Driver-Adaptive Distance-Weighted Social Tensor for Vehicle Trajectory Prediction

This repository contains the code and experiments created for the course project of Urban Computing at Leiden Univeristy. The project investiages distance-weighted interaction modelling based on driver behavor for vehicle trajectory prediction and extends the Convolutional Social Pooling approach proposed by Deo and Rivedi (2018):

@inproceedings{deo2018convolutional,
  author = {Deo, Nachiket and Trivedi, Mohan},
  title = {Convolutional Social Pooling for Vehicle Trajectory Prediction},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year = {2018},
  month = {June},
  doi = {10.1109/CVPRW.2018.00196}
}