Problem
Research questions and friction points this paper is trying to address.
traffic calibration
black-box optimization
digital twins
microscopic traffic models
rugged objective landscape
FLAT: Smoothing the Rugged Landscape for Learnable, Sample-Efficient Traffic Calibration
🤖 AI Summary
This study addresses the high computational cost of black-box optimization and the low sample efficiency caused by rugged objective landscapes in microscopic traffic model calibration. To overcome these challenges, we propose a behavior fingerprint-based smoothing calibration framework. Methodologically, this work pioneers the decoupling of objective geometric smoothing from sequential sampling allocation, reconstructing the parameter error landscape via an eight-dimensional behavioral fingerprint. By integrating ensemble surrogate models, such as Gaussian processes, with an annealed lower confidence bound acquisition strategy, the framework achieves efficient optimization. We further demonstrate that the performance gains stem from improved landscape structure rather than increased model capacity. Experimental evaluations across six real-world scenarios show that the proposed method consistently outperforms baselines, reducing simulation overhead by up to 4.4 times while significantly mitigating behavioral errors.
📝 Abstract
Calibrating microscopic traffic models for digital twins is an expensive black-box optimization problem: tuning car-following and lane-changing parameters requires a full simulation run, affording only a tight budget per recalibration window. Matching raw trajectories yields a rugged objective that sparse surrogates cannot learn, reducing sequential acquisition to near-random probing. We present FLAT, which couples what to optimize with where to sample next. An eight-dimensional behavioral fingerprint smooths the parameter-error landscape, making the objective learnable from a few dozen samples; annealed lower-confidence-bound (LCB) acquisition then spends each remaining run where it most reduces error. The surrogate, interchangeable among a Gaussian process (GP), random forest (RF), or multi-layer-perceptron (MLP) ensemble, plugs into the same LCB loop. Across six heterogeneous real-world scenes, FLAT-GP achieves the lowest scene-averaged behavioral error, winning 6/6 scenes against SPSA, GA, and CMA-ES and 5/6 against TPE under the matched budget. Some baselines need up to 4.4 times more simulations to match. Ablations show objective choice shifts final behavioral error by 81% on average, removing sequential LCB raises the six-scene mean by 20%, and surrogate choice shifts it by at most 4.2%, confirming gains trace to objective geometry and sequential allocation rather than surrogate capacity.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Traffic Calibration
Behavioral Fingerprint
Black-box Optimization
Lower Confidence Bound
Sample Efficiency
🔎 Similar Papers
No similar papers found.
