Cooperative adaptive cruise control (CACC) is a smart transportation solution to alleviate traffic congestion and enhance road safety. The performance of CACC systems can be remarkably affected by communication time delays, and traditional control methods often compromise control performance by adjusting control gains to maintain system stability. In this article, we present a study on the stability of a CACC system in the presence of time delays and highlight the tradeoff between control performance and tuning controller gains to address increasing delays. We propose a novel approach incorporating a neural network module called the deep time delay filter (DTDF) to overcome this limitation. The DTDF leverages the assumption that time delays primarily originate from the communication layer of the CACC network, which can be subject to adversarial delays of varying magnitudes. By considering time-delayed versions of the car states and predicting the present (un-delayed) states, the DTDF compensates for the effects of communication delays. The proposed approach combines classical control techniques with machine learning, offering a hybrid control system that excels in explainability and robustness to unknown parameters. We conduct comprehensive experiments using various deep learning architectures to train and evaluate the DTDF models. Our experiments utilize a robot platform consisting of MATLAB, Simulink, the Optitrack motion capture system, and the Qbot2e robots. Through these experiments, we demonstrate that when appropriately trained, our system can effectively mitigate the adverse effects of constant time delays and outperforms a traditional CACC baseline in control performance. This experimental comparison, to the best of the authors’ knowledge, is the first of its kind in the context of a hybrid machine learning CACC system. We thoroughly explore initial conditions and range policy parameters to evaluate our system under various experimental scenarios. By providing detailed insights and experimental results, we aim to contribute to the advancement of CACC research and highlight the potential of hybrid machine learning approaches in improving the performance and reliability of CACC systems.

This paper extends the results in [1] considering time delays in Standard Car Following models (CFMs). In [1], connected vehicles are characterized with CFMs models and controlled using linear string analysis to stabilize single-lane car following of human-driven vehicles (HDVs). In this paper, we revisit stability and safety conditions for traffic considering time delays due to lags in the input signals. We perform plant stability and string stability analysis to derive these conditions. Then we obtain the optimal number of HDVs that can be stabilized using one autonomous vehicle. Numerical simulations are provided to implement a case study on Intelligent Driver Model to discuss the influence of time delays that arise on HDVs and the autonomous vehicle on optimal number of HDVs that can be stabilized using one autonomous vehicle.

In this paper, we consider periodic communication delays within the connected autonomous vehicles platoon. Periodic signals are fundamentally simple to create, and in this study we analyze whether certain amplitude or frequencies can cause instability. This is important as we discover in this study, the classical method of replacing time-varying delays with constant delays does not capture the complex stability boundary of periodic time delays which could be exploited by attackers to cause instability in the vehicle platoon. We use the semi-discretization method to obtain plant stability. Then, we take the average value of the time delay functions to characterize the maximal admissible delay region such that the time-delayed system remains stable and provide string stability analysis. Through numerical simulations, we verify the analytical results. We construct stability charts in different parameter spaces to explore the effects of the model parameters on the system stability. A specific range of frequencies was found that could destabilize the connected autonomous vehicle platoon.