Gray Markov model-based hybrid enhanced intelligent trajectory prediction method and device

Abstract

The invention discloses a gray Markov model-based hybrid enhanced intelligent trajectory prediction method and device, the method is applied to a coke oven coal car, and the method comprises: the cokeoven coal car uses a UWB positioning system to obtain real-time position data of each moving target in a coal car operation area; obtaining a classification result of each moving target after judgingthat the moving targets are regular targets based on a human-in-loop hybrid enhanced intelligent method; and receiving the classification result and the real-time position data of each moving target,predicting the next moving position and the moving direction of each moving target in the coal car operation area according to the priori data in combination with a grey prediction method and a Markov model correction method, and analyzing and judging the moving trend of each moving target so as to control the operation of the coke oven coal car. According to the invention, based on the human-in-loop hybrid enhanced intelligence concept, the next moving position and moving direction of the moving target are subjected to trajectory prediction and correction in combination with the grey prediction method and the Markov model, so that the active safety performance of the coal car is improved.

Description

technical field [0001] The invention relates to the field of intelligent vehicles, in particular to a gray Markov model-based hybrid enhanced intelligent trajectory prediction method and device. Background technique [0002] When the coke oven coal car runs on a fixed track, there are pedestrians walking forward, reverse and across the track. Usually, a coke oven coal car with hundreds of tons runs on a track about a few hundred meters long, and the braking distance can generally reach 100 to 200 meters, that is, it can be detected within a range of more than 100 meters from the coke oven coal car. When moving obstacles, the brake operation should be performed. But in actual operation, such brakes almost prevent the coal car from working properly, especially when it is unmanned. Therefore, in order to reduce the impact on the work of coke oven coal wagons and ensure the safety of coke oven coal wagons and pedestrians when the staff are walking in the coke oven coal wagon o...

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present application provides a hybrid enhanced intelligent trajectory prediction method and device based on the gray Markov model, which solves the problem that the coke oven coal car cannot work normally due to the activities in the operation area of ​​the moving target coke oven coal car in the prior art. The problem of the work is to realize the real-time collection of the position data of each moving target in the coke oven coal car operation area, and according to the human-in-the-loop hybrid enhanced intelligence method, after the prediction object is determined by human beings as the regular target, the regular target is determined based on human cognition. Classification, upload the classification results, combined with the gray prediction method is suitable for predicting the characteristics of small sample data, according to the prior data, combined with the gray prediction method and Markov model correction, predict the next step of the pedestrian trajectory in the coal car area, and solve the problem of coke oven coal Pedestrian Trajectory Prediction Problem for Unmanned Vehicle Operation

Images