Abstract: The disclosure is generally directed to systems and methods associated with communicating privacy rights pertaining to data captured from a vehicle. An example method executed by a processor of a data capture apparatus in a vehicle can include capturing an image. In an example scenario, the image may include an individual who is located outside the vehicle. Furthermore, in some cases, the image can be a part of a video clip containing multiple images. The method further includes generating an identifier for identifying the image(s). The identifier can be a machine-readable symbol such as, for example, a QR-code symbol or a barcode. A notification that includes the identifier may be generated and conveyed to the individual for use by the individual to exercise his/her rights to privacy with respect to the images in which he/she is present.

Abstract: Removal of PII is provided. Sensor data is captured using sensors of a vehicle. Object detection is performed on the sensor data to create a sematic labeling of objects in the sensor data. A model is utilized to classify regions of the sensor data with a public or private labeling according to the sematic labeling and a PII filter corresponding to a jurisdiction of a current location of the vehicle. The sensor data is utilized in accordance with the public or private labeling.

Abstract: A system is disclosed that includes a computer that includes a processor and a memory, the memory including instructions executable by the processor to acquire real world sensor data from a mobile platform for a first time period. The real world sensor data from the mobile platform can be input to a first neural network to predict sensor data of the mobile platform for a second time period that is prior to the first time period. The predicted sensor data and the real world sensor data can be input to a simulation of the mobile platform; wherein the simulation outputs predicted real world operation of the mobile platform based on the predicted sensor data for the second time period and the real world sensor data for the first time period.

Abstract: Rider identification systems and methods using motion sensing are disclosed herein. An example method includes obtaining a location of a mobile device associated with an individual, obtaining sensor data from the mobile device that includes a first motion profile, the sensor data also including environment information around the location, generating a motion model for the individual using the environment information, generating a second motion profile using the motion model, comparing the second motion profile to the first motion profile, and confirming when the second motion profile matches the first motion profile to confirm that the individual is at the location.

Abstract: The disclosure is generally directed to systems and methods for detecting that the vehicle is in a reverse mode, receiving a road surface topology, determining a feature of interest is within a collected image and outside a displayed field of view (FOV) for a rear-facing camera due to the road surface topology, adjusting the displayed FOV for the rear-facing camera to place the feature of interest within the displayed FOV. Receiving a reverse mode indication may be over a controller area network (CAN) bus in the vehicle. Receiving a road surface topology includes receiving an estimate of the road surface topology via at least one of monocular depth estimation, photogrammetric range imaging using structure from motion (SFM), multi-view stereo, imaging radar, lidar and a sensor system on the vehicle.

Abstract: The present disclosure relates to a system and a method for addressing an error in a localization system that includes monitoring a plurality of sensors of a driver assistance system in real-time, with each sensor generating a data stream. The method further includes identifying a sensor having an anomalous data stream and calculating a primary localization and a backup localization. The primary localization calculation includes the anomalous data stream and the backup localization calculation does not include the anomalous data stream. Further, the method includes executing an action when the backup localization error estimate exceeds a threshold.

Abstract: An object can be detected in contact with a steering wheel of a vehicle. A first image of the steering wheel at a first angle of rotation and a second image of the steering wheel at a second angle of rotation are then obtained. A type of the object is identified based on at least one of the first image or the second image, as one of a human hand or a foreign object. A vehicle component is controlled based on the type of object.

Abstract: Handling personally identifiable information (PII) in data streams is provided. Processed sensor data is received, from a plurality of vehicles including sensors capturing raw sensor data, the raw sensor data including captured PII and non-PII. The processed sensor data includes simulated PII created based on the captured PII and one or more layers of the captured PII corresponding to the simulated PII. A request is received from a client device for a portion of the processed sensor data. Access keys corresponding to the request are identified. A result is constructed according to the access keys using the processed sensor data. The constructed result is sent to the client device responsive to the request.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive operation data generated by first components of a vehicle; determine that the vehicle is being operated autonomously by an on-board autonomous-operation module based on the operation data without using output from the on-board autonomous-operation module; and upon determining that the vehicle is being operated autonomously, actuate a second component of the vehicle.

Abstract: A vehicle can include a body coupled communication (BCC) sensor. A computer in the vehicle can detect that an occupant of a vehicle is touching a screen of a user device, based on a signal from the BCC sensor. Further, it can be determined whether the occupant is in the position of the vehicle operator. Upon determining that the occupant is in the position of the vehicle operator, a gaze direction of the occupant of the vehicle can be determined while the occupant is touching the screen. A prediction can then be output that occupant attention is directed to the screen based on the gaze direction and the signal from the BCC sensor.

Abstract: Utilizing local camera compute for camera calibration is provided. Perception outputs are generated, by respective camera processors of each of a plurality of cameras, the perception outputs indicating properties of calibration references located in raw images captured by the respective camera. In a calibration mode, a camera controller, in communication with the plurality of cameras over a data bus, receives the perception outputs from the plurality of cameras. In a runtime mode, the camera controller utilizes calibration data generated based on the perception outputs to fuse compressed images received from the plurality of cameras over the data bus into a combined surround view.

Abstract: A method and apparatus for protecting vehicle data from a vehicle includes identifying the vehicle data to be included in output from a processor that is designated for protection, selecting a digital watermark based on a manner in which the output is subject to at least one of observation or interception, applying the digital watermark to the vehicle data to obtain watermarked output for output from the processor, and communicating a watermark identifier over a communication link of the vehicle to a location external from the vehicle. Detection of the digital watermark in data outside of the vehicle based upon the watermark identifier may be used to determine misuse of the vehicle data.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive lidar data from a lidar device, generate a point cloud from the lidar data, identify an object in the point cloud, and, upon identifying the object, delete a portion of the lidar data that is from a region encompassing the object. The object includes personally identifiable information.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive a first time series of positions of a vehicle sensor mounted on a vehicle from at least one calibration sensor spaced from the vehicle, measured while vibrations are applied to the vehicle; receive a second time series of motion of the vehicle sensor based on data from the vehicle sensor measured while the vibrations are applied to the vehicle; fuse the first and second time series; and determine at least one calibration value for an adjustment model based on the fusion of the first and second time series. The adjustment model is a model of motion of the vehicle sensor relative to the vehicle resulting from motion of the vehicle.

Abstract: A computer is programmed to receive a plurality of first values for a respective plurality of variables transmitted over a communications network of a vehicle; determine a similarity measure between the first values and a plurality of second values of the variables; determine whether to transmit a collection of data transmitted over the communications network based on the similarity measure; and, upon so determining, transmit the collection of data to a server remote from the vehicle. The second values are a most similar set of values from an activation surface for a feature of the vehicle. The activation surface is a surface in a space defined by the variables dividing the space into regions in which activation of the feature is more or less likely than not, respectively, to have occurred when the variables have values in that region.

Abstract: Systems and methods for mitigating certain spoofing of vehicle features are disclosed herein. An example method can include determining input torque values obtained from a steering torque sensor associated with a steering wheel of a vehicle, wherein the input torque values are obtained over a period of time, determining road disturbances using a road disturbance model, applying a driver model that is indicative of human driver hands-on-wheel behaviors, determining when input torque values are indicative of a spoof or human interaction with the steering wheel using the input torque values, the road disturbance model, and the driver model, and executing a remediating measure when the input torque values are indicative of the spoof.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive data recorded in a plurality of vehicles, the data including a plurality of decisions about activating a feature of the vehicles and values of a plurality of variables; receive a plurality of decision scores indicating whether the respective decision was optimal according to the data recorded in the respective vehicle; determine an uncertainty function indicating an uncertainty of a likely value of the decision score based on the values of the variables; determine a set of conditions for the variables based on the uncertainty function; and transmit an instruction to the vehicles to record and upload data when the values of the variables satisfy the set of the conditions.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to predict a quantity of misalignment of an optical sensor based on a projected motion of a vehicle, predict an error of the predicted quantity of misalignment, and actuate the vehicle based on the predicted quantity of misalignment and the predicted error. The vehicle includes the optical sensor.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive a first time series of positions of a vehicle sensor mounted on a vehicle from at least one calibration sensor spaced from the vehicle, measured while vibrations are applied to the vehicle; receive a second time series of motion of the vehicle sensor based on data from the vehicle sensor measured while the vibrations are applied to the vehicle; fuse the first and second time series; and determine at least one calibration value for an adjustment model based on the fusion of the first and second time series. The adjustment model is a model of motion of the vehicle sensor relative to the vehicle resulting from motion of the vehicle.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive sensor data in a time series from a sensor, identify an object in the sensor data, generate anonymized data for the object at a first time in the time series based on the sensor data of the object at the first time, and apply the same anonymized data to an instance of the object in the sensor data at a second time in the time series. The object includes personally identifiable information.