A Physics-Informed Deep Learning Paradigm for Car-Following Models

Abstract

Car-following behavior has been extensively studied using physics-based models, such as the Intelligent Driver Model. These models successfully interpret traffic phenomena observed in the real-world but may not fully capture the complex cognitive process of driving. Deep learning models, on the other hand, have demonstrated their power in capturing observed traffic phenomena but require a large amount of driving data to train. This paper aims to develop a family of neural network based car-following models that are informed by physics-based models, which leverage the advantage of both physics-based (being data-efficient and interpretable) and deep learning based (being generalizable) models. We design physics-informed deep learning car-following (PIDL-CF) architectures encoded with two popular physics-based models - IDM and OVM, on which acceleration is predicted for four traffic regimes: acceleration, deceleration, cruising, and emergency braking. Two types of PIDL-CFM problems are studied, one to predict acceleration only and the other to jointly predict acceleration and discover model parameters. We also demonstrate the superior performance of PIDL with the Next Generation SIMulation (NGSIM) dataset over baselines, especially when the training data is sparse. The results demonstrate the superior performance of neural networks informed by physics over those without. The developed PIDL-CF framework holds the potential for system identification of driving models and for the development of driving-based controls for automated vehicles.

References in corpus (17)

• Congested Traffic States in Empirical Observations and Microscopic Simulations
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Dissipation of stop-and-go waves via control of autonomous vehicles: Field experiments
• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Deep Learning of Vortex Induced Vibrations
• Microscopic Calibration and Validation of Car-Following Models -- A Systematic Approach
• Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanics
• An LSTM-Based Autonomous Driving Model Using Waymo Open Dataset
• Waymo Driverless Car Data Analysis and Driving Modeling using CNN and LSTM
• Stabilizing Traffic via Autonomous Vehicles: A Continuum Mean Field Game Approach
• Modeling Stochastic Microscopic Traffic Behaviors: a Physics Regularized Gaussian Process Approach
• Physics-Informed Deep Learning for Traffic State Estimation
• Scaling Limit of Neural Networks with the Xavier Initialization and Convergence to a Global Minimum
• Model-Informed Machine Learning for Multi-component T2 Relaxometry

Cited by in corpus (15)

• Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey
• A Physics-Informed Deep Learning Paradigm for Traffic State and Fundamental Diagram Estimation
• STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
• A Generative Car-following Model Conditioned On Driving Styles
• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• Car-Following Models: A Multidisciplinary Review
• Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control
• Enhancing System-Level Safety in Mixed-Autonomy Platoon via Safe Reinforcement Learning
• Fourier neural operator for learning solutions to macroscopic traffic flow models: Application to the forward and inverse problems
• A Knowledge-Informed Deep Learning Paradigm for Generalizable and Stability-Optimized Car-Following Models
• Inverting the Fundamental Diagram and Forecasting Boundary Conditions: How Machine Learning Can Improve Macroscopic Models for Traffic Flow
• Knowledge-data fusion dominated vehicle platoon dynamics modeling and analysis: A physics-encoded deep learning approach
• Mitigating Traffic Oscillations in Mixed Traffic Flow with Scalable Deep Koopman Predictive Control
• RACER: Rational Artificial Intelligence Car-following-model Enhanced by Reality
• Reconstructing Physics-Informed Machine Learning for Traffic Flow Modeling: a Multi-Gradient Descent and Pareto Learning Approach