Online Adaptive Platoon Control for Connected and Automated Vehicles via Physics Enhanced Residual Learning

2024-12-30

AI Summary

To address the low control accuracy and poor robustness of autonomous vehicle platoons under dynamic disturbances in vehicle-infrastructure cooperative environments, this paper proposes a Physics-Enhanced Residual Learning (PERL) framework. PERL tightly couples a vehicle-dynamics-based physical controller with an online neural network residual learner and incorporates a disturbance-aware adaptive parameter update mechanism, thereby preserving model interpretability while enhancing environmental adaptability. Simulation and real-world experiments demonstrate that PERL reduces cumulative position and velocity errors by up to 58.5% and 40.1%, respectively, compared to pure physics-based models, and by up to 58.4% and 47.7% compared to purely data-driven models. In on-road testing, error reductions reach 72.73% and 99.05%, significantly improving convergence speed and robustness against disturbances.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper introduces a physics enhanced residual learning (PERL) framework for connected and automated vehicle (CAV) platoon control, addressing the dynamics and unpredictability inherent to platoon systems. The framework first develops a physics-based controller to model vehicle dynamics, using driving speed as input to optimize safety and efficiency. Then the residual controller, based on neural network (NN) learning, enriches the prior knowledge of the physical model and corrects residuals caused by vehicle dynamics. By integrating the physical model with data-driven online learning, the PERL framework retains the interpretability and transparency of physics-based models and enhances the adaptability and precision of data-driven learning, achieving significant improvements in computational efficiency and control accuracy in dynamic scenarios. Simulation and robot car platform tests demonstrate that PERL significantly outperforms pure physical and learning models, reducing average cumulative absolute position and speed errors by up to 58.5% and 40.1% (physical model) and 58.4% and 47.7% (NN model). The reduced-scale robot car platform tests further validate the adaptive PERL framework's superior accuracy and rapid convergence under dynamic disturbances, reducing position and speed cumulative errors by 72.73% and 99.05% (physical model) and 64.71% and 72.58% (NN model). PERL enhances platoon control performance through online parameter updates when external disturbances are detected. Results demonstrate the advanced framework's exceptional accuracy and rapid convergence capabilities, proving its effectiveness in maintaining platoon stability under diverse conditions.

Problem

• Connected Autonomous Vehicles
• Formation Control
• Adaptive Adjustment

Innovation

• PERL
• Physics-Informed Neural Networks
• Connected Autonomous Vehicles (CAV) Control