Abstract: A radar system comprises a radar sensor and circuitry configured to perform acts comprising receiving radar sensor data from the radar sensor and detecting static objects in the radar sensor data. The acts further comprise calculating cell parameters related to the static objects for a given radar cell, the cell parameters including a minimum residual velocity value for a static object detection. The acts also comprise generating a 2D cell map grid representing 3D radar cells including the given radar cell and comparing the calculated cell parameters to respective threshold values. Additionally, the acts comprise assigning weight scores to the cell parameters based on the threshold comparison and summing the weight scores assigned to the cell parameters to generate a combined score. The acts also comprise comparing the combined score to a probability threshold and outputting an indication that the cell is occupied or not occupied.

Abstract: The technologies described herein relate to computing a point cloud based upon data output by several radar sensors in a distributed radar system. The radar sensors generate tensors based upon echo signals detected by the radar sensors. Values are extracted from the tensors and a sequence of tokens is created, where the sequence of tokens includes the values extracted from the tensors. The sequence of tokens is provided as input to a transformer model, which outputs a point cloud based upon the sequence of tokens.

Abstract: A radar system comprises a transmit antenna that transmits a radar signal and a receive antenna that receives a radar return. The system further comprises one or more processors configured to perform acts comprising: detecting object based on information in the radar return. The acts further comprise generating and providing to a tracking system a point cloud comprising information related to the detected object. Additionally, the acts comprise receiving from the tracking system an indication of a predicted cell in which the detected object is predicted to be located in a subsequent radar frame, wherein the predicted cell is associated with a confidence value. The acts further comprise reducing, for the subsequent radar frame, a detection threshold value for the predicted cell.

Abstract: A radar sensor system comprises a first radar sensor and at least a second radar sensor and one or more processors configured to perform acts comprising transmitting a first signal from a first transmit antenna in a first radar sensor and transmitting a second signal from a second transmit antenna in a second radar sensor. The acts further comprise detecting an object at the first radar sensor and the second radar sensor and estimating vector velocity information vx and vy for the object. The acts also comprise generating a radar measurement vector z that comprises position information px and py for the object and incorporating the vector velocity information vx and vy into the radar measurement vector z. Additionally, the acts comprise iteratively performing a measurement update using the measurement vector z, with velocity information incorporated therein, and a linear Kalman filter until correct velocity values are determined.

Abstract: A radar sensor system comprises a transmit antenna configured to transmit a radar signal into an environment of the radar sensor system, and a receive antenna configured to receive a return signal from the environment of the radar sensor system responsive to the radar signal. The radar sensor system further comprises radar processing circuitry that is configured to perform acts comprising transmitting a radar signal having a predefined pulse repetition interval (PRI). The acts further comprise monitoring ego velocity of the radar sensor and detecting that the ego velocity has exceeded a first predetermined ego velocity threshold. The acts also comprise decreasing the predefined pulse repetition interval (PRI) based on the first predetermined ego velocity threshold.

Abstract: A radar sensor system comprises a first radar sensor and at least a second radar sensor and one or more processors configured to assign different pulse rate intervals (PRI) to the first radar sensor and the second radar sensor. The processor(s) s are further configured to: receive ambiguous velocity estimates from the first and second radar sensors, respectively; determine maximum detectable velocity (Vmax) values for the first and second radar sensors based on their respective PRIs; generate a first velocity vector for the first radar sensor based on the first Vmax and the first ambiguous velocity estimate; generate a second velocity vector for the second radar sensor based on the second Vmax and the second ambiguous velocity estimate; compare velocity values in the first and second velocity vectors; and identify and output a velocity value common to the first and second velocity vectors as a correct unambiguous velocity of the object.

Abstract: Various technologies described herein pertain to systems and methods for increasing radar resolution by, for example, combining radar information. In one embodiment, beamforming is performed using radar units that are individually coherent but collectively do not need to be coherent. Each radar transmits and receives its own signal to process and generate target information including beamforming information and/or virtual receiver channel information. The target information from each radar is then merged or summed into a combined beamforming based on all the target information received from all the radar units. When the radar units used in this manner are separated by a distance, the resulting beamforming information is representative of an aperture/resolution based on the total space or distance between the radar units. Thus, having an improved resolution, benefits such as improved target resolution (e.g., size, position, and detection) can be achieved.

Abstract: Technologies described herein relate to a distributed aperture radar (DAR) system that includes multiple radar sensors. A graph neural network (GNN) is employed to cause radar data output by the multiple radar sensors to correspond to a same coordinate system.

Abstract: A radar system comprises a plurality of receive antennas that receive a radar signal. One or more processors are configured to perform acts selecting one or more training cells for noise power estimation based upon a radar signal received at one or more receive antennas. The acts further comprise calculating a mean noise power value for the one or more training cells and calculating a noise power variance for the one or more training cells. The acts also comprise estimating a probability of false alarm (PFA) threshold to be applied for a non-training cell and estimating a PFA threshold offset based on the noise power variance. The acts further comprise adjusting a current PFA threshold offset based on the estimated PFA threshold offset.

Abstract: A radar system comprises a plurality of receive antennas that receive a radar signal. One or more processors are configured to generate an n-dimensional point cloud comprising values for parameters of an object in an environment of the radar system, where the n-dimensional point cloud is generated based upon the radar signal, and where n is greater than 2. The one or more processors are further configured to generate from the n-dimensional point cloud a 2D RGB image representing the values of the parameters in different colors, respectively. The parameters can comprise at least object radar cross-section, height, and velocity, etc. The one or more processers are further configured to provide the 2D RGB image to a convolutional neural network that assigns a classification to the object based on the 2D RGB image.

Abstract: A radar system comprises a plurality of transmit antennas that transmit a radar signal toward a target, wherein respective transmit antennas are assigned a transmitter-specific phase offset via which the radar signal is modulated, and wherein respective phase offsets correspond to an offset in velocity of a target. The system further comprises a plurality of receive antennas that receive comprising transmitted signals reflected by the target, and one or more processors configured to determine whether a peak signal is present for respective transmitted signals reflected by the target, the peak signals corresponding to perceived velocities at which the target is moving.

Abstract: Various technologies described herein pertain to a radar sensor system that performs ego motion estimation. A radar sensor system can be utilized to generate an instantaneous three-dimensional ego motion estimate of a vehicle. The radar sensor system employs an algorithm that enables generating ego motion estimates for velocities of the vehicle that can be greater than, less then, or equal to the unambiguous maximum velocity of the radar sensor system. Moreover, a single radar sensor system of a vehicle can implement the approaches set forth herein and the techniques can be applicable regardless of modulation of the radar sensor system.

Abstract: A radar system comprises a plurality of transmit antennas that transmit a radar signal toward a target, wherein each transmit antenna transmits its signal using a different space-time block code in a given transmission time slot. In one embodiment, no two transmit antennas transmit using the same space-time block code in the same transmission time slot.

Abstract: Various technologies described herein pertain to disambiguating velocity estimate data of a radar sensor system. First range estimate data can be computed based on samples from a period of a ramp for each ramp in a sequence. First velocity estimate data can be computed based on samples from a range bin across the ramps in the sequence for each range bin. For each of the ramps in the sequence, samples from a period of a ramp can be divided into a plurality of groups of the samples respectively from periods of subramps. The first velocity estimate data can be disambiguated to generate second velocity estimate data. The first velocity estimate data can be disambiguated based on the plurality of groups of the samples respectively from the periods of the subramps.

Abstract: A radar sensor system transmits a radar signal that comprises first pulses in a first frequency band and second pulses in a second frequency band. The radar sensor system receives a return of the radar signal from a target, wherein the return comprises the first pulses and the second pulses. The radar sensor system concatenates the first pulses and the second pulses, and computes an estimated range to a target based upon a Fourier transform of the concatenated first and second pulses. A range resolution of the estimated range is based upon a bandwidth of a third frequency band that includes the first frequency band and the second frequency band.

Abstract: A radar sensor system transmits a radar signal that comprises first pulses in a first frequency band and second pulses in a second frequency band. The radar sensor system receives a return of the radar signal from a target, wherein the return comprises the first pulses and the second pulses. The radar sensor system computes a coarse range estimate to the target. Based upon the coarse range estimate, the radar sensor system further computes a fine range estimate to the target, where a resolution of the fine range estimate is based upon a third frequency band that has a bandwidth greater than the first frequency band or the second frequency band.