BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem

2025-10-21

AI Summary

Estimating high-dimensional origin-destination (OD) demand from sparse sensor data in large-scale urban road networks constitutes a computationally expensive, stochastic, and non-differentiable inverse optimization problem. Method: This paper introduces BO4Mob—the first Bayesian optimization (BO) benchmark framework tailored for urban traffic inversion. It integrates high-resolution microscopic traffic simulation (SUMO) and encompasses five real-world scenarios with input dimensions up to 10,100. Contribution/Results: BO4Mob establishes a standardized, reproducible, and scalable testbed for high-dimensional stochastic optimization in traffic inversion. It is the first systematic application of BO to ultra-large-scale traffic inversion and supports both algorithmic evaluation and digital twin research. Extensive experiments comparing five optimization methods demonstrate significant differences in computational efficiency, robustness, and estimation accuracy. By providing a rigorous, unified benchmark, BO4Mob introduces a new paradigm for evaluating optimization algorithms in urban computing.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

We introduce extbf{BO4Mob}, a new benchmark framework for high-dimensional Bayesian Optimization (BO), driven by the challenge of origin-destination (OD) travel demand estimation in large urban road networks. Estimating OD travel demand from limited traffic sensor data is a difficult inverse optimization problem, particularly in real-world, large-scale transportation networks. This problem involves optimizing over high-dimensional continuous spaces where each objective evaluation is computationally expensive, stochastic, and non-differentiable. BO4Mob comprises five scenarios based on real-world San Jose, CA road networks, with input dimensions scaling up to 10,100. These scenarios utilize high-resolution, open-source traffic simulations that incorporate realistic nonlinear and stochastic dynamics. We demonstrate the benchmark's utility by evaluating five optimization methods: three state-of-the-art BO algorithms and two non-BO baselines. This benchmark is designed to support both the development of scalable optimization algorithms and their application for the design of data-driven urban mobility models, including high-resolution digital twins of metropolitan road networks. Code and documentation are available at https://github.com/UMN-Choi-Lab/BO4Mob.

Problem

• Benchmarking high-dimensional Bayesian Optimization for urban mobility
• Solving origin-destination travel demand estimation in large networks
• Optimizing computationally expensive stochastic non-differentiable objective functions

Innovation

• Bayesian Optimization for high-dimensional urban mobility
• Benchmark with real-world road network simulations
• Evaluates scalable algorithms for travel demand estimation