The path inference filter: model-based low-latency map matching of probe vehicle data

Abstract

We consider the problem of reconstructing vehicle trajectories from sparse sequences of GPS points, for which the sampling interval is between 10 seconds and 2 minutes. We introduce a new class of algorithms, called altogether path inference filter (PIF), that maps GPS data in real time, for a variety of trade-offs and scenarios, and with a high throughput. Numerous prior approaches in map-matching can be shown to be special cases of the path inference filter presented in this article. We present an efficient procedure for automatically training the filter on new data, with or without ground truth observations. The framework is evaluated on a large San Francisco taxi dataset and is shown to improve upon the current state of the art. This filter also provides insights about driving patterns of drivers. The path inference filter has been deployed at an industrial scale inside the Mobile Millennium traffic information system, and is used to map fleets of data in San Francisco, Sacramento, Stockholm and Porto.

Preprint, 23 pages and 23 figures

References in corpus (1)

• Travel time estimation for ambulances using Bayesian data augmentation

Cited by in corpus (16)

• Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities
• Travel time reliability in transportation networks: A review of methodological developments
• DeepIST: Deep Image-based Spatio-Temporal Network for Travel Time Estimation
• Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning
• Sparse Travel Time Estimation from Streaming Data
• A Simple Baseline for Travel Time Estimation using Large-Scale Trip Data
• Spatio-Temporal Dual Graph Neural Networks for Travel Time Estimation
• Map Matching based on Conditional Random Fields and Route Preference Mining for Uncertain Trajectories
• HTTE: A Hybrid Technique For Travel Time Estimation In Sparse Data Environments
• Bayesian inference for link travel time correlation of a bus route
• Efficient Dynamic Programming Solution to a Platoon Coordination Merge Problem With Stochastic Travel Times
• Travel Time Prediction from Sparse Open Data
• Empirical validation of network learning with taxi GPS data from Wuhan, China
• A CAV-based perimeter-free regional traffic control strategy utilizing existing parking infrastructure
• Traffic Predictive Control from Low-Rank Structure
• Graph-based Proprioceptive Localization Using a Discrete Heading-Length Feature Sequence Matching Approach