In a method for traffic-dependent output of a control signal for at least one of a barrier and a traffic light signal at a grade crossing, a radar sensor device detects motions of traffic objects over a street traffic area of the grade crossing, a control signal is emitted to a control unit for the barrier and/or for the traffic light signal situated on the inflow side of the grade crossing, using a lead time before an expected time of arrival of a train at the grade crossing, and the lead time is determined with the aid of a curve over time of the detected motions of the traffic objects, the lead time for a slow-moving traffic being greater than for a more rapidly flowing, unimpeded traffic.

In one embodiment, a railroad scout vehicle system includes a scout vehicle and a processing unit. The scout vehicle may include at least two wheels configured to engage a set of railroad tracks, a motor mechanically coupled to at least one of the wheels, a speed controller, an electromagnetic sensor aimed at the set of railroad tracks, a positioning receiver, a local speed sensing device and a transceiver. The speed controller may be coupled to the motor and configured to control the speed of the scout vehicle in order to maintain an appropriate distance between the scout vehicle and a train traveling behind. The processing unit may be configured to transmit the track status information via the transceiver, receive train speed and position signals from the train via the transceiver.

Methods and apparatus for real time machine vision and point-cloud data analysis are provided, for remote sensing and vehicle control. Point cloud data can be analyzed via scalable, centralized, cloud computing systems for extraction of asset information and generation of semantic maps. Machine learning components can optimize data analysis mechanisms to improve asset and feature extraction from sensor data. Optimized data analysis mechanisms can be downloaded to vehicles for use in on-board systems analyzing vehicle sensor data. Semantic map data can be used locally in vehicles, along with onboard sensors, to derive precise vehicle localization and provide input to vehicle to control systems.

A system comprises a first sensor on a first end of a vehicle and an on-board controller coupled to the first sensor. The first sensor is configured to detect a radio frequency (RF) signature of a marker along a guideway. The first sensor is a radar detection device. The on-board controller is configured to determine a first position of the vehicle on the guideway or a first distance from the position of the vehicle to a stopping location along the guideway based on at least the RF signature received from the first sensor. The marker is a metasurface plate comprising a first diffused element, a first retroreflector element, a first absorbing element and a second diffused element between the first retroreflector element and the first absorbing element.

An anti-collision system for railcars and locomotives and, more particularly, to a distance ranging and worker coupling protection system utilizes remote-sensing radar techniques for use with a locomotive and railcar. The anti-collision system may include an object detector device attached to a railcar or a locomotive that detects objects in a path of the railcar and the locomotive and a train display device electrically connected to the object detector device. The anti-collision system may also include an emergency action device which enables a crew member to stop the railcar or locomotive without communication to a locomotive operator when a hazard is recognized. The object detector device may include a remote sensor, a radio, and a microprocessor programmed to include data-logging to record and log all data from the anti-collision system.

Systems and methods according to one or more embodiments are provided for detecting an object in a field of view of an imaging device. An object may be detected by an imaging device when the object is present along a trajectory in a target scene. In one example, a system includes a memory component to store a plurality of images of the target scene and a processor. The processor is configured to define the trajectory between two locations within the target scene and extract a subset of pixel values from each of successive images corresponding to the trajectory. The extracted subsets of pixel values are processed to detect an object within the target scene. Additional systems and methods are also provided.

A method validates an obstacle identification system. In order to be able to demonstrate that obstacles are identified by an obstacle identification system at least as reliably as by a driver, it is provided that, in order to form driving scenarios, stochastic combinations of prespecified distributions of submodules are provided. The provided combinations are subjected first, for carrying out a simulation study, to simulation by a simulator and second to automatic processing by an obstacle identification algorithm of the obstacle identification system, and a result of a simulation study, which is carried out by the simulator, and a result of the automatic processing are automatically tested for agreement.

A monitoring and surveillance system arranged for processing video data associated with a vehicle, wherein said system is arranged to operate in at least two operating modi, a first modus of said two modi being associated with a first latency requirement for said video data and a second modus of said two modi being associated with a second latency requirement, said system comprising a camera unit, arranged to be installed in said vehicle, wherein said camera unit is arranged for capturing video data; a streaming unit, arranged to be installed in said vehicle, and arranged for receiving said video data and for transmitting said video data over a telecommunication network to a video processing server; said video processing server arranged for selecting a modus of said at least two operating modi, and for communicating said selected modus, over said telecommunication network, to said camera unit such that said streaming unit can be tuned to said selected modus. Complementary systems and methods are also presented herein.

An automated on-vehicle rail vehicle control system has an on-vehicle set point value detection unit, an automated train operating system, a driving and braking unit, and additional sensors for detecting environment-related information. The on-vehicle set point value detection unit is configured to determine, based on on-vehicle positioning and map data as well as sensor data from the additional sensors, operative set point values for the control mode and the current driving mission of the rail vehicle. The automated train operating system is configured to generate driving and braking commands based on the set point values of the on-vehicle set point value detection unit. The driving and braking unit is configured to carry out traction and braking operations based on the driving and braking commands so determined. There are also described a rail vehicle and a method for the automated control of a rail vehicle.

In an example, the autonomous vehicle (“AV”) can be configured among the other vehicles and railway to communicate with a rider on a peer to peer basis to pick up the rider on demand from a location on a track, like a railway, tram or other track, rather than the rider being held hostage to a fixed railway schedule. The rider can have an application on his/her cell phone, which tracks each of the AVs, and contact them using the application on the cell phone. In an example, the AV is configured for both on-track and off track operation with different operating parameters for on-track and off track, including speed, degree of autonomy, sensors used etc.