Physics-informed platooning with learning-augmented calibration and compensation: a real-world study

Abstract

Autonomous vehicle platooning improves overall energy efficiency and enhances road capacity through close-range cooperative driving. However, practical deployment under complex real-world conditions remains challenging due to sensor noise, model uncertainties, and actuator nonlinearities. This paper presents a hierarchical control framework that integrates multi-source sensor fusion and a controller combining longitudinal Model Predictive Control (MPC) with Lateral Feedforward-Feedback Control (LFFC) with data-driven improvement. First, a prediction-correction fusion module combines wheel odometry (ODOM), Inertial Measurement Unit (IMU), and GPS measurements to obtain continuous and globally consistent vehicle state estimates. Second, an MPC-LFFC-based physical controller is developed, where longitudinal MPC optimizes velocity corrections and lateral LFFC combines curvature feedforward with proportional feedback of heading and lateral errors. Third, a data-driven improvement module comprises an offline Conservative Q-Learning (CQL) agent that automatically calibrates controller parameters, and a neural residual learning network that predicts feedforward compensation. Extensive experiments on a real-world vehicle platooning platform demonstrate that the proposed framework consistently outperforms baselines, achieving a position RMSE of 0.0781 m and a 30.66% improvement in linear velocity tracking.