Abstract: Examples disclosed herein relate to a radar system in an autonomous vehicle for object detection and classification. The radar system has a radar module having a dynamically controllable beam steering antenna and a perception module. The perception module includes a machine learning module trained on a first set of data and retrained on a second set of data to generate a set of object locations and classifications, and a classifier to use velocity information combined with the set of object locations and classifications to output a set of classified data.

Abstract: Examples disclosed herein relate to an antenna calibration method for a beam steering radar. A first set of input voltages is determined for a plurality of phase shifters coupled to a plurality of antenna elements in an antenna array in the beam steering radar, the voltages to control phases of signals for transmission by the antenna array. A first set of input voltages is applied to the antenna array. Radiating signals resulting from the first set of input voltages are measured. Voltage and phase values for the plurality of phase shifters are iteratively optimized to determine voltage and phase value pairs that result in a desired gain for the antenna array. The voltage and phase value pairs are stored in a look-up-table in the beam steering radar.

Abstract: Examples disclosed herein relate to a beam steering vehicle radar for object identification. The beam steering vehicle radar includes a beam steering receive antenna having a plurality of antenna elements to generate a radiation beam comprising a main lobe and a plurality of side lobes, at least one guard band antenna to generate a guard band radiation beam, and a perception module coupled to the beam steering receive antenna to detect and identify a first object reflection in the radiation beam. The perception module has a monopulse module to determine a range and angle of arrival for the first object reflection and detect multiple objects upon determining an absence of a second object reflection in the guard band radiation beam.

Abstract: Examples disclosed herein relate to reflectarray antenna for enhanced wireless applications. The reflectarray antenna has a ground conductive plane, a dielectric substrate coupled to the ground conductive plane, and a patterned conductive plane coupled to the dielectric substrate and comprising an array of cells to generate an antenna gain. In some aspects, each cell in the array of cells includes a reflector element with a predetermined custom configuration and configured to receive a radio frequency (RF) signal and to generate an RF return beam at a predetermined direction. Other examples disclosed herein relate to a portable reflectarray and a method of fabricating a reflectarray antenna.

Abstract: Examples disclosed herein relate to an autonomous driving system in an ego vehicle. The autonomous driving system includes a radar system configured to detect and identify a target in a path and a surrounding environment of the ego vehicle. The autonomous driving system also includes a sensor fusion module configured to receive radar data on the identified target from the radar system and compare the identified target with one or more targets identified by a plurality of perception sensors that are geographically disparate from the radar system. Other examples disclosed herein include a method of operating the radar system in the autonomous driving system of the ego vehicle.

Abstract: Examples disclosed herein relate to a Multiple-Input Multiple-Output (MIMO) radar for virtual beam steering. The MIMO radar has a plurality of transmit antennas and a receive antenna array having a plurality of radiating elements. The MIMO radar also includes a digital signal processor (DSP) configured to synthesize a virtual receive array having N×M receive subarrays from the plurality of transmit antennas and the receive antenna array, where N is the number of transmit antennas and M is the number of receiving elements. Other examples disclosed herein relate to a method of virtual beam steering.

Abstract: Examples disclosed herein relate to a reflectarray antenna system with two-dimensional beam scanning that includes a first reflectarray having a polarizing grid that operates as a reflective surface in a first polarization and operates as a transparent surface in a second polarization. The reflectarray antenna system includes a second reflectarray comprising an array of reflectarray cells and arranged parallel to the first reflectarray. The second reflectarray includes a first set of feed elements arranged along a first axis and a second set of feed elements arranged along a second axis orthogonal to the first axis to scan a field of view along the first and second axes. The second reflectarray can radiate radio frequency (RE) beams in the first polarization with the first and second sets of feed elements for reflection at the polarizing grid and radiate reflected RE beams in the second polarization for transmission through the polarizing grid.

Abstract: Examples disclosed herein relate to a stripline feed distribution network with embedded resistor for use in millimeter-wave applications. The feed distribution network includes a plurality of ground planes and a signal plane coupled to the plurality of ground planes. The signal plane is configured to serve as a feed to an antenna array with signaling operating at a millimeter-wave frequency bands. The signal plane includes an input transmission line and a plurality of output transmission lines coupled to the input transmission line. The feed distribution network also includes a resistor plane interposed between the signal plane and at least one ground plane of the plurality of ground planes. The resistor plane is configured to isolate the signal plane from the antenna array, and to match a characteristic impedance between the input transmission line and the plurality of output transmission lines.

Abstract: A perception engine incorporating place information for a vehicular sensor. The system uses place information to trigger responses in a perception engine. In some examples the system implements a mirroring process in response to other vehicle actions.

Abstract: Examples disclosed herein relate to a phased array antenna calibration system. The system includes a radio frequency (RF) probe configured to transmit and receive an RF signal, a probe layer coupled to the RF probe via a transmission line layer and configured to transmit or receive the RF signal with the RF probe. In some aspects, the probe layer comprising a plurality of probe elements arranged in an array that corresponds to an arrangement of radiating elements in an antenna-under-test (AUT). The system also includes a foam layer coupled to the probe layer and configured to isolate the AUT from the probe layer.

Abstract: Examples disclosed herein relate to an autonomous driving system in a vehicle. The autonomous driving system includes a radar system configured to detect a target in a path and a surrounding environment of the vehicle and produce radar data with a first resolution that is gathered over a continuous field of view on the detected target. The system includes a super-resolution network configured to receive the radar data with the first resolution and produce radar data with a second resolution different from the first resolution using first neural networks. The system also includes a target identification module configured to receive the radar data with the second resolution and to identify the detected target from the radar data with the second resolution using second neural networks. Other examples disclosed herein include a method of operating the radar system in the autonomous driving system of the vehicle.

Abstract: A radar system for interacting with navigation targets is provided. The radar system is configured to interact with navigation targets (target devices) that shift the phase of a received radar transmission to generate a phase shifted response signal. Phase shifters (e.g., silicon germanium phase shifters) are designed to assign specific frequency responses from one or more navigation modules to identify target locations. The radar module transmits at a modulated signal at first frequency, each navigation target receives the radar transmission, phase shifts the signal and returns the phase shifted signal. Where two or more navigation targets are used, each will apply a different phase shift to the received radar transmission, wherein the frequency identifies the navigation target devices. In a radar system, the modulated transmission signal is compared to the returned phase shifted signal to determine a frequency difference between the two signals.

Abstract: Examples disclosed herein relate to a radar system for use in millimeter wave applications. The radar system includes a lighting device, such as a light bulb or an array of light emitting diodes (LEDs). The radar system further includes an array of transmit elements to transmit at least one transmit signal, where at least one transmit signal reflects off of at least one object to generate at least one receive signal. The array of transmit elements is configured around at least a first portion of a perimeter of the lighting device. Also, the radar system includes an array of receive elements to receive at least one receive signal, where the array of receive elements is configured around at least a second portion of the perimeter of the lighting device.

Abstract: Examples disclosed herein relate to an antenna system. The antenna system has a transceiver unit adapted to receive a composite communication signal, wherein the composite communication signal is a mix of multiple individual communication signals transmitted at different frequencies, a radiating structure comprising multiple subarrays of radiating elements, each subarray responsive to a different frequency, and an antenna controller adapted to map each communication signal to a user equipment.

Abstract: Examples disclosed herein relate to a radar system and method of angular resolution refinement for use in autonomous vehicles. The method includes transmitting a radio frequency (RF) beam to a surrounding environment with a beamsteering radar system and receiving return RF beams from the surrounding environment. The method also includes generating radar data from the return RF beams and detecting objects from the radar data, and determining a direction of arrival of each of object and determining an angular distance between the objects. The method further includes initiating a guard channel detection based at least on the angular distance and determining gain amplitudes of the return RF beams, and determining a null between the objects from the gain amplitudes and resolving the objects as separate objects based at least on the determined null. The method also includes determining a refined direction of arrival of the objects based at least on the resolved objects.

Abstract: Examples disclosed herein relate to a beam steering vehicle radar for object identification. The beam steering radar includes a beam steering receive antenna having a plurality of antenna elements to receive radar return signals, a LNA circuit having a plurality of LNAs, each LNA coupled to each element in the beam steering receive antenna to apply a gain to the return signals to generate amplified return signals, wherein gains of LNAs coupled to center antenna elements are higher than gains of LNAs coupled to edge antenna elements, and a phase shifter circuit to apply a plurality of phase shifts to the amplified return signals.

Abstract: Examples disclosed herein relate to a method for semi-supervised training of a radar system. The method includes training a first radar network of the radar system with a first set of radar object detection labels corresponding to a first set of radar data, training a generative adversarial network (GAN) with the trained first radar network, synthesizing a training data set for a second radar network of the radar system with the trained GAN, training a second radar network with the synthesized training data set, and generating a second set of radar object detection labels based on the training of the second radar network.

Abstract: Examples disclosed herein relate to an antenna system in a radar system for object detection with a sounding signal. The antenna system includes a radiating array of elements configured to transmit a reference signal and an antenna controller coupled to the radiating array of elements. The antenna controller is configured to detect a set of reflections of the reference signal from an object. The antenna is configured to determine a location of the object and a mobility status from the set of reflections. The antenna controller is also configured to generate signaling indicating the location and mobility status of the object as output to identify a target object different from the object. Other examples disclosed herein relate to a radar system and a method of object detection with the radar system.

Abstract: Examples disclosed herein relate to an autonomous driving system in a vehicle, including a radar system with a reinforcement learning engine to control a beam steering antenna and identity targets in a path and a surrounding environment of the vehicle, and a sensor fusion module to receive information from the radar system on the identified targets and compare the information received from the radar system to information received from at least one sensor in the vehicle.

Abstract: Systems, methods, and apparatus for hybrid radar and camera edge sensors are disclosed. Examples disclosed herein relate to a hybrid sensor system having a plurality of edge sensors positioned on the perimeter of a vehicle. The hybrid sensor system processes signals received from the various sensors to identify a target located within the vicinity of the vehicle.