Abstract: In one embodiment, a method includes a computing system obtaining, via one or more sensors of a personal mobile vehicle (PMV), a reflection signal indicating a characteristic of a road surface of an environment external to the PMV. The computing system may determine one or more characteristic factors of the road surface of the environment external to the PMV based on the reflection signal. The computing system may generate a vulnerable road user (VRU) classification probability distribution by using a machine learning classifier. The VRU classification probability distribution indicates whether a combination of the one or more characteristic factors is associated with the VRU. The computing system may determine, based on the VRU classification probability distribution, that the road surface is associated with the VRU. The computing system may present an alert message to a display associated with the PMV.

Abstract: Commercial personal mobile vehicles (PMVs) managed by a fleet management system are sometimes equipped with a radar sensor to detect objects in an environment external to the PMVs. Specifically, the PMV may be equipped with a variety of sensors, such as a radar, a sonar sensor, a (optional) camera, an inertia measurement unit (IMU), and/or the like. The combination of a radar reflection signal and a sonar signal may provide measurements of characteristics such as a Doppler velocity and height information of a nearby object, which may be input to a machine learning classifier to determine the probability that the nearby object is a VRU. For another example, the reflection pattern from radar and ultrasonic may be used to input to a machine learning classifier to determine a type of the road surface, e.g., an asphalt road surface, a concrete sidewalk surface, a wet-grass lawn surface, and/or the like.

Abstract: Examples disclosed herein relate to a beam steering radar for use in an autonomous vehicle. The beam steering radar has a radar module with at least one beam steering antenna, a transceiver, and a controller that can cause the transceiver to perform, using the at least one beam steering antenna, a first scan of a field-of-view (FoV) with a first number of chirps in a first radio frequency (RF) signal and a second scan of the FoV with a second number of chirps in a second RF signal. The radar module also has a perception module having a machine learning-trained classifier that can detect objects in a path and surrounding environment of the autonomous vehicle based on the first number of chirps in the first RF signal and classify the objects based on the second number of chirps in the second RF signal.

Abstract: Examples disclosed herein relate to a radar system for object identification. The radar system transmitting an azimuth fan beam and incrementing elevation of the beam. The radar system may include a transmit antenna and a receive antenna, each having a plurality of antenna elements arranged in rows and columns. The radar system may include a transceiver coupled to the transmit antenna and the receive antenna, the transceiver configured to control transmit beams having an azimuth fan beam, or an elevation fan beam. The radar system may include a processing unit. In various embodiments, the processing unit may include a digital processing unit; a range Doppler mapping module; and an azimuth detection module coupled to the transceiver. The azimuth detection module may be configured to process received signals and identify an azimuth angle of arrival by correlating signals received at antenna elements in rows of the receive antenna.

Abstract: Examples disclosed herein relate to a beam steering radar for use in an autonomous vehicle. The beam steering radar has a radar module with at least one beam steering antenna, a transceiver, and a controller that can cause the transceiver to perform, using the at least one beam steering antenna, a first scan of a field-of-view (FoV) with a first number of chirps in a first radio frequency (RF) signal and a second scan of the FoV with a second number of chirps in a second RF signal. The radar module also has a perception module having a machine learning-trained classifier that can detect objects in a path and surrounding environment of the autonomous vehicle based on the first number of chirps in the first RF signal and classify the objects based on the second number of chirps in the second RF signal.

Abstract: Commercial personal mobile vehicles (PMVs) managed by a fleet management system are sometimes equipped with a radar sensor to detect objects in an environment external to the PMVs. Specifically, the PMV may be equipped with a variety of sensors, such as a radar, a sonar sensor, a (optional) camera, an inertia measurement unit (IMU), and/or the like. The combination of a radar reflection signal and a sonar signal may provide measurements of characteristics such as a Doppler velocity and height information of a nearby object, which may be input to a machine learning classifier to determine the probability that the nearby object is a VRU. For another example, the reflection pattern from radar and ultrasonic may be used to input to a machine learning classifier to determine a type of the road surface, e.g., an asphalt road surface, a concrete sidewalk surface, a wet-grass lawn surface, and/or the like.

Abstract: In the present disclosure, a radar system is configured to interact with beacons that shift the phase of a received radar transmission to generate a phase shifted response signal. Phase shifters are designed to assign specific frequency responses to identify target locations. The radar module transmits at a modulated signal at first frequency, each beacon receives the radar transmission, phase shifts the signal and returns the phase shifted signal. Where two or more beacons are used, each will apply a different phase shift to the received radar transmission, wherein the frequency identifies the specific beacons. 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 beam steering radar for use in an autonomous vehicle. The beam steering radar has a radar module with at least one beam steering antenna, a transceiver, and a controller that can cause the transceiver to perform, using the at least one beam steering antenna, a first scan of a first field-of-view (FoV) with a first chirp slope in a first radio frequency (RF) signal and a second scan of a second FoV with a second chirp slope in a second RF signal. The radar module also has a perception module having a machine learning-trained classifier that can detect objects in a path and surrounding environment of the autonomous vehicle based on the first chirp slope in the first RF signal and classify the objects based on the second chirp slope in the second RF signal.

Abstract: Examples disclosed herein relate to a radar system for object identification. The radar system transmitting an azimuth fan beam and incrementing elevation of the beam. The radar system may include a transmit antenna and a receive antenna, each having a plurality of antenna elements arranged in rows and columns. The radar system may include a transceiver coupled to the transmit antenna and the receive antenna, the transceiver configured to control transmit beams having an azimuth fan beam, or an elevation fan beam. The radar system may include a processing unit. In various embodiments, the processing unit may include a digital processing unit; a range Doppler mapping module; and an azimuth detection module coupled to the transceiver. The azimuth detection module may be configured to process received signals and identify an azimuth angle of arrival by correlating signals received at antenna elements in rows of the receive antenna.

Abstract: In accordance with various implementations, a radar system comprising a non-line of sight (NLOS) module to enhance operation of the radar system is provided. In various embodiments, the NLOS module is a radar repeater module with phase shifters to generate an indication of an object detected in a NLOS area. In various embodiments, the NLOS module includes a reflector structure configured to reflect or redirect radar signals from a train on the tracks into a NLOS area. The NLOS module can include a receive antenna, a transmit antenna configured to transmit one or more received radar signals into a NLOS area, and a phase shifting module for applying a phase shift to a radar signal reflected from an object in the NLOS area that is outside an operational range of the radar unit.

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 warning system positioned in a highway infrastructure. The infrastructure element includes a radar unit that is configured to produce radar data from one or more return radio frequency (RF) beams reflected from a surrounding environment using one or more steerable RF beams radiated to the surrounding environment, detect a moving object in a path of the surrounding environment from the radar data, determine whether the moving object in the path is violating directional criteria, and generate an alert message notifying one or more receiving units to avoid the path of the moving object when the moving object in the path is violating the directional criteria. The infrastructure element also includes a communication unit coupled to the radar unit and configured to send the alert message to the one or more receiving units in the surrounding environment.

Abstract: Examples disclosed herein relate to a radar warning system positioned in a highway infrastructure. The infrastructure element includes a radar unit that is configured to produce radar data from one or more return radio frequency (RF) beams reflected from a surrounding environment using one or more steerable RF beams radiated to the surrounding environment, detect a moving object in a path of the surrounding environment from the radar data, determine whether the moving object in the path is violating directional criteria, and generate an alert message notifying one or more receiving units to avoid the path of the moving object when the moving object in the path is violating the directional criteria. The infrastructure element also includes a communication unit coupled to the radar unit and configured to send the alert message to the one or more receiving units in the surrounding environment.

Abstract: Examples disclosed herein relate to a beam steering radar for use in an autonomous vehicle. The beam steering radar has a radar module with at least one beam steering antenna, a transceiver, and a controller that can cause the transceiver to perform, using the at least one beam steering antenna, a first scan of a field-of-view (FoV) with a first number of chirps in a first radio frequency (RF) signal and a second scan of the FoV with a second number of chirps in a second RF signal. The radar module also has a perception module having a machine learning-trained classifier that can detect objects in a path and surrounding environment of the autonomous vehicle based on the first number of chirps in the first RF signal and classify the objects based on the second number of chirps in the second RF signal.

Abstract: Examples disclosed herein relate to a radar system for three-dimensional beam scanning that includes an antenna module that radiates radio frequency (RF) beams with an analog beamforming antenna in a plurality of directions using phase control elements and generates radar data capturing a surrounding environment from received RF return signals. The antenna module includes a first transceiver operational at a first frequency and configured to scan a field of view with first RF beams along a first axis, and a second transceiver operational at a second frequency and configured to scan the field of view with second RF beams along a second axis. The radar system also includes a perception module that detects and identifies a target in the surrounding environment from the radar data.

Abstract: Examples disclosed herein relate to a radar warning system positioned in a highway infrastructure. The infrastructure element includes a radar unit that is configured to produce radar data from one or more return radio frequency (RF) beams reflected from a surrounding environment using one or more steerable RF beams radiated to the surrounding environment, detect a moving object in a path of the surrounding environment from the radar data, determine whether the moving object in the path is violating directional criteria, and generate an alert message notifying one or more receiving units to avoid the path of the moving object when the moving object in the path is violating the directional criteria. The infrastructure element also includes a communication unit coupled to the radar unit and configured to send the alert message to the one or more receiving units in the surrounding environment.