A Traffic Adapative Physics-informed Learning Control for Energy Savings of Connected and Automated Vehicles

TL;DR

This paper introduces a traffic adaptive physics-informed learning control framework for connected and automated vehicles that improves real-time energy efficiency and reduces computational load by combining model-based principles with learning methods.

Contribution

It develops a novel traffic adaptive augmented state space system and a physics-informed learning control framework that enhances robustness and efficiency in vehicle energy management.

Findings

Achieves 9% energy savings in real-world data scenarios.

Reduces real-time computational requirements compared to traditional methods.

Maintains car-following behavior comparable to model-based control.

Abstract

Model predictive control has emerged as an effective approach for real-time optimal control of connected and automated vehicles. However, nonlinear dynamics of vehicle and traffic systems make accurate modeling and real-time optimization challenging. Learning-based control offer a promising alternative, as they adapt to environment without requiring an explicit model. For learning control framework, an augmented state space system design is necessary since optimal control depends on both the ego vehicle's state and predicted states of other vehicles. This work develops a traffic adaptive augmented state space system that allows the control strategy to intelligently adapt to varying traffic conditions. This design ensures that while different vehicle trajectories alter initial conditions, the system dynamics remain independent of specific trajectories. Additionally, a physics-informed learning control framework is presented that combines value function from Bellman's equation with derivative of value functions from Pontryagin's Maximum Principle into a unified loss function. This method aims to reduce required training data and time while enhancing robustness and efficiency. The proposed control framework is applied to car-following scenarios in real-world data calibrated simulation environments. The results show that this learning control approach alleviates real-time computational requirements while achieving car-following behaviors comparable to model-based methods, resulting in 9% energy savings in scenarios not previously seen in training dataset.