TR2023-011

Estimating Traffic Density Using Transformer Decoders


    •  Wang, Y., Zhang, J., Nikovski, D., Kojima, T., "Estimating Traffic Density Using Transformer Decoders", International Workshop on Statistical Methods and Artificial Intelligence, March 2023.
      BibTeX TR2023-011 PDF
      • @inproceedings{Wang2023mar,
      • author = {Wang, Yinsong and Zhang, Jing and Nikovski, Daniel and Kojima, Takuro},
      • title = {Estimating Traffic Density Using Transformer Decoders},
      • booktitle = {International Workshop on Statistical Methods and Artificial Intelligence},
      • year = 2023,
      • month = mar,
      • url = {https://www.merl.com/publications/TR2023-011}
      • }
  • MERL Contacts:
  • Research Areas:

    Data Analytics, Machine Learning

Abstract:

We propose a combined particle-based density prediction model consisting of three components: trajectory prediction for existing particles, entering particle prediction, and iterative sampling. At initialization, the combined model takes in a set of trajectories for trajectory prediction and a sequence of observation vectors for entering particle prediction. Then, the iterative sampling module generates the density prediction for the next time instance. It will also sample a pool of particles and pass on their trajectories to the next trajectory prediction model for future density prediction.