DuETA: Traffic Congestion Propagation Pattern Modeling via Efficient Graph Learning for ETA Prediction at Baidu Maps

Abstract

Estimated time of arrival (ETA) prediction, also known as travel time estimation, is a fundamental task for a wide range of intelligent transportation applications, such as navigation, route planning, and ride-hailing services. To accurately predict the travel time of a route, it is essential to take into account both contextual and predictive factors, such as spatial-temporal interaction, driving behavior, and traffic congestion propagation inference. The ETA prediction models previously deployed at Baidu Maps have addressed the factors of spatial-temporal interaction (ConSTGAT) and driving behavior (SSML). In this work, we focus on modeling traffic congestion propagation patterns to improve ETA performance. Traffic congestion propagation pattern modeling is challenging, and it requires accounting for impact regions over time and cumulative effect of delay variations over time caused by traffic events on the road network. In this paper, we present a practical industrial-grade ETA prediction framework named DuETA. Specifically, we construct a congestion-sensitive graph based on the correlations of traffic patterns, and we develop a route-aware graph transformer to directly learn the long-distance correlations of the road segments. This design enables DuETA to capture the interactions between the road segment pairs that are spatially distant but highly correlated with traffic conditions. Extensive experiments are conducted on large-scale, real-world datasets collected from Baidu Maps. Experimental results show that ETA prediction can significantly benefit from the learned traffic congestion propagation patterns. In addition, DuETA has already been deployed in production at Baidu Maps, serving billions of requests every day. This demonstrates that DuETA is an industrial-grade and robust solution for large-scale ETA prediction services.

arXiv commentTo appear at CIKM 2022

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Deep Learning using Rectified Linear Units (ReLU)
• Graph Neural Network for Traffic Forecasting: A Survey
• Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions
• Simple and Deep Graph Convolutional Networks
• ETA Prediction with Graph Neural Networks in Google Maps
• Understanding the Impact of the COVID-19 Pandemic on Transportation-related Behaviors with Human Mobility Data
• Decoupling the Depth and Scope of Graph Neural Networks
• 3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting
• Predictive Analytics for Enhancing Travel Time Estimation in Navigation Apps of Apple, Google, and Microsoft
• Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting

Cited by in corpus (6)

• Scalable Transformer for High Dimensional Multivariate Time Series Forecasting
• DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation
• LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating
• A Preference-aware Meta-optimization Framework for Personalized Vehicle Energy Consumption Estimation
• CAMETA: Conflict-Aware Multi-Agent Estimated Time of Arrival Prediction for Mobile Robots
• A Spatiotemporal Adaptive Local Search Method for Tracking Congestion Propagation in Dynamic Networks