereby realizing an optimal decision for active prevention and control of rollover of the heavy commercial vehicle. The decision-making method provided by the invention overcomes the defects of lack of effectiveness, environmental adaptability and the like of an existing method,and provides accurate and quantitative driving suggestions such as brake pedal opening, steering wheel angle control quantity and the like for a driver, so an effective, reliable and self-adaptive rollover prevention driving decision is realized.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a decision-making method for anti-rollover driving, in particular to a decision-making method for anti-rollover driving of heavy commercial vehicles based on deep reinforcement learning, and belongs to the technical field of automobile safety. Background technique

[0002] As the main undertaker of my country's road transportation, heavy-duty commercial vehicles have a direct impact on the safety of my country's road transportation. Once a traffic accident occurs during transportation, it will easily lead to serious consequences such as mass death and mass injury, cargo falling off, burning, explosion, etc., resulting in property loss, environmental pollution, ecological damage, etc. Threat to the public security of our society.

[0003] Relevant data from the U.S. Highway Traffic Safety Administration show that among all commercial vehicle traffic accidents, rollover accidents are second only to collision accidents, ranking s...

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