Systems may include at least one processor configured to determine a predicted value of an unwrap factor using a machine learning model, wherein the machine learning model is a trained machine learning model configured to provide a predicted value of an unwrap factor for dealiasing a measurement of range rate of a target object as an output, dealiase a measurement value of range rate from a radar of an autonomous vehicle (AV) based on the predicted value of the unwrap factor to provide a true value of range rate, and control an operation of the AV in a real-time environment based on the true value of range rate. Methods, computer program products, and autonomous vehicles are also disclosed.

A method and system involve obtaining reflected signals in a radar system using a first one-dimensional array of antenna elements and a second one-dimensional array of antenna elements. The reflected signals result from reflection of transmitted signals from the radar system by one or more objects. The method includes processing the reflected signals obtained using the first one-dimensional array of antenna elements to obtain a first array of angle of arrival likelihood values in a first plane, and processing the reflected signals obtained using the second one-dimensional array of antenna elements to obtain a second array of angle of arrival likelihood values. A four-dimensional image indicating a range, relative range rate, the first angle of arrival, and the second angle of arrival for each of the one or more objects is obtained.

A trajectory identification apparatus, method, and computer program product thereof are provided. The apparatus converts the object positions into a two-dimensional space to generate and sequence a plurality of object coordinates, calculates a distance of adjacent object coordinates to generate a trajectory-time image. The apparatus calculates a sum-distance, and calculates an initial speed based on a first distance and the sum-distance to generate a trajectory-speed image. The apparatus separates the trajectory-time image into a first channelizing datum, separates trajectory-speed image into a second channelizing datum, and overlaps the first channelizing datum and the second channelizing datum to generate a to-be detected channelizing datum. The apparatus inputs the to-be detected channelizing datum into an identification model to generate a prospective channelizing datum, compares the degree of difference between the to-be detected channelizing datum and the prospective channelizing datum to generate a trajectory identification result.

Various embodiments relate to a device and method for controlling vehicles and a radar system for vehicles. The vehicle controller may include a spectrum generator generating a 2D spectrum, a range-velocity map generator generating a range-velocity map corresponding to each height value included in a height set, a correlation coefficient determiner determining a correlation coefficient corresponding to each height value included in the height set, and a target determiner estimating a height of a target based on the correlation coefficient and recognizing the target based on the height of the target.

A range setting unit sets, for each of tracked objects as objects being tracked, a connection range as a range in which the tracked object is estimated to be movable based on a state quantity of the tracked objects determined in the previous processing cycle. An association extraction unit extracts, for each of the tracked objects, a reflection point detected in the current processing cycle and positioned in the connection range as an associated reflection point. A state quantity update unit updates, for each of the tracked objects, the state quantity of the tracked objects in the current processing cycle, based on the previous state quantity and the state quantity of the associated reflection point.

A system for determining a stationary state of a rail vehicle on a track includes a first radar mounted at an end of the rail vehicle and a second radar mounted at another end of the rail vehicle. A speed sensor is mounted on the rail vehicle. A series of fixed reflective track features are found along the track. A processing unit, communicably connected with the speed sensor, the first radar and the second radar receives data from the first radar and the second radar corresponding to the distance to the fixed reflective track features and determines the stationary state or low-speed condition of the rail vehicle and checks the state or condition by comparing it with an output of the speed sensor.

The disclosure provides systems, apparatuses, and techniques for operating automotive MIMO radars in crowded multi-path environments to obtain reliable detections by linearly predicting whether a bistatic condition occurred. To avoid saturating computing resources processing bistatic detections, the described techniques enable a radar system to quickly identify and discard from the field-of-view radar detections that are likely a result of bistatic conditions. By ignoring unusable radar returns that are likely a result of bistatic conditions, an example radar system can focus on processing radar returns from static conditions, for example, in providing radar-based detections as output to an automotive system that is driving a vehicle in an autonomous or a semi-autonomous mode. In so doing, the example radar system provides a highly accurate static object detector that is sufficiently quick in detecting bistatic conditions for use in vehicle-safety systems as well as autonomous and semi-autonomous control.

A sensor system includes a first metamaterial track mechanically coupled to a rotational shaft configured to rotate about a rotational axis, wherein the first metamaterial track is arranged at least partially around the rotational axis, and wherein the first metamaterial track includes a first array of elementary structures; at least one transmitter configured to transmit a first continuous wave towards the first metamaterial track, wherein the first metamaterial track is configured to convert the first continuous wave into a first receive signal based on a rotational parameter of the rotational shaft; and at least one quadrature continuous-wave receiver configured to receive the first receive signal, acquire a first measurement of a first property of the first receive signal, and determine a measurement value for the rotational parameter of the rotational shaft based on the first measurement.

A method includes transmitting a first transmitted signal corresponding to a first range rate window size; receiving a first received signal; determining a first detected range rate of an object based on the first received signal; transmitting a second transmitted signal corresponding to a second range rate window size; receiving a second received signal; determining a second detected range rate of the object based on the second received signal; computing a first range rate window index based on a first range rate window index difference; in accordance with a determination that the first range rate window index meets predefined criteria, computing an estimated range rate based on the first range rate window index difference; and in accordance with a determination that the first range rate window index does not meet the predefined criteria, foregoing computing an estimated range rate based on the first range rate window index difference.

A follow-on object for use in a salvo mission in which one or more lead objects (LO) and a follow-on object track a target. A track state of a tracked object within a sensor field-of-view (FOV) of the follow-on object is initialized. Target-state estimator (TSE) processing based on sensor measurements from the sensor FOV is performed to maintain the track state of the tracked object. Kinematic characteristics of the tracked object are evaluated based on the sensor measurements to compute a probability that the tracked object is an LO based on the evaluated kinematic characteristics. If the probability is not greater than a threshold, the tracked object is designated as the target and TSE processing is resumed. Otherwise, the tracked object is designated as an LO and the track state is re-initialized and the track of the LO is excluded from some intercept task considerations.