TR2023-094
3T-Net: Transformer Encoders for Destination Prediction
-
- "3T-Net: Transformer Encoders for Destination Prediction", The Chinese Control Conference, DOI: 10.23919/CCC58697.2023.10240616, July 2023.BibTeX TR2023-094 PDF Presentation
- @inproceedings{Zhang2023jul3,
- author = {Zhang, Jing and Nikovski, Daniel and Kojima, Takuro},
- title = {3T-Net: Transformer Encoders for Destination Prediction},
- booktitle = {The Chinese Control Conference},
- year = 2023,
- month = jul,
- doi = {10.23919/CCC58697.2023.10240616},
- url = {https://www.merl.com/publications/TR2023-094}
- }
,
- "3T-Net: Transformer Encoders for Destination Prediction", The Chinese Control Conference, DOI: 10.23919/CCC58697.2023.10240616, July 2023.
-
MERL Contact:
-
Research Areas:
Abstract:
The need for accurate and timely destination prediction arises in many transportation applications. We formulate destination prediction as a multivariate time series classification problem, and leverage part of the core components of the Transformer network to build a new deep neural network model exclusively for this task. The key building block of our model consists of Two Towers of Transformer encoders, and we call it “3T-Net.” Through extensive comparison experiments on a simulated indoor trajectories data set, we show that 3T-Net performs better or close to other investigated state-of-the-art deep learning based models. Our model can also be used for outdoor destination prediction scenarios and more general multivariate time series classification problems.