Bayesian Calibration of the Intelligent Driver Model
arXiv:2210.03571 · doi:10.1109/TITS.2024.3354102
Abstract
Accurate calibration of car-following models is essential for understanding human driving behaviors and implementing high-fidelity microscopic simulations. This work proposes a memory-augmented Bayesian calibration technique to capture both uncertainty in the model parameters and the temporally correlated behavior discrepancy between model predictions and observed data. Specifically, we characterize the parameter uncertainty using a hierarchical Bayesian framework and model the temporally correlated errors using Gaussian processes. We apply the Bayesian calibration technique to the intelligent driver model (IDM) and develop a novel stochastic car-following model named memory-augmented IDM (MA-IDM). To evaluate the effectiveness of MA-IDM, we compare the proposed MA-IDM with Bayesian IDM in which errors are assumed to be i.i.d., and our simulation results based on the HighD dataset show that MA-IDM can generate more realistic driving behaviors and provide better uncertainty quantification than Bayesian IDM. By analyzing the lengthscale parameter of the Gaussian process, we also show that taking the driving actions from the past five seconds into account can be helpful in modeling and simulating the human driver's car-following behaviors.
arXiv commentIEEE Transactions on Intelligent Transportation Systems (2024)
References in corpus (14)
- Congested Traffic States in Empirical Observations and Microscopic Simulations
- Delays, Inaccuracies and Anticipation in Microscopic Traffic Models
- Calibrating Car-Following Models using Trajectory Data: Methodological Study
- Memory effects in microscopic traffic models and wide scattering in flow-density data
- Microscopic Calibration and Validation of Car-Following Models -- A Systematic Approach
- Social Interactions for Autonomous Driving: A Review and Perspectives
- Learning and Inferring a Driver's Braking Action in Car-Following Scenarios
- A Generative Car-following Model Conditioned On Driving Styles
- An Open-Source Microscopic Traffic Simulator
- Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios
- Physics-augmented models to simulate commercial adaptive cruise control (ACC) systems
- Characterizing driver heterogeneity within stochastic traffic simulation
- Identifiability of car-following dynamic
- Bayesian calibration of traffic flow fundamental diagrams using Gaussian processes