Logistics, Graphs, and Transformers: Towards improving Travel Time Estimation
This addresses the fundamental challenge of travel time estimation for logistics, but appears incremental as it applies an existing transformer architecture to a known problem.
The paper tackles the problem of travel time estimation in logistics by proposing a new transformer-based method called TransTTE, aiming to significantly outperform earlier solutions, though no concrete numbers are provided.
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.