Examples of imaging systems are described herein which may implement microwave or millimeter wave imaging systems. Examples described may implement partitioned inverse techniques which may construct and invert a measurement matrix to be used to provide multiple estimates of reflectivity values associated with a scene. The processing may be partitioned in accordance with a relative position of the antenna system and/or a particular beamwidth of an antenna. Examples described herein may perform an enhanced resolution mode of imaging which may steer beams at multiple angles for each measurement position.

A sensing system provided in a vehicle capable of running in an autonomous driving mode, includes: a LiDAR unit configured to acquire point group data indicating surrounding environment of the vehicle; and a LiDAR control module configured to identify information associated with a target object existing around the vehicle, based on the point group data acquired from the LiDAR unit. The LiDAR control module is configured to control the LiDAR unit so as to increase a scanning resolution of the LiDAR unit in a first angular area in a detection area of the LiDAR unit, wherein the first angular area is an area where the target object exists.

Sensors coupled to a vehicle are calibrated, optionally using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. One vehicle sensor captures a representation of one feature of a sensor target, while another vehicle sensor captures a representation of a different feature of the sensor target, the two features of the sensor target having known relative positioning on the target. The vehicle generates a transformation that maps the captured representations of the two features to positions around the vehicle based on the known relative positioning of the two features on the target.

Aspects of the disclosure relate to training a labeling model to automatically generate labels for objects detected in a vehicle's environment. In this regard, one or more computing devices may receive sensor data corresponding to a series of frames perceived by the vehicle, each frame being captured at a different time point during a trip of the vehicle. The computing devices may also receive bounding boxes generated by a first labeling model for objects detected in the series of frames. The computing devices may receive user inputs including an adjustment to at least one of the bounding boxes, the adjustment corrects a displacement of the at least one of the bounding boxes caused by a sensing inaccuracy. The computing devices may train a second labeling model using the sensor data, the bounding boxes, and the adjustment to increase accuracy of the second labeling model when automatically generating bounding boxes.

Systems and methods of adjusting zone associated risks of a coverage zone covered by one or more sensors of an autonomous driving vehicle (ADV) operating in real-time are disclosed. As an example, the method includes defining a performance limit detection window associated with a first sensor based on a mean time between failure (MTBF) lower limit of the first sensor and a MTBF upper limit of the first sensor. The method further includes determining whether an operating time of the ADV operating in autonomous driving (AD) mode is within the performance limit detection window associated with the first sensor. The method further includes in response to determining that the operating time of the ADV operating in AD mode is within the performance limit detection window of the first sensor, adjusting a zone associated risk of the coverage zone to a performance risk of a second sensor.

The present disclosure is directed to processing data associated with a non-radar type sensing device to identify data points associated with a radar type sensing device that are likely secondary radar reflections such that a processor of a sensing apparatus can direct processing resources to processing radar data that are associated with primary radar reflections. The receipt of secondary radar reflections may cause a processor of a sensing apparatus to identify that an object is located at a location when there is no object in that location. Because of this, methods and apparatus of the present disclosure identify and avoid processing radar data that are likely to be associated with a object that does not exist. Eliminating false radar data, therefore, can prevent a processor of a sensing apparats from performing unnecessary processing tasks and can help prevent that processor from making false determinations.

A sensor evaluation device evaluates a first sensor mounted on a sensor-mounting object. The sensor evaluation device is provided with a specific event detecting unit, and a recording unit. The specific event detecting unit detects a specific event which is at least one of (a) an unrecognized event where a second sensor mounted on the sensor-mounting object recognizes a first target whereas the first sensor does not recognize the first target, and (b) a misrecognized event where the first sensor recognizes a second target whereas the second sensor does not recognize the second target. The recording unit records information on the specific event when detecting the specific event.

Systems and methods are disclosed that provide contextual tracking information to tracking sensor systems to provide accurate and efficient object tracking. Contextual data of a first tracking sensor system is used to identify a tracked object of a second tracking sensor system.

An end-to-end system for data generation, map creation using the generated data, and localization to the created map is disclosed. Mapstreams—or streams of sensor data, perception outputs from deep neural networks (DNNs), and/or relative trajectory data—corresponding to any number of drives by any number of vehicles may be generated and uploaded to the cloud. The mapstreams may be used to generate map data—and ultimately a fused high definition (HD) map—that represents data generated over a plurality of drives. When localizing to the fused HD map, individual localization results may be generated based on comparisons of real-time data from a sensor modality to map data corresponding to the same sensor modality. This process may be repeated for any number of sensor modalities and the results may be fused together to determine a final fused localization result.