Traffic signal control is important for intersection safety and efficiency. However, most traffic signal control methods are designed for individual intersections or corridors. Although some adaptive control systems have been developed, the methods used are often proprietary and not published, making it difficult to evaluate their effectiveness. This study proposes an adaptive multi-input and multi-output traffic signal control method that not only can improve network-wide traffic operations in terms of reduced traffic delay and energy consumption, but also is more computationally feasible than existing centralized signal control methods. Considering intersection interactions, a linear dynamic traffic system model was built and adaptively updated to reflect how the signal control input of each intersection affects network-wide vehicle travel delay. Based on the system model, an adaptive linear-quadratic regulator (LQR) was designed to minimize both traffic delay and incremental changes in the control input. The proposed control method was evaluated in a microscopic traffic simulation environment with a 35-intersection network of Bellevue City, Washington. Simulation results show that the proposed method had shorter average traffic delays in the network when compared with the traffic delays controlled by the state-of-the-art max-pressure, self-organizing traffic lights, and independent deep Q network methods.

A resilient control system is expected to have the capacity to restore the desired system stability and tracking performance in the presence of uncertain system faults such as actuator failures. While redundant actuators are used for actuator failure accommodation, uncertain actuator failures, whose failure time, pattern, and values may be unknown, can bring new challenges to feedback control design as such uncertain failures can introduce large structural, parametric, and actuation uncertainties. Two technical issues are associated with using redundant actuators: how redundant actuators should be coordinated for effective failure compensation control, and how a feedback control law should be adaptively designed to compensate uncertain actuator failures. In this paper, we present a tutorial on direct adaptive failure compensation-based solutions to these issues for different types of control systems: state tracking using state feedback, output tracking using state feedback or output feedback, for linear, non-linear, and multi-input multi-output systems. We give an overview on such adaptive actuator failure compensation designs which have special capacities to effectively use actuation redundancy to handle uncertain actuator failures, using either direct or indirect adaptive control approaches for direct adaptive actuator failure compensation without explicit failure detection, for fast and effective failure accommodation.

In this paper, an adaptive failure compensation problem is addressed for high-speed trains with longitudinal dynamics and traction system actuator failures. Considered the time-varying parameters of the train motion dynamics caused by time-varying friction characteristics, a new piecewise constant model is introduced to describe the longitudinal dynamics with variable parameters. For both the healthy piecewise constant system and the system with actuator failures, the adaptive controller structure and conditions are derived to achieve the plant-model matching. The adaptive laws are designed to update the adaptive controller parameters, in the presence of the system piecewise constant parameters and actuator failure parameters which are unknown. Based on Lyapunov functions, the closed-loop stability and asymptotic state tracking are proved. Simulation results on a high-speed train model are presented to illustrate the performance of the developed adaptive actuator failure compensation control scheme.

This article proposes a new traffic signal control algorithm to deal with unknown-traffic-system uncertainties and reduce delays in vehicle travel time. Unknown-traffic-system dynamics are approximated using a recurrent neural network (NN). To accurately identify the traffic system model, an online-learning scheme is developed to switch among a set of candidate NNs (i.e., multiple-model NNs) based on their estimation errors. Then, a bank of optimal signal-timing controllers is designed based on the online identification of the traffic system. Simulation studies have been carried out for the obtained control strategies using multiple-model NNs, and the desired results have been obtained. Moreover, compared with the widely used actuated traffic signal control schemes, it is shown that the proposed method can reduce vehicle travel delays and improve traffic system robustness.