Intelligent decision-making method for unmanned vehicles based on motivation and risk assessment

Abstract

The invention discloses an intelligent decision-making method for an unmanned vehicle based on motivation and risk assessment. First, the surrounding environment conditions and motivation are analyzed when the vehicle needs to change state in a high-speed environment. On this basis, the motivation to change the driving state is extracted, and it is taken as the core of behavior decision-making, and the decision is made only when there is motivation to trigger, while the current driving state remains in other cases. At the same time, a risk assessment model for the surrounding environment of unmanned vehicles is established to dynamically verify the decision-making results, judge the rationality of the decision-making, and calculate the optimal target point of the decision-making. The invention can avoid too many meaningless decisions of the decision-making system during the driving process of the unmanned vehicle, improve the calculation efficiency, and realize the real-time, efficient and safe driving decision of the unmanned vehicle under the dynamic uncertain environment.

Description

technical field [0001] The invention relates to the technical field of unmanned vehicle decision-making, in particular to an intelligent decision-making method for unmanned vehicles based on motivation and risk assessment. Background technique [0002] With the rapid development of computer and communication technology, self-driving cars have gained more and more attention. Major auto companies around the world are also stepping up research and development of higher-level technologies for autonomous driving. Advanced auxiliary technologies and decision-making algorithms such as BSD, CTA, IACC, etc. developed to cope with different scenarios have been put into the market one after another. Among them, behavior decision-making and planning in the face of various traffic environments and emergency situations is the core technology to ensure safe and efficient driving of vehicles. At present, driving behavior decision-making is mainly based on rule-based or learning algorithm-...

AI Technical Summary

Problems solved by technology

When the actual human driver is driving, he does not plan all the feasible trajectories in his mind at all times, which greatly reduces the calculation efficiency and real-time performance.

Images