Metros have the problems of passenger crowding during the peak hours and waste of transport capacity during the non-rush hours. Virtual coupling (VC) is expected to be a good solution to this problem, by which train formation can be dynamically adjusted, thus the line capacity is adjusted. This paper introduces the concept and relevant research of VC, and the existing problems and possible solutions are presented. Train protection and operation control methods are two most important problems among them. For the former, although relative braking distance principle is adopted, the space-time relationship between successive trains is omitted, thus, a space-time-separation-based train protection principle is proposed in this paper; for the latter, most of the existing studies only focus on the cruising control of VC, while the problem of non-synchronous parking that exists in the process of VC arrival at a station is wrongly ignored, which is particularly important in metros, a cooperative-control-based train following method is presented to solve this problem. This paper can provide a reference for readers to understand the development trend of virtual coupling technology in metros and to engage in relevant research.

This paper summarizes the application of robotics in the three aspects of rail transit, i.e., equipment manu-facturing, maintenance inspection, and operation services. Combined with the development status of intel-ligent robot technology in this field, we summarize the key technology and challenges of robots. Thus to propose the future direction of the cooperation of robotics and rail transit.

Virtual Coupling has been a hot research topic in railways in recent years. The proposed control methods in the existing literature for virtually coupled train sets (VCTS) mainly try to operate train units with the constraint of maintaining a small gap distance, but pay insufficient attention to the needs in the entering station process, which affects the work of VCTS in a station and is thus one of the most important part of VCTS in unban rail transits. To fill this gap, this paper firstly proposes an unsynchronized stopping problem between the train units in a VCTS when entering a station, defines the concept and the calculation method of stopping time difference between the train units. Then, inspired by the multi-agent cooperative control methods in related fields, a cooperative control-based reference curve generating method for VCTS is proposed. Followed by it, a mathematical optimization model to generate the reference curves for the train units in a VCTS is formulated, and a reinforcement learning DQN (deep Q network) based algorithm is designed to solve this problem. Optimized reference curves for each train units are generated automatically, considering the global objects and all constraints of VCTS. Finally, based on the real data of trains and lines from Beijing Metro Line 11, numerical simulation experiments are conducted. Experimental results prove the effectiveness of the proposed method which outperforms a commonly used control method of VCTS in the literature.

In order to solve the problem that intelligent train visual positioning system based on deep learning is difficult to test, this paper proposes a safety test method for intelligent train visual positioning. Firstly, based on the idea of Image-to-Image translation, we construct a generative adversarial network (GAN) to generate test cases. Then we implement the quantitative evaluation of the error detection ability of test cases based on deep mutation testing. Finally, according to the characteristics of urban rail operation organization, we propose a parallel test platform architecture of "virtual-reality, semi-reality, reality" to support the construction of the test case generation model and test execution. The method proposed in this paper provides a basis for ensuring the safety of intelligent visual train positioning, provides a new research idea for the safety application of intelligent visual perception technology in the autonomous running of trains, and plays an essential role in ensuring the safety of trains.

Next generation train control system（NGTC）based on Train-Train communication realizes highly efficient train tracking control through three control strategies of constant spacing, constant time interval, and dynamic headway. Since the leader train control is random in the platoon control, how to ensure the safety of the platoon in different control strategies is very important. This paper proposes a Train-Train communication control strategy modeling and verification method based on stochastic priced timed game（SPTG）. Firstly, according to the requirements of different control strategies, a platoon control model including a leader train and follower trains is established by using SPTG automata, and the stability is verified. Secondly, taking time as the cost function, Q-learning is used to obtain the optimal driving strategy of the platoon through the platoon's SPTG automata model. Finally, combined with multi-train operation tracking scenarios, the stability simulation optimization of the platoon is carried out. The result shows that the stability error of the platoon is smaller than that of the random operation of the platoon.