Trajectory Map-Matching in Urban Road Networks Based on RSS Measurements

TL;DR

This paper introduces an RSS-based vehicle trajectory reconstruction method in urban road networks using an HMM-based embedding and speed constraints to improve accuracy amidst noisy and sparse data.

Contribution

It develops a novel HMM-based RSS embedding technique combined with a maximum speed constraint to enhance trajectory inference from RSS data.

Findings

Effective trajectory reconstruction from noisy RSS data

Improved convergence speed with speed-constrained estimation

Captures spatiotemporal dependencies in urban environments

Abstract

This paper proposes an RSS-based approach to reconstruct vehicle trajectories within a road network, enforcing signal propagation rules and vehicle mobility constraints to mitigate the impact of RSS noise and sparsity. The key challenge lies in leveraging latent spatiotemporal correlations within RSS data while navigating complex road networks. To address this, we develop a Hidden Markov Model (HMM)-based RSS embedding (HRE) technique that employs alternating optimization to infer vehicle trajectories from RSS measurements. This model captures spatiotemporal dependencies while a road graph ensures network compliance. Additionally, we introduce a maximum speed-constrained rough trajectory estimation (MSR) method to guide the optimization process, enabling rapid convergence to a favorable local solution.