Presented herein are systems and methods for automatically evaluating detection accuracy of dynamic objects by equipment under test, comprising receiving a first record generated by an evaluated equipment under test and a second record generated by a validated reference equipment both deployed in a vehicle, the first record comprising a plurality of attributes of dynamic object(s) detected by the evaluated equipment and the second record comprising a plurality of attributes of dynamic object(s) detected by the reference equipment, correlating between dynamic object(s) detected by both the evaluated equipment and the reference equipment according to matching spatial and temporal attributes of the dynamic object(s) in the first record and in the second record, analyzing at least some of the attributes of the respective dynamic object in the first record compared to the second record, and outputting an indication of differences identified between the first record and the second record.

The technologies described herein relate to a domain adaptation system for sensor data. A computer-implemented model is trained using a set of training sensor data to facilitate classification of objects that are in the vicinity of an autonomous vehicle (AV). The set of training data corresponds to a first domain, such as firmware version of a sensor system, model of a sensor system, position of the sensor system on a vehicle, an environmental condition, etc. The set of training data is generated based upon pre-existing training data that corresponds to a second domain that is different from the first domain. Put differently, the pre-existing training data is transformed to correspond to the domain of a sensor system as it will be used on the AV.

An emergency action system for use with a railcar or locomotive is described herein. The emergency action system may include a transmitter and a locomotive transceiver located within a cabin of the locomotive. The locomotive transceiver may receive a signal sent from the transmitter and may further send an emergency stop signal to a set of brakes on the locomotive to stop. The emergency stop signal may cause air to be released from the brake pipe, thereby applying the brakes and bringing the train to an immediate stop. The emergency action system enables crew members to stop a train or railcar without communication to the locomotive operator when a hazard is recognized.

An object detection device includes processing circuitry configured to acquire wave data; acquire the moving velocity of a radar device; estimate a relative distance between the radar device and a target, angle of incidence of a reflection signal from the target, and a first relative velocity between the radar device and the target, by using the wave data; and estimate a second relative velocity between the radar device and the target in a case where the target is a static object, on the basis of the acquired moving velocity and the relative distance and the angle of incidence, and determine whether the target is a static object by comparing the first relative velocity and the second relative velocity.

Methods and systems are provided for generating an on-demand distributed aperture by mechanical articulation. In some aspects, a process can include steps for determining a location of an autonomous vehicle, determining whether a maneuver requires long range detections or medium range detections based on the location of the autonomous vehicle, positioning at least two articulated radars based on the determining of whether the maneuver requires long range detections or medium range detections, and enabling a mode of resolution based on the positioning of the at least two articulated radars and by utilizing a static radar. Systems and machine-readable media are also provided.

Disclosed are devices, systems and methods for compensating radar measurements of a vehicle. One exemplary method includes generating a set of velocity hypotheses of a target object based on a first measurement data obtained from sensors mounted on the vehicle; generating cluster velocity estimates by applying a clustering algorithm to a second measurement data obtained from the sensors; and providing one or more selected velocity hypotheses from the set of velocity hypothesis as compensated radar measurements for the target object based on the cluster velocity estimates.

A predicted course estimating apparatus for estimating a predicted course of the own vehicle, includes: a data acquiring means for acquiring turning data that indicates a turning direction of the own vehicle; a filtering means for removing a high-frequency component that is included in the turning data; a course predicting means for calculating an estimated value for course prediction of the own vehicle, based on the turning data that has been filtered and a speed of the own vehicle; a determining means for determining whether the own vehicle is traveling a part of a road where the shape changes; and a characteristics changing means for changing the extent of removing of the high-frequency component by the filtering means when it is determined that the own vehicle is traveling a part of the road where the shape changes.

An emergency steering system for a vehicle includes a memory including instructions that, when executed by a processor, cause the processor to: receive information corresponding to an environment external to the vehicle; identify an obstacle in the environment external to the vehicle using the information; determine a distance between the vehicle and the obstacle; determine whether a collision is imminent; in response to determining that a collision is imminent, determine whether the vehicle can move within a lane of travel to avoid the collision; in response to determining that the vehicle can move within the lane of travel to avoid the collision, determine a trajectory of travel for the vehicle; generate a steering assist angle command based on the trajectory of travel; and control position of a steering mechanism of the vehicle using the steering assist angle command and a measured steering angle.

Provided herein is a system on a vehicle, the system comprising an active Doppler sensor; one or more processors; and a memory storing instructions that, when executed by the one or more processors, causes the system to perform: obtaining a Doppler signature from each of one or more entities; and determining one or more calibration parameters of the active Doppler sensor based on the Doppler signature from at least a portion of the one or more entities.

A blind-spot detection system includes an angle-detector, a radar-sensor, and a controller. The angle-sensor is used to determine a trailer-angle relative to a host-vehicle of a trailer being towed by the host-vehicle. The radar-sensor is used to detect an other-vehicle present in a blind-zone proximate to the host-vehicle. The controller is in communication with the angle-detector and the radar-sensor. The controller is configured to adjust a sensing-boundary that defines the blind-zone based on the trailer-angle.