With the development of automatic driving technology and the internet of vehicles, platooning based on control of connected autonomous vehicles has become one of the most promising approaches to improve traffic efficiency. This paper studies the control problem of mixed vehicle platoons consisting of human-driven vehicles and connected autonomous vehicles. Firstly, we propose a data-driven method to model mixed vehicle platoons based on Koopman operator theory. This method gives a way to represent the mixed vehicle platoon by a linear model in a high-dimensional space, the approximation of which is obtained by a neural network framework. Secondly, we employ model predictive control (MPC) to address the platoon control problem of mixed vehicle platoons, where both centralized MPC and distributed MPC algorithms are designed. Finally, the effectiveness of the data-driven modeling method and the centralized/distributed MPC algorithms is verified by numerical simulations. It is revealed that the proposed data-driven DMPC algorithm exhibits comparable control performance with less computation cost compared with the centralized MPC algorithm, and it shows faster convergence speed than the nonlinear model based DMPC algorithm.

We develop backstepping state feedback control to stabilize a moving shockwave in a freeway segment under bilateral boundary actuations of traffic flow. A moving shockwave, consisting of light traffic upstream of the shockwave and heavy traffic downstream, is usually caused by changes of local road situations. The density discontinuity travels upstream and drivers caught in the shockwave experience transitions from free to congested traffic. Boundary control design in this paper brings the shockwave front to a static setpoint position, hindering the upstream propagation of traffic congestion. The traffic dynamics are described with Lighthill-Whitham-Richard (LWR) model, leading to a system of two first-order hyperbolic partial differential equations (PDEs). Each represents the traffic density of a spatial domain segregated by the moving interface. By Rankine-Hugoniot condition, the interface position is driven by flux discontinuity and thus governed by an ordinary differential equation (ODE) dependent on the PDE states. The control objective is to stabilize both the PDE states of traffic density and the ODE state of moving shock position to setpoint values. Using delay representation and backstepping method, we design predictor feedback controllers to cooperatively compensate statedependent input delays to the ODE. From Lyapunov stability analysis, we show local stability of the closed-loop system in H $^1$ norm with an arbitrarily fast convergence rate. The stabilization result is demonstrated by a numerical simulation and the total travel time of the open-loop system is reduced by 12% in the closed-loop.

Recent research has demonstrated that Vision Transformers (ViTs) are capable of comparable or even better performance than convolutional neural network (CNN) baselines. The differences in their structural designs are obvious, but our understanding of the differences in their feature representations remains limited. In this work, we propose several techniques to achieve high-quality visualization of representations in ViTs. Both qualitative and quantitative experiments show that our technical improvements can observably improve ViT visualization quality compared to previous studies. Furthermore, we conduct visualizations to explore the disparities between ViTs and CNNs pre-trained on ImageNet1K, revealing three intriguing properties of ViTs: (a) ViT feature propagation retains image detail information with minimal loss, whereas CNNs discard most image details for class discrimination. (b) Different from CNNs, object-related features do not show in ViT higher layers, suggesting that class-discriminative features may not be required for ViT classification. (c) Our visualization-assisted texture-bias experiment reveals that both ViTs and CNNs exhibit texture bias, of which ViTs seem to be more biased towards local textures.

The boundary feedback control of networks of freeway traffic is considered in this article by means of the partial differential equation (PDE)-based techniques. The control and measurements are all located at the boundaries of each link. We have established the boundary control model for the system, a linear hyperbolic system of balance laws, which includes not only the traffic flow dynamics of the network described by combining the linearized Aw–Rascle–Zhang (ARZ) traffic flow model of each link but also the integrated on-ramping metering and variable speed limit control modeled as the boundary condition. As the traffic demand of the network is fluctuated, the boundary input-to-state stability (ISS) controller is designed to suppress the disturbance and regulate the traffic flow into the boundedness regions of the desired states. Based on a novel Lyapunov function, some sufficient conditions in terms of the matrix inequalities are derived for the ISS boundary stabilization in the ${L}^{2}$ -norm. The numerical simulation is given to illustrate the effectiveness of the developed boundary feedback control. Moreover, an interesting traffic experiment is carried out by using the traffic simulation software, AIMSUN, and some specific traffic data are collected and analyzed to verify the feasibility and effectiveness of the boundary control.

This article proposes a new multivehicle cooperative localization approach that combines time of arrival (TOA) with a heuristic simulated annealing extended Kalman filter (SA-EKF) to enhance positioning accuracy and robustness in urban canyons. The method incorporates a path loss model to account for the complex communication environment between vehicles, using TOA measurements for distributed EKF estimation. The integration of a simulated annealing strategy within the method is instrumental in circumventing local minima, thereby facilitating global optimisation. Furthermore, an adaptive weighted filtering correction mechanism is employed to enhance estimation accuracy and system stability. Experimental results conducted on the SUMO simulation platform and in real-world scenarios demonstrate that the proposed method offers certain advantages over existing approaches in complex, noisy environments.