In order to improve the safety of pedestrian interaction in complex traffic scenes, this paper proposed a pedestrian trajectory prediction algorithm SAN-GAN based on social-GAN. The algorithm firstly took the pedestrian's historical location information and head information as input, obtained the hidden feature information of the pedestrian through the trajectory generator LSTM network, captured the dynamic changes of the pedestrian's visual field based on the pedestrian visual field module, built a fan-shaped visual field for all pedestrians and filtered the valid information, thus driving the neural network model to predict future trajectory changes of pedestrians. By comparing SAN-GAN with LSTM, social-LSTM, social-GAN and other trajectory prediction algorithms, the results show that the SAN-GAN algorithm reduces the ADE by an average of 65.8%, 51.2% and 10.7%, and the FDE by an average of 73.6%, 60.9% and 10.4%, respectively, in predicting the pedestrian trajectory for 3.2 s. The SAN-GAN is effective in predicting the future trajectory of pedestrians interacting in complex traffic environments compared to other algorithms.

[2022-08-22] Accepted Paper /doc/2022.06.0289/v1

[2023-01-05] Printed Article /doc/2022.06.0289/v2