Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

Abstract: According to one aspect, a radar system suitable for use in an autonomous vehicle is configured to provide a relatively high resolution in azimuth. The radar system may include multiple antenna blocks which may each include a transmitter and a receiver, and may be provided in an array, e.g., in a horizontal array. Each radar block may define an airgap therein which includes azimuth power dividers, elevation power dividers, vertical power dividers, and open-ended waveguides.

Abstract: A method is provided that includes a vehicle receiving data from an external computing device indicative of at least one other vehicle in an environment of the vehicle. The vehicle may include a sensor configured to detect the environment of the vehicle. The at least one other vehicle may include at least one sensor. The method also includes determining a likelihood of interference between the at least one sensor of the at least one other vehicle the sensor of the vehicle. The method also includes initiating an adjustment of the sensor to reduce the likelihood of interference between the sensor of the vehicle and the at least one sensor of the at least one other vehicle responsive to the determination.

Abstract: A plurality of radar units is included in an overall radar module such that the plurality of radar units effectively cooperates to provide an approximately 360-degree field-of-view over a relatively long range. The overall radar module may include a ring-shaped printed circuit board, and a rim that includes multiple radar units positioned to substantially cover a 360-degree field-of-view. Radar units of the overall radar module may be grouped together such that two or more radar units may operate substantially synchronously, e.g., as a substantially single radar unit.

Abstract: Disclosed herein are systems for navigating an autonomous or semi-autonomous fleet comprising a plurality of autonomous or semi-autonomous vehicles within a plurality of navigable pathways within an unstructured open environment.

Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

Abstract: A method is provided that includes a vehicle receiving data from an external computing device indicative of at least one other vehicle in an environment of the vehicle. The vehicle may include a sensor configured to detect the environment of the vehicle. The at least one other vehicle may include at least one sensor. The method also includes determining a likelihood of interference between the at least one sensor of the at least one other vehicle the sensor of the vehicle. The method also includes initiating an adjustment of the sensor to reduce the likelihood of interference between the sensor of the vehicle and the at least one sensor of the at least one other vehicle responsive to the determination.

Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

Abstract: An inertial measurement unit (IMU) may be used to align a plurality of radar units coupled to a vehicle via a plurality of mounting structures. The IMU may be placed at a reference location and reference-location data may be captured. The IMU may be coupled to each of the mounting structures and, at each mounting structure, respective mounting-location inertial measurement data may be captured using the IMU. For each mounting structure, a measured roll angle, measured elevational angle, and measured azimuthal angle is determined based on at least the mounting-location inertial measurement obtained at the mounting structure and the reference inertial measurement. Further, for each mounting structure, offsets are determined for the measured roll angle, the measured elevational angle, and the measured azimuthal angle. One or more of the mounting structures and/or radar units are adjusted based on one or more of the offsets.

Abstract: An example method may involve forming, in a first metal layer, a first half of waveguide channels including an input waveguide channel, a plurality of wave-dividing channels, and a plurality of wave-radiating channels. The input waveguide channel may include an input port for receiving electromagnetic waves into the waveguide channels, and the first half of the plurality of wave-radiating channels may include wave-directing members configured to propagate sub-portions of waves from the first metal layer to another metal layer. The method may also involve forming, in a second metal layer, a second half of the waveguide channels. The second half of the wave-radiating channels may include pairs of output ports configured to radiate the sub-portions of waves out of the second metal layer. The method may further involve fastening the first metal layer to the second metal layer so as to substantially align the halves of the waveguide channels.

Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

Abstract: An example method for a beamforming network for feeding short wall slotted waveguide arrays. The beamforming network may include six beamforming network outputs, where each beamforming network output is coupled to one of a set of waveguide inputs. Further, the beamforming network may include a cascaded set of dividers configured to split electromagnetic energy from a beamforming network input to the six phase-adjustment sections. The cascade may include a first level of the cascade configured to split the electromagnetic energy from the beamforming network input into two first-level beamforming waveguides, a second level configured to split the electromagnetic energy from each of two first-level beamforming waveguides into two respective second-level beamforming waveguides, and a third level of the cascade configured to split the electromagnetic energy from one of two respective second-level beamforming waveguides into two respective third-level beamforming waveguides.

Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

Abstract: Disclosed herein are embodiments that relate to phase coded linear frequency modulation for a radar system. Embodiments include transmitting at least two signal pulses. The transmitting includes transmitting a first pulse with a first phase modulation and a first chip rate, and transmitting a second pulse with a second phase modulation and a second chip rate. The second chip rate may be different than the first chip rate. Embodiments also include receiving a signal that includes at least two reflection signals associated with reflection of the at least two transmitted signal pulses. Embodiments further include processing the received signal to determine target information. The processing includes filtering the received signal to time-align the at least two reflection signals. The filtering includes applying a frequency-dependent time delay to one or more of the at least two reflection signals. Additionally, embodiments include removing phase code modulations from the time-aligned reflection signals.

Abstract: A method is provided that includes a vehicle receiving data from an external computing device indicative of at least one other vehicle in an environment of the vehicle. The vehicle may include a sensor configured to detect the environment of the vehicle. The at least one other vehicle may include at least one sensor. The method also includes determining a likelihood of interference between the at least one sensor of the at least one other vehicle the sensor of the vehicle. The method also includes initiating an adjustment of the sensor to reduce the likelihood of interference between the sensor of the vehicle and the at least one sensor of the at least one other vehicle responsive to the determination.

Abstract: A method is provided that includes a vehicle receiving data from an external computing device indicative of at least one other vehicle in an environment of the vehicle. The vehicle may include a sensor configured to detect the environment of the vehicle. The at least one other vehicle may include at least one sensor. The method also includes determining a likelihood of interference between the at least one sensor of the at least one other vehicle the sensor of the vehicle. The method also includes initiating an adjustment of the sensor to reduce the likelihood of interference between the sensor of the vehicle and the at least one sensor of the at least one other vehicle responsive to the determination.

Abstract: A method and apparatus are provided for optimizing one or more object detection parameters used by an autonomous vehicle to detect objects in images. The autonomous vehicle may capture the images using one or more sensors. The autonomous vehicle may then determine object labels and their corresponding object label parameters for the detected objects. The captured images and the object label parameters may be communicated to an object identification server. The object identification server may request that one or more reviewers identify objects in the captured images. The object identification server may then compare the identification of objects by reviewers with the identification of objects by the autonomous vehicle. Depending on the results of the comparison, the object identification server may recommend or perform the optimization of one or more of the object detection parameters.

Abstract: An example method for a beamforming network for feeding short wall slotted waveguide arrays. The beamforming network may include six beamforming network outputs, where each beamforming network output is coupled to one of a set of waveguide inputs. Further, the beamforming network may include a cascaded set of dividers configured to split electromagnetic energy from a beamforming network input to the six phase-adjustment sections. The cascade may include a first level of the cascade configured to split the electromagnetic energy from the beamforming network input into two first-level beamforming waveguides, a second level configured to split the electromagnetic energy from each of two first-level beamforming waveguides into two respective second-level beamforming waveguides, and a third level of the cascade configured to split the electromagnetic energy from one of two respective second-level beamforming waveguides into two respective third-level beamforming waveguides.

Abstract: An inertial measurement unit (IMU) may be used to align a plurality of radar units coupled to a vehicle via a plurality of mounting structures. The IMU may be placed at a reference location and reference-location data may be captured. The IMU may be coupled to each of the mounting structures and, at each mounting structure, respective mounting-location inertial measurement data may be captured using the IMU. For each mounting structure, a measured roll angle, measured elevational angle, and measured azimuthal angle is determined based on at least the mounting-location inertial measurement obtained at the mounting structure and the reference inertial measurement. Further, for each mounting structure, offsets are determined for the measured roll angle, the measured elevational angle, and the measured azimuthal angle. One or more of the mounting structures and/or radar units are adjusted based on one or more of the offsets.

Abstract: Embodiments of a system and method for tracking objects are described herein. Aspects of this disclosure efficiently update object “belief” data by creating a bitmap representation of object locations and velocities. The bitmap provides a three-dimensional representation of the object as viewed by one or more sensors. The bitmap representations are blended with sensor data over time to determine a current object belief state which can accurately account for asynchronous sensor data. Peaks in the belief data, which may be represented by pixels with an intensity value above a threshold value, are identified as likely objects. Additional sensor data is used to detect longitudinal velocities located at one or more of the peaks.