A computer-implemented method in which one or more processing devices perform operations may include obtaining a field image of a railcar collected from a field camera system and applying a machine-learning algorithm to the field image to generate a machine-learning algorithm output. The method may also include performing a post-processing operation on the machine-learning algorithm output to generate a filtered machine-learning algorithm output. Further, the method may include detecting a defect of the railcar using the filtered machine-learning algorithm output.

The disclosed solution generally relates to a hyperloop vehicle detecting objects in a hyperloop system. Hyperloop vehicles operate at incredible velocities and require robust systems to detect objects that increase the risk to a hyperloop vehicle. Transponders typically provide long-range data about the activity of downstream hyperloop vehicles. However, nearby objects require detection at line-of-sight distances in order to ensure that objects and vehicles within a given transponder interval distance are detected. The disclosed system provides an elegant solution that combines the advantages of both transponder-based object detection and sensor-based object detection.

Disclosed is a technique for a railway disaster monitoring system for monitoring a foreign matter on a railway, which includes a camera and an image processing unit that receives a railway image captured by the camera. The image processing unit includes a segmented image acquisition unit that obtains a plurality of segmented images including a rail from the railway image received from the camera and scales the segmented images to obtain segmented image blocks of a predetermined size, and a segmented image determination unit which includes deep neural network (DNN) discriminators trained with deep learning neural networks and inputs the segmented image blocks to the DNN discriminators to determine whether the railway is in a normal state in which there is no foreign matter on the railway except a train passing by. Using the segmented images, a foreign matter on a railway can be rapidly and easily determined using a deep learning neural network even with a small number of resources.

A system and method for automating railroad maintenance by a tie gang using electronic tie marking (ETM) configured to optimize railroad asset maintenance. The system enables collision avoidance between members of the tie gang performing maintenance on railway assets (e.g., Rails, Ties, Ballasts, Turnouts, Crossings, etc.). The system can generate production numbers for the railway assets and evaluate an asset queue for the tie gang to perform maintenance. The system can utilize real-time updates from the tie gang to optimize work output. The system can provide a customizable user interface to identify, track, and process information related to maintenance of the railroad asset. The system also provides for a heads-up-display (HUD) to notify an operator of relevant information, such as maintenance information, travel indicators, and updated asset queue. The system can identify a next location and calculate an optimum path based on sensor input incorporating machine-specific and environmental characteristics.

A farming system (1) for row crop installations (10) comprises: a first plurality of plants (10A) and a second plurality of fruit or vegetable plants (10B), disposed along a first longitudinal axis (L1) and a second longitudinal axis (L2), respectively, and mutually spaced along a transverse direction (T) to form a first row (F1) and a second row (F2); a supporting structure (11), configured to support the plants and including, for the first row (F1) and the second row (F2), a first plurality of posts (11A) and a second plurality of posts (11B); a first rail (12A), connected to the first plurality of posts (11A); a second rail (12B), connected to the second plurality of posts (11B). The first rail (12A) and the second rail (12B) are oriented longitudinally and spaced transversely from each other to define a track (12). The system comprises a trolley (13), movable along the track (12) and including a movement actuator (131), configured to move the trolley (13) on the track (12).

A method uses a track-side obstacle identification arrangement and a vehicle-side obstacle identification arrangement in order to identify obstacles in a danger zone in front of a rail vehicle. In order to allow improved autonomous driving of the rail vehicle, it is provided that, as it approaches a relevant one of the obstacles, at least one reaction or response of the rail vehicle is derived depending on an evaluation signal of the track-side obstacle identification arrangement and an actual value of at least one variable which characterizes the effectiveness or performance of the vehicle-side obstacle identification arrangement. A system for identifying obstacles is also provided.

Apparatuses, systems, methods, and software for train control and tracking using multi sensors, SSD/QR signs, and/or RF reflectors are disclosed, which enable determination of train location on a guideway, train movement authority, train length, and coupler status of each vehicle (married pair) and the consist (integrity) of the train.

Various embodiments of an autonomous rail vehicle that can travel ahead of a locomotive at a distance proportional to the locomotive's stopping capability are disclosed. The rail vehicle may scan its surroundings, gauges track conditions, and communicates with locomotive operators of the scanned results in real-time to timely enable activation of the locomotive's emergency brakes in case of detection of off-normal track conditions. The rail vehicle may paired with the locomotive and provides eyes to locomotive operators so that they can have information on tracks viability well ahead of the locomotive.

System (1) for detecting events or situations having associated patterns of acoustic vibrations in a train rail (2), which comprises a vibration detector unit (3) provided with an acoustic sensor (31) and attached to the rail (2) that can sense the acoustic vibrations transmitted through the rail (2) and a main assembly (4) connected to the vibration detector unit (3), wherein the vibration detector unit (3) comprises a processor (32) and the main assembly (4) comprises a control unit (41), the processor (32) comprising stored patterns corresponding to known events, the processor (32) being configured to preprocess the vibrations transmitted to the rail (2), to determine if the vibrations correspond to a stored pattern and, if the vibrations correspond to a stored pattern, send to the control unit (41) a signal associated to the event. The invention also refers to the vibration detector unit (3) itself.

A railway vehicle is provided with a pantograph movable under the action of a moving device between a raised position, in which it is able to cooperate in contact, in use, with a catenary conductor cable for drawing electrical energy, and a lowered position, in which it is lower than the height where, in use, such catenary is provided; the vehicle is provided with a battery pack and a control system for controlling the moving device and therefore lowering/raising the pantograph; the control system has a microprocessor control unit configured to control the moving device in response to signals containing information indicative of the actual position of the vehicle, and/or indicative of the presence or absence of the conductor cable in the vicinity of the vehicle.