Logistics, Graphs, and Transformers: Towards improving Travel Time Estimation

Natalia Semenova, Vadim Porvatov, Vladislav Tishin, Artyom Sosedka, Vladislav Zamkovoy
7/12/2022
cs.LGcs.AI

No official code found. Best implementation: Vloods/TransTTE_demo (6 stars, last commit 2023-04-06).

Abstract

The problem of travel time estimation is widely considered as the fundamental challenge of modern logistics. The complex nature of interconnections between spatial aspects of roads and temporal dynamics of ground transport still preserves an area to experiment with. However, the total volume of currently accumulated data encourages the construction of the learning models which have the perspective to significantly outperform earlier solutions. In order to address the problems of travel time estimation, we propose a new method based on transformer architecture - TransTTE.

View on arXivView PDF

Code Implementations(1)

Vloods/TransTTE_demoCommunity100%
62CSS, HTMLFeb 14, 20223 years ago

Similar Papers

GCT-TTE: Graph Convolutional Transformer for Travel Time Estimation

92% match1 repo102023

DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation

79% match1 repo32024

Multitask Weakly Supervised Learning for Origin Destination Travel Time Estimation

79% match2023

Trajectory Data Mining and Trip Travel Time Prediction on Specific Roads

77% match2024

RLER-TTE: An Efficient and Effective Framework for En Route Travel Time Estimation with Reinforcement Learning

77% match2025

Transfer Learning Study of Motion Transformer-based Trajectory Predictions

77% match2024

Cite this paper

@article{semenova2022logistics,
  title  = {Logistics, Graphs, and Transformers: Towards improving Travel Time Estimation},
  author = {Natalia Semenova and Vadim Porvatov and Vladislav Tishin and Artyom Sosedka and Vladislav Zamkovoy},
  year   = {2022},
  eprint = {2207.05835},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.05835v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.05835.svg)](https://codeofpaper.com/paper/2207.05835)

Discussion