Abstract: Disclosed are systems and methods for scintillation-based neural network for RADAR target classification. In some aspects, a method includes generating a point cloud from radio frequency (RF) scene responses received from a radio detection and ranging (RADAR) sensor for a scanned scene; populating a rolling buffer with frame data from the point cloud, the frame data including radar cross section (RCS) values, RCS scintillation measurements, and velocity values for objects in the scanned scene; inputting the RCS scintillation measurements and velocity values for an object of the objects to a convolutional neural network (CNN); and receiving a classification of the object from the CNN, wherein the CNN is to utilize a probability density function (PDF) estimate of the RCS scintillation measurements and the velocity values to determine fits with one or more reference PDFs based on a Neyman-Pearson evaluation, and wherein the fits are assessed to classify the object.

Abstract: Curvelet-based low level fusion of camera and RADAR sensor information is disclosed and includes processing RADAR data corresponding to a scene to generate a RADAR point cloud and processing camera image data corresponding to the scene using a curvelet transform to identify a target of interest in the scene and generate for the target of interest a target type, (x,y) coordinate values, and a curvelet magnitude per decomposition level. If discrepancies exist between (x,y) coordinate values of the RADAR point cloud and the target type, (x,y) coordinate values, and curvelet magnitude per composition level of the target of interest, a portion of the RADAR data processing is repeated to regenerate the RADAR point cloud; otherwise, the RADAR point cloud to a perception stack of a vehicle.

Abstract: A current set of radar data may be combined with previous sets of radar data to create a combined set of radar data. Each of these sets of radar data and the combined set of radar data may include various data points and each of these data points may be associated with certain specific features or classifications. The set of combined data may then be pre-processed to identify distances to associate with certain data points, locations to associate with those data points, and velocities associated with the data points such that each of the respective data points may be mapped and tagged with data that identifies identify positions, velocities, and other physical details of the respective data points. This pre-processed data may then be processed by a machine learning process to identify kinematic information that may then be provided to a tracking system of an AV.

Abstract: The present disclosure is directed to combining the strengths of different methods of analyzing collected sensor data to updating a driving pattern of an automated vehicle (AV). This may include combining data from sets of data that track movement of objects over time with instantaneously received sensor data based on a series of steps that include accessing data that tracks the motion of objects in the field of view of a sensing apparatus, receiving current sensor data that includes a component of current or instantaneous object motion, and identifying whether controls of AV should be maintained or changed. When controls of the AV are maintained, an AV may be controlled to stay in driving in a same lane of a roadway at a same velocity. When controls of an AV are changed, changes may include applying, increasing a velocity, or altering the course of the AV.

Abstract: Depth data processing systems and methods are disclosed. A mapping system receives, from one or more depth sensors, depth sensor data that includes a plurality of points corresponding to an environment. The mapping system uses one or more trained machine learning models to perform semantic segmentation of the plurality of points, to classify a first subset of the points into a first category and to classify a second subset of the points into a second category. The mapping system clusters the plurality of points into a plurality of clusters based on the semantic segmentation. At least some of the first subset of the points are clustered into a first cluster and at least some of the second subset of the points are clustered into a second cluster. The mapping system generates a map of at least a portion of the environment based on the plurality of clusters.