Abstract: One or more embodiments of the present disclosure relate to obtaining a first state estimate corresponding to an object, the first state estimate including a first velocity vector estimate corresponding to the object. The disclosure may further relate to receiving first sensor data corresponding to a first portion of the object. The embodiments may further include determining a first expected measurement corresponding to the first portion, the first expected measurement including a first expected range rate determined based at least on the first angle measurement and the first velocity vector estimate of the first state estimate. And, determining a second state estimate corresponding to the object, the second state estimate including a second velocity vector estimate corresponding to the object and determined based at least on the first range rate measurement and the first expected range rate.

Abstract: In various examples, methods and systems are provided for sampling and transmitting the most useful information from a radar signal representing a scene while staying within the computational and storage confines of a standard automotive radar sensor and the bandwidth constraints of a standard communication link between a radar sensor and processing unit. Disclosed approaches may select a patch of frequency bins that correspond to radar signals based at least on proximities of the frequency bins to one or more frequency bins corresponding to at least one peak and/or detection point in the radar signals. Data representing samples corresponding to the patch of frequency bins may be transmitted to the processing unit and applied to one or more machine learning models in order to accurately classify, identify, and/or track objects.

Abstract: In various examples, methods and systems are provided for sampling and transmitting the most useful information from a radar signal representing a scene while staying within the computational and storage confines of a standard automotive radar sensor and the bandwidth constraints of a standard communication link between a radar sensor and processing unit. Disclosed approaches may select a patch of frequency bins that correspond to radar signals based at least on proximities of the frequency bins to one or more frequency bins corresponding to at least one peak and/or detection point in the radar signals. Data representing samples corresponding to the patch of frequency bins may be transmitted to the processing unit and applied to one or more machine learning models in order to accurately classify, identify, and/or track objects.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three-dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: Embodiments of the present disclosure relate to a system and method used to transfer image data via Ethernet. In some embodiments, the method may include determining, using a machine learning model, an estimated velocity corresponding to an object based at least on measured RADAR data, where the measured RADAR data may correspond to RADAR detections associated with the object. In some embodiments, the method may further include determining expected RADAR data corresponding to the object based at least on the estimated velocity. Some embodiments may additionally include updating one or more parameters of the machine learning model based on the difference between the measured RADAR data and the expected RADAR data.

Abstract: One or more embodiments of the present disclosure relate to obtaining a first state estimate corresponding to an object, the first state estimate including a first velocity vector estimate corresponding to the object. The disclosure may further relate to receiving first sensor data corresponding to a first portion of the object. The embodiments may further include determining a first expected measurement corresponding to the first portion, the first expected measurement including a first expected range rate determined based at least on the first angle measurement and the first velocity vector estimate of the first state estimate. And, determining a second state estimate corresponding to the object, the second state estimate including a second velocity vector estimate corresponding to the object and determined based at least on the first range rate measurement and the first expected range rate.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: Systems and methods are disclosed that relate to freespace detection using machine learning models. First data that may include object labels may be obtained from a first sensor and freespace may be identified using the first data and the object labels. The first data may be annotated to include freespace labels that correspond to freespace within an operational environment. Freespace annotated data may be generated by combining the one or more freespace labels with second data obtained from a second sensor, with the freespace annotated data corresponding to a viewable area in the operational environment. The viewable area may be determined by tracing one or more rays from the second sensor within the field of view of the second sensor relative to the first data. The freespace annotated data may be input into a machine learning model to train the machine learning model to detect freespace using the second data.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, methods and systems are provided for sampling and transmitting the most useful information from a radar signal representing a scene while staying within the computational and storage confines of a standard automotive radar sensor and the bandwidth constraints of a standard communication link between a radar sensor and processing unit. Disclosed approaches may select a patch of frequency bins that correspond to radar signals based at least on proximities of the frequency bins to one or more frequency bins corresponding to at least one peak and/or detection point in the radar signals. Data representing samples corresponding to the patch of frequency bins may be transmitted to the processing unit and applied to one or more machine learning models in order to accurately classify, identify, and/or track objects.

Abstract: In various examples, systems are described herein that may evaluate one or more radar detections against a set of filter criteria, the one or more radar detections generated using at least one sensor of a vehicle. The system may then accumulate, based at least on the evaluating, the one or more radar detections to one or energy levels that correspond to one or more locations of the one or more radar detections in a zone positioned relative to the vehicle. The system may then determine one or more safety statuses associated with the zone based at least on one or more magnitudes of the one or more energy levels. The system may transmit data, or take some other action, that causes control of the vehicle based at least on the one or more safety statuses.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: A device for stimulation, the device comprising a hollow body having a first end and a second end, wherein a first connection mechanism is located distal to the first end and the second end has an opening to an interior cavity of the hollow body, a handle attached to the first connection mechanism, a motor positioned within the interior cavity of the hollow body, and a lower panel mechanically secured to the motor, wherein when the motor is activated the lower panel moves in a predetermined pattern.

Abstract: Described are occupant positioning systems, and methods of use thereof, which combine image capture and radar or ultrasonic sensors, determine the head position and/or velocity of a vehicle occupant's head in three dimensions for use in a driver monitoring application. The driver monitoring applications may include features such as driver drowsiness estimation and indication, driver attention monitoring, driver gaze direction and driver gaze positioning, driver identification, head-up display adjustment and automatic sun blocking. These are features that can improve the operational safety of the vehicle.