Reinforcement learning has increasingly showcased its potential in decision-making for the autonomous operation of urban rail transit. However, the inability of reinforcement learning to ensure safety during both the learning and execution phases presents a significant barrier to its practical application. This limitation makes it challenging to implement reinforcement learning in safety-critical domains. In urban rail transit, it is reflected in generating control command sequences that keep the train’s speed consistently below the speed limit. To address this issue, a framework is proposed for intelligent control of autonomous urban rail transit trains, referred to as SSA-DRL (Shield-Searching-Additional-DRL). This framework comprises four modules: a post-posed Shield, a Searching Tree, an Additional Learner, and a DRL framework. It effectively satisfies speed and schedule constraints while optimizing operational processes. The framework is evaluated across sixteen different sections, demonstrating its effectiveness through both basic simulations and additional experiments.

Virtual coupling is regarded as an efficient way to improve the line capacity of rail transportation systems by reducing the spacing between consecutive trains. This paper is the first to compare and assess different distributed model predictive control (MPC) approaches, i.e., cooperative distributed MPC, serial distributed MPC, and decentralized MPC, for virtually coupled trains with a nonlinear train dynamic model. To make a balanced trade-off between computational complexity and efficiency, we also propose and assess convex approximations of the above control approaches. Furthermore, we are the first to introduce the relaxed dynamic programming approach to analyze the stability of the MPC-based nonlinear train control problem. By using the relaxed dynamic programming approach, a distributed stopping criterion with a stability guarantee is developed for the cooperative distributed MPC approach. In real life, masses of trains are different and can change at stations due to changes in passenger loads. This change in mass can significantly affect the dynamics and control of the virtually coupled trains when not taken into account in the control design. Therefore, we explicitly consider heterogeneous train masses when designing MPC approaches. We evaluate the different distributed MPC approaches through case studies based on the data of the Beijing Yizhuang Line. Simulation results indicate that the cooperative distributed MPC approach has the best tracking performance, while the serial distributed MPC approach can reduce communication requirements and computation capabilities with sacrifices of tracking performance.

The single train trajectory optimization, also known as speed profile optimization (SPO), is a traditional problem to minimize the traction energy consumption of trains. As a kind of optimal method, reinforcement learning (RL) has been used to solve the SPO problem. In the learning process of a common RL algorithm, a soft constraint (punishment) is always used to keep the agent away from unsafe states. However, a soft constraint can not guarantee and explain the safety of the result. For the SPO problem, it means that the optimized speed profile obtained by a simple RL may break the speed limit which is unacceptable in reality. This paper proposes a protection mechanism called Shield and constructs a Shield SARSA (${S}$-SARSA) algorithm to protect the learning process of the high-speed train. Four different reward functions are used to compare the protective efficacy between the proposed algorithm and the soft constraint. The numerical experiments based on the line data from Wuxi East to Suzhou North verify the protective efficacy and effectiveness.

The high-speed train control system is essential to the safety and efficiency of train operation. With the rapid increase of high-speed railway (HSR) operating mileage and development of information technology, the disposal flow and methods in emergency response are still based on dispatchers and drivers’ experience within the “layered” architecture of current system. There is a certain gap between current processing methods and effective resolution, which may even cause the spread of delay along with the railway networks. Therefore, we propose an integration system of operation control and online rescheduling to improve the recovery ability of HSR carrying capacity. We first describe the framework, information flow, and disposal process of the current system and analyze the shortcomings in handling emergencies. Then, the basic concept, system structure, and framework of the integration system are introduced. Finally, taking temporary speed restriction caused by strong wind as an example, we also analyze the principle of why and how the integration system can promote the recovery ability of HSR carrying capacity.

With the rapid development of Metro, it has aroused more attention to its energy efficiency. The regenerative energy is a kind of energy generated by a braking train, which can be used by other trains nearby. Due to the application of regenerative braking and automatic train operation function, more and more studies focus on using regenerative energy by optimal train control. To maximize the utilization of regenerative energy for a couple of trains, we formulate a model and design an algorithm for maximizing the utilization of regenerative energy (MURE) by using the proposed approximate dynamic programming (ADP) approach to adjust the speed curve of the accelerating train. Then, we discuss three approximation methods for the proposed ADP-based approach such as rollout method, interpolation method, and neural network. The rollout algorithm could improve the basic policy for train control with carefully designing. The function approximation method using interpolation could further decrease the energy consumption with assuring punctuality. The neural network approximation usually cannot realize the effect superior to the interpolation strategy due to its complex structure, and it needs more computation time. Finally, the analysis of regenerative energy utilization is given by implementing the numerical experiments with field data from the Yizhuang line, Beijing subway. The numerical results show its effectiveness and stability.

In high-speed railways equipped with advanced train control systems, the train-to-train or train-to-ground communication technologies enable the trains to follow their former trains with a constant headway. Due to some disturbances (e.g., weather condition, train re-routing), the train following headway may be inconsistent between successive trains, which requires real-time headway adjustment to coordinate train operations by selecting proper speed curves to improve system performances (e.g., line capacity, energy consumption, power demand, etc) with constrains of safety, punctuality and comfort. This paper proposes a multi-train control model based on cooperative control to adjust train following headway. In particular, this train cooperative control model considers several practical constraints, e.g., train controller output constraints, safe train following distance. Then, this control problem is solved through a rolling horizon approach by calculating the Riccati equation with Lagrangian multipliers. Finally, two case studies are given through simulation experiments. The simulation results are analyzed which demonstrate the effectiveness of the proposed approach.

In an urban rail transit system, issues regarding headway regulation have aroused wide attention. The assurance of headway regularity can decrease train delay times and average passenger waiting times. An integrated control method is proposed to optimize train headway by adjusting the train arrival time at stations. The adjustment of train arrival time is achieved by using an analytical method, and then the speed profile for each train is calculated by a suboptimal method, which has been applied in a practical system. Through simulation, the CPU time for calculating optimal train arrival time and speed profile is analyzed, respectively. The analysis demonstrates that the proposed method satisfies the real-time requirements for solving the headway regulation problem. By adopting the proposed method, the average passenger waiting time and the energy consumption can be decreased. In particular, the proposed method has better performance when the dispatch headway is large.