Graph convolutional neural network model and vehicle trajectory prediction method using same

Abstract

The invention discloses a graph convolutional neural network model and a vehicle trajectory prediction method using the same. The model is composed of an encoder module, a spatial information extraction layer module and a decoder module. The method comprises the following steps: firstly, sampling a predicted vehicle and surrounding vehicles in a traffic scene at a frequency of 5Hz, and collectingposition coordinates and kinetic parameters of each vehicle sampling point, including horizontal and longitudinal coordinates, horizontal and longitudinal vehicle speeds and accelerations; calculatingcollision time TTC between the predicted vehicle and surrounding vehicles according to the coordinates and speeds of the predicted vehicle and the surrounding vehicles, and judging vehicle behaviors;inputting each historical track of the vehicle containing the information into the model, encoding time sequence interaction features in the track, extracting spatial features, summarizing the features into context vectors, and inputting the context vectors into an LSTM decoder to generate future track coordinates of the vehicle. According to the method, the problem that feature information generated by vehicle interaction cannot be obtained by using a traditional recurrent neural network is solved, and the prediction precision of the vehicle trajectory is greatly improved.

Description

technical field [0001] The invention belongs to the field of vehicle intelligent driving, and in particular relates to a vehicle trajectory prediction method based on a graph convolutional neural network model. Background technique [0002] With the changes of the times and the development of science and technology, domestic and foreign researchers have deepened their research on the control decision-making of intelligent driving vehicles. To safely and efficiently navigate complex traffic scenarios populated by human drivers, intelligent driving vehicles must have the initiative, such as deciding when to change lanes, overtake or slow down to allow other vehicles to merge. This requires intelligent driving vehicles to have some ability to predict the trajectories of themselves and surrounding vehicles, so that they can actively take measures to avoid such risks before interacting with surrounding vehicles. [0003] At present, the vehicle trajectory prediction method mainl...

AI Technical Summary

Problems solved by technology

The model established by long-short-term memory neural network and convolutional neural network only considers spatial information and temporal information, and it is difficult to express this implicit relationship.

Images