Vehicle trajectory network interactive predicting method for movement states of multiple vehicles

Abstract

The invention relates to a vehicle trajectory network interactive predicting method for the movement states of a plurality of vehicles, and belongs to the technical field of intelligent networking vehicle environment awareness. The method provided by the invention comprises the following steps: determining the relative position relationship of a plurality of networked vehicles; extracting the characteristics of the driving state of each vehicle, respectively inputting the characteristics of the driving states of the vehicles into short and long term memory units, and connecting and sharing hidden states of adjacent vehicles through a radial network so as to construct structured short and long time memory units and realize the modelling of an interaction relationship among the vehicles; then, establishing a multilayer encoder-decoder network to predict the future driving trajectories of the vehicles by utilizing the structured short and long time memory units; finally, transmitting thepredicted state obtained by the network to a decision making module to perform autonomous decision-making and path planning. According to the vehicle trajectory network interactive predicting method for the movement states of the vehicles, the driving states of the networked vehicles are shared in a hidden state layer by adopting the structured short and long time memory units so as to realize themodelling of the interaction relationship; by the method, synchronous long-time span prediction can be performed on the vehicles in a complex traffic environment to achieve high prediction accuracy.

Description

technical field [0001] The invention relates to a method for interactively predicting vehicle trajectories and networks in the motion state of multiple vehicles, and belongs to the technical field of intelligent and networked vehicle environment perception. Background technique [0002] Intelligentization and networking are the development trend of automobile technology. Intelligent networked vehicles have the potential advantages of enhancing safety, improving economy and increasing traffic volume, and have become a research hotspot at home and abroad. In order to ensure driving safety in complex traffic environments, ICVs need to predict changes in the traffic environment in the future and make reasonable responses. The driving state of surrounding cars is usually difficult to predict, mainly caused by the following uncertain factors: randomness of driver behavior, strong interaction with other traffic participants, spatial constraints of road structure, and noise perceive...

AI Technical Summary

Problems solved by technology

[0004] However, since the above-mentioned multi-vehicle input prediction algorithm only considers the influence of environmental vehicles on the predicted target when predicting the future driving state, but does not consider the impact of the predicted target on surrounding vehicles, it is essentially a single vehicle that does not consider multi-vehicle interaction. Independent prediction, so the application of this method is limited in complex traffic scenarios with strong interactions between multiple vehicles

Images