TAS-TsC: A Data-Driven Framework for Estimating Time of Arrival Using Temporal-Attribute-Spatial Tri-space Coordination of Truck Trajectories

TL;DR

This paper introduces TAS-TsC, a novel data-driven framework that combines temporal, attribute, and spatial features to improve truck ETA estimation from GPS trajectories, addressing data sparsity and inter-trajectory dependencies.

Contribution

The paper presents a new multi-space coordination framework with modules for temporal learning, attribute extraction, and spatial fusion, enhancing ETA prediction accuracy.

Findings

Outperforms existing ETA estimation methods on real datasets.

Effectively captures temporal dependencies and trajectory interactions.

Demonstrates robustness to data sparsity and variable sequence lengths.

Abstract

Accurately estimating time of arrival (ETA) for trucks is crucial for optimizing transportation efficiency in logistics. GPS trajectory data offers valuable information for ETA, but challenges arise due to temporal sparsity, variable sequence lengths, and the interdependencies among multiple trucks. To address these issues, we propose the Temporal-Attribute-Spatial Tri-space Coordination (TAS-TsC) framework, which leverages three feature spaces-temporal, attribute, and spatial-to enhance ETA. Our framework consists of a Temporal Learning Module (TLM) using state space models to capture temporal dependencies, an Attribute Extraction Module (AEM) that transforms sequential features into structured attribute embeddings, and a Spatial Fusion Module (SFM) that models the interactions among multiple trajectories using graph representation learning.These modules collaboratively learn trajectory embeddings, which are then used by a Downstream Prediction Module (DPM) to estimate arrival times. We validate TAS-TsC on real truck trajectory datasets collected from Shenzhen, China, demonstrating its superior performance compared to existing methods.