DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation

2024-08-23

arXiv.org

AI Summary

This work addresses uncertainty quantification in origin-destination (OD) travel time estimation (TTE). We propose a novel paradigm that jointly optimizes most-probable path selection and time-varying, link-level uncertainty modeling. Methodologically, we introduce the first deep reinforcement learning–driven path alignment mechanism, integrated with a context-aware Mixture-of-Experts (MoE) framework for uncertainty modeling, and calibrate statistically guaranteed confidence intervals via Hoeffding’s upper confidence bound. Experiments on two real-world traffic datasets demonstrate that our approach outperforms state-of-the-art methods: it improves 95% confidence interval coverage by 12.7 percentage points and reduces mean absolute error by 9.3%, while ensuring strong generalization capability and statistical reliability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Uncertainty quantification in travel time estimation (TTE) aims to estimate the confidence interval for travel time, given the origin (O), destination (D), and departure time (T). Accurately quantifying this uncertainty requires generating the most likely path and assessing travel time uncertainty along the path. This involves two main challenges: 1) Predicting a path that aligns with the ground truth, and 2) modeling the impact of travel time in each segment on overall uncertainty under varying conditions. We propose DutyTTE to address these challenges. For the first challenge, we introduce a deep reinforcement learning method to improve alignment between the predicted path and the ground truth, providing more accurate travel time information from road segments to improve TTE. For the second challenge, we propose a mixture of experts guided uncertainty quantification mechanism to better capture travel time uncertainty for each segment under varying contexts. Additionally, we calibrate our results using Hoeffding's upper-confidence bound to provide statistical guarantees for the estimated confidence intervals. Extensive experiments on two real-world datasets demonstrate the superiority of our proposed method.

Problem

• Travel Time Estimation
• Uncertainty Quantification
• Route Optimization

Innovation

• Deep Reinforcement Learning
• Uncertainty Quantification
• Hoeffding's Bound