A train control system uses artificial intelligence for maintaining synchronization between centralized and distributed train control models. A machine learning engine receives training data from a data acquisition hub, a first set of output control commands from a centralized virtual system modeling engine, and a second set of output control commands from a distributed virtual system modeling engine. The machine learning engine compares the first set of output control commands and the second set of output control commands, and trains a learning system using the training data to enable the machine learning engine to safely mitigate any difference between the first and second sets of output control commands using a learning function including at least one learning parameter.

This system includes a ground ATC and an on board ATC, which is switched from an active mode toward a standby mode and vice versa by a wake-up unit. In the standby mode, only the following components remain powered: odometry device; a main computer; a radio communication device between the on board ATC and the ground ATC; the wake-up unit. The main computer is programmed so as, in the standby mode, to verify that the movement of the train measured by the odometry device from the switching from the active mode to the standby mode is zero and, in the affirmative, to send the ground ATC an instantaneous position of the train using the radio communication device.

A method of controlling a vehicle to soft-land at a target destination includes: determining a terminal set, which is a set of system states of the vehicle under which the vehicle will converge to a target set under constant zero control input; determining a sequence of polytopes, each polytope being an approximation of a backward reachable set of system states of the vehicle; and controlling the vehicle to reach the destination based on the determined polytopes. The method may be performed by one or more controllers.

A robust system processor comprising three parallel processors, each configured to process in parallel an input and emit an output; and a reconciler that compares the three outputs, determines whether at least two of the outputs are equal, and if so validates the majority output and communicates the validated output via a network to at least one other system processor.

A model formula representing the relationship between an error between a predetermined stopping position and an actually-stopped position of a vehicle indicating the result of an automatic stop control, which controls the vehicle to stop at the predetermined stopping position using running-condition parameters, and the running-condition parameters used for the automatic stop control is calculated via machine learning. A stopping error is estimated with respect to the next stopping position, at which the vehicle currently running is going to stop, according to the model formula which is calculated in the past. The changing parameter to be changed is specified among the running-condition parameters, and then the changing parameter used for the automatic stop control is updated with a correction value configured to correct the stopping error of the vehicle.

A control arrangement for a railroad level crossing is disclosed. The control arrangement comprises monitoring sensors for monitoring the level crossing, the monitoring sensors arranged to detect an obstruction within a restricted area at or near to the level crossing, and a processing unit associated with the monitoring sensors and arranged to generate an alarm warning when an obstruction is detected. The alarm warning is used to adjust a Movement Authority issued to a train approaching the level crossing.

A protection method for a railway network which is divided into track sections by track elements, and which can be traveled on by vehicles. The vehicles request steps for assignment from selected track elements to form travel path elements. In order to optimize the train service, each of the selected track elements provides at least one signal for each vehicle that requests at least one of the steps for assignment as a travel path element from same. A protection system for a railway network is configured to carry out the protection method.

A signal aspect enforcement method for a rail vehicle includes determining if vehicle position is unknown. The system determines if rail vehicle speed is less than a line-of-sight threshold speed. The system determines the grade of the rail. A worst-case braking distance of rail vehicle is calculated. The signal aspect is determined using a camera system and a beacon system. The system determines if the signal aspect determined by camera system is same as signal aspect determined by beacon system and, if so, determines the route of rail vehicle and speed limit of rail vehicle.

Systems and methods for obstacle avoidance with a self-driving vehicle are provided. The system comprises a processor connected to the self-driving vehicle and a sensor in communication with the processor. The sensor is configured to detect objects. The processor is configured to receive a measurement of the self-driving vehicle's speed, and define a sensor region based on the speed. The processor can determine that an object detected by the sensor is within the sensor region, and then initiate a fail-safe routine. The sensor region may be defined based on a range parameter. The sensor region may be defined based on the stopping distance of the vehicle. The sensor region may be redefined when the vehicle's speed changes.

A train control method is provided for a vehicle on-board controller (VOBC) configured on one end of a train. The method includes: performing a train awakening process; acquiring a running plan sent by an automatic train supervision (ATS) system after the train is successfully awakened; setting, according to a direction indicated by the running plan, a running direction of the train to be downward or upward; when the running direction is set to downward, using, as a head for train positioning, one end of the train not configured with the VOBC, to acquire positioning information of the train; when the running direction is set to upward, using, as the head for train positioning, one end of the train configured with the VOBC, to acquire the positioning information of the train; and controlling, according to the positioning information of the train, the train to pull out of a parking garage.