A decision-making method for rearward collision avoidance driving of heavy-duty commercial vehicles

Abstract

The invention discloses a decision-making method for rearward collision avoidance driving of a heavy commercial vehicle. First, a traffic environment model is established, and the movement state information of heavy-duty commercial vehicles and vehicles behind them is collected. Secondly, a rearward collision risk assessment model based on the backward distance to collision time is established to accurately quantify the rearward collision risk. Finally, the backward collision avoidance driving decision-making problem is described as a Markov decision process under a certain reward function, and a backward collision avoidance driving decision-making model based on deep reinforcement learning is established to obtain an effective, reliable and adaptive backward collision avoidance Crash driving decision-making strategy. The method proposed by the present invention overcomes the lack of research on rearward collision avoidance driving decision-making of heavy-duty commercial vehicles in the existing methods, can quantitatively output reasonable steering wheel angle and throttle opening control amount, and provides drivers with effective and reliable rear Suggestions for anti-collision driving to reduce the occurrence of rear collision accidents.

Description

technical field [0001] The invention relates to a decision-making method for anti-collision driving, in particular to a decision-making method for backward anti-collision driving of heavy commercial vehicles, and belongs to the technical field of automobile safety. Background technique [0002] As the main undertaker of road transportation, the safety status of operating vehicles directly affects the safety of road transportation in our country. Vehicle collision is the most important accident form in road transportation. Heavy-duty commercial vehicles represented by dangerous goods transport tankers are mostly loaded with dangerous chemicals such as inflammable, explosive, and highly toxic (methanol, acrylonitrile). Compared with forward collisions, rear collisions are more likely to cause tank damage. If the body is damaged, it will cause serious consequences such as leakage, combustion, and explosion of dangerous goods in the tank. Driving decision-making is an importan...

AI Technical Summary

Problems solved by technology

Therefore, the driving decision-making method for passenger vehicles is difficult to apply to heavy-duty commercial vehicles

In general, the existing research does not involve the driving decision-making of heavy-duty commercial vehicles, especially the lack of effective, reliable and adaptive traffic environment characteristics of heavy-duty commercial vehicles.

Images