Recent studies and industry developments indicate that modular autonomous vehicles (MAVs) have the potential to enhance transportation systems by offering vehicles with adjustable capacities en route. However, the practical realization of reliable control during docking/undocking operations remains a significant challenge, primarily due to safety concerns arising from the close proximity of MAVs. This study proposes a safety assurance adaptive model predictive control (SAAMPC) framework to achieve distributed docking/undocking operations for MAVs in uncertain environments. The SAAMPC framework integrates a model predictive control (MPC) controller for trajectory optimization, an adaptive module for dynamic adjustment of control parameters with disturbance, and an adaptive safety assurance module with longitudinal and lateral control barrier functions (CFB) to ensure safe operation during risky and uncertain conditions. The effectiveness of the proposed approach is validated through simulations in Simulink and field tests on a reduced-scale MAV platform. Experimental results validate that the SAAMPC framework successfully ensures smooth and safe vehicle following and robust execution of docking/undocking operations under uncertainties.

While physics models for predicting system states can reveal fundamental insights owing to their parsimonious structure, they may not always yield the most accurate predictions, particularly for complex systems. As an alternative, neural network (NN) models usually yield more accurate predictions; however, they lack interpretable physical insights. To articulate the advantages of both physics and NN models while circumventing their limitations, this study proposes a physics-enhanced residual learning (PERL) framework that adjusts a physics model prediction with a corrective residual predicted from a residual learning NN model. The integration of the physics model preserves interpretability and tremendously reduces the amount of training data compared with pure NN models. We apply PERL to a vehicle trajectory prediction problem with real-world trajectory data of both a human-driven vehicle (HV) and an autonomous vehicle (AV), using an adapted Newell car-following model as the physics model and four kinds of neural networks (Gated Recurrent Unit (GRU), Convolution long short-term memory (CLSTM), Variational Autoencoder (VAE), and the Informer model) as the residual learning model. We compare this PERL model with pure physics models, NN models, and other physics-informed neural network (PINN) models. The results reveal that PERL yields the best prediction when the training data are small. The PERL model converges quickly during training. Moreover, compared with the NN and PINN models, the PERL model requires fewer parameters to achieve similar predictive performance. A sensitivity analysis revealed that the PERL model consistently outperforms the physics models, NN models and PINN models with different physics and residual learning models given a small training dataset. Among these, the PERL model based on CLSTM achieved the most accurate predictions.

Real-time vehicle prediction is crucial in autonomous driving technology, as it allows adjustments to be made in advance to the driver or the vehicle, enabling them to take smoother driving actions to avoid potential collisions. This study proposes a physics-enhanced residual learning (PERL)-based predictive control method to mitigate traffic oscillation in the mixed traffic environment of connected and automated vehicles (CAVs) and human-driven vehicles (HDVs). The introduced model includes a prediction model and a CAV controller. The prediction model is responsible for forecasting the future behavior of the preceding vehicle on the basis of the behavior of preceding vehicles. This PERL model combines physical information (i.e., traffic wave properties) with data-driven features extracted from deep learning techniques, thereby precisely predicting the behavior of the preceding vehicle, especially speed fluctuations, to allow sufficient time for the vehicle/driver to respond to these speed fluctuations. For the CAV controller, we employ a model predictive control (MPC) model that considers the dynamics of the CAV and its following vehicles, improving safety and comfort for the entire platoon. The proposed model is applied to an autonomous driving vehicle through vehicle-in-the-loop (ViL) and compared with real driving data and three benchmark models. The experimental results validate the proposed method in terms of damping traffic oscillation and enhancing the safety and fuel efficiency of the CAV and the following vehicles in mixed traffic in the presence of uncertain human-driven vehicle dynamics and actuator lag.

Motivated by the promising benefits of connected and autonomous vehicles (CAVs) in improving fuel efficiency, mitigating congestion, and enhancing safety, numerous theoretical models have been proposed to plan CAV multiple-step trajectories (time–specific speed/location trajectories) to accomplish various operations. However, limited efforts have been made to develop proper trajectory control techniques to regulate vehicle movements to follow multiple-step trajectories and test the performance of theoretical trajectory planning models with field experiments. Without an effective control method, the benefits of theoretical models for CAV trajectory planning can be difficult to harvest. This study proposes an online learning-based model predictive vehicle trajectory control structure to follow time–specific speed and location profiles. Unlike single-step controllers that are dominantly used in the literature, a multiple-step model predictive controller is adopted to control the vehicle’s longitudinal movements for higher accuracy. The model predictive controller output (speed) cannot be interpreted by vehicles. A reinforcement learning agent is used to convert the speed value to the vehicle’s direct control variable (i.e., throttle/brake). The reinforcement learning agent captures real-time changes in the operating environment. This is valuable in saving parameter calibration resources and improving trajectory control accuracy. A line tracking controller keeps vehicles on track. The proposed control structure is tested using reduced-scale robot cars. The adaptivity of the proposed control structure is demonstrated by changing the vehicle load. Then, experiments on two fundamental CAV platoon operations (i.e., platooning and split) show the effectiveness of the proposed trajectory control structure in regulating robot movements to follow time–specific reference trajectories.