Abstract: An identifier for first set of display content on a vehicle display is input to a statistical model that outputs a plurality of probabilities that a user input will select each of a plurality of second set of display contents for display after the first set of display content is displayed. A first probability is identified for a predicted set of display content that is a highest probability in the plurality of probabilities. The plurality of probabilities are provided to at least one of an optimization model and a neural network upon determining an accuracy of the statistical model is below a threshold. Upon receiving, from the at least one of the optimization model and the neural network, a second probability for the predicted set of display content, the display content is selected based on the first and second probabilities. The vehicle display is updated based on the selected set of display content.

Abstract: A vehicle may determine that erratic vehicle behavior has been sensed, based on comparison of a sensed vehicle behavioral characteristic at a given location compared to a predefined expected value of the characteristic. The vehicle may further determine whether an environmental anomaly has been detected in association with the given location and classify the sensed erratic behavior based on whether the environmental anomaly was detected. Responsive to classifying the behavior as erratic based on determining no environmental anomaly was detected, the vehicle may report the erratic behavior to a remote server, along with the given location. The remote server may receive a plurality of such reports for a given location and update a classification of the behavior based on data indicated in the plurality of reports.

Abstract: A system comprises an image sensor with a field of view of an exterior of a vehicle; a human machine interface (HMI) in the vehicle arranged to display images based on data from the image sensor; and a first computer that includes a processor and a memory. The first computer is programmed to provide data from the image sensor to a machine learning program that outputs a bounding box around an object; cause the bounding box around the object to be displayed via the HMI; and transmit object data including an inputted label identifying the object to a second computer that is remote from the vehicle.

Abstract: This disclosure describes systems and methods for personalized route prediction. An example method may include receiving, at a first time, first input data associated with a first route traversed by a vehicle. The example method may also include populating a first database with the input data. The example method may also include receiving, at a third time, second input data associated with a second route traversed by the vehicle. The example method may also include comparing the second input data to the first input data included within the first database. The example method may also include determining, based on the comparison, a first cluster including the first data and the second input data or a second cluster including the second input data. The example method may also include populating a second database based on the first cluster or the second cluster.

Abstract: A profile for an occupant is stored. The profile includes a plurality of clusters of sitting positions for the occupant in a seat and classifications of respective clusters as preferred or nonpreferred. Respective clusters are classified as preferred or nonpreferred based on sitting scores for the respective sitting positions in that cluster. A higher sitting score increases a likelihood of the classification being preferred. A series of pressure maps indicating a respective series of sitting positions of the occupant in the seat are received. The pressure maps include a current pressure map. One of the sitting positions is assigned to one of the clusters that is classified as preferred in response to the sitting score of that sitting position being greater than a threshold score. A physical configuration of the seat is adjusted in response to the current sitting position being in one of the clusters that is classified as nonpreferred.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive a series of pressure maps indicating a respective series of sitting positions of an occupant in a seat, wherein the pressure maps include a current pressure map; update a profile of the occupant based on the pressure maps, wherein the profile includes a plurality of clusters of sitting positions and classifications of the clusters as preferred or nonpreferred, and updating the profile includes sorting one of the sitting positions into one of the clusters that is classified as preferred in response to the occupant remaining in that sitting position for greater than a threshold time; and adjust a physical configuration of the seat in response to the current sitting position being in one of the clusters that is classified as nonpreferred.

Abstract: A vehicle may determine that erratic vehicle behavior has been sensed, based on comparison of a sensed vehicle behavioral characteristic at a given location compared to a predefined expected value of the characteristic. The vehicle may further determine whether an environmental anomaly has been detected in association with the given location and classify the sensed erratic behavior based on whether the environmental anomaly was detected. Responsive to classifying the behavior as erratic based on determining no environmental anomaly was detected, the vehicle may report the erratic behavior to a remote server, along with the given location. The remote server may receive a plurality of such reports for a given location and update a classification of the behavior based on data indicated in the plurality of reports.

Abstract: A system comprises an image sensor with a field of view of an exterior of a vehicle; a human machine interface (HMI) in the vehicle arranged to display images based on data from the image sensor; and a first computer that includes a processor and a memory. The first computer is programmed to provide data from the image sensor to a machine learning program that outputs a bounding box around an object; cause the bounding box around the object to be displayed via the HMI; and transmit object data including an inputted label identifying the object to a second computer that is remote from the vehicle.

Abstract: A vehicle may be configured to detect an object within an interior of the vehicle using a vehicle sensor. The vehicle may further determine whether the object should be removed, based on a determined object value, such as may be determined by comparison of an object characteristic to a database of objects. Also, responsive to determining the object should be removed, the vehicle may schedule removal at an automated object-removal center. The vehicle may also wirelessly notify the object-removal center of vehicle arrival when the vehicle arrives at the object-removal center, including sending identification of the object, receiving indication from the object-removal center that the object has been removed, and confirming removal of the object by attempting to detect the object using the vehicle sensor, the confirmation occurring based on non-detection of the object by the vehicle that originally detected the object and requested removal.

Abstract: An identifier for first set of display content on a vehicle display is input to a statistical model that outputs a plurality of probabilities that a user input will select each of a plurality of second set of display contents for display after the first set of display content is displayed. A first probability is identified for a predicted set of display content that is a highest probability in the plurality of probabilities. The plurality of probabilities are provided to at least one of an optimization model and a neural network upon determining an accuracy of the statistical model is below a threshold. Upon receiving, from the at least one of the optimization model and the neural network, a second probability for the predicted set of display content, the display content is selected based on the first and second probabilities. The vehicle display is updated based on the selected set of display content.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to receive a series of pressure maps indicating a respective series of sitting positions of an occupant in a seat, wherein the pressure maps include a current pressure map; update a profile of the occupant based on the pressure maps, wherein the profile includes a plurality of clusters of sitting positions and classifications of the clusters as preferred or nonpreferred, and updating the profile includes sorting one of the sitting positions into one of the clusters that is classified as preferred in response to the occupant remaining in that sitting position for greater than a threshold time; and adjust a physical configuration of the seat in response to the current sitting position being in one of the clusters that is classified as nonpreferred.

Abstract: An indication of a physical location specified as a name of a geoshortcut is received. The name is identified as corresponds to the geoshortcut according to a format of the name matching a format of geoshortcut name identifiers. The name is sent, to a cloud server maintaining a geoshortcut service, in a request for geoshortcut information regarding the geoshortcut. The geoshortcut information regarding the geoshortcut is received from the cloud server responsive to the request, the geoshortcut information including data identifying the physical location in a native format as received, data identifying the physical location in a predefined location format available across geoshortcuts, and expiration data indicative of for how long the data identifying the physical location is deemed valid. The geoshortcut information is utilized to determine the physical location referenced by the name of the geoshortcut.

Abstract: Multiple display infotainment systems in vehicles provide various options for drivers and passengers to interact with elements on the multiple displays. Techniques include accessing historical driver information that includes previous or typical driver preferences and actions while operating the vehicle. Driving context information and driver state information are received describing the conditions in and around the vehicle. When a signal indicates that an interactive element should be presented to the driver or a passenger, an adaptive rule-based system uses the contextual information and previous history to determine a score for each interaction element. The score and they type of interaction required by the element are then used to determine a location on the multiple displays for presenting the interactive element.

Abstract: A device that includes a processor and a memory, the memory storing instructions executable by the processor such that the device is programmed to identify a wearable device and a set of vehicle data from a vehicle. The user device sends a human machine interface (HMI) message to the wearable device. The HMI message is based at least in part on the set of vehicle data.

Abstract: An indication of a physical location specified as a name of a geoshortcut is received. The name is identified as corresponds to the geoshortcut according to a format of the name matching a format of geoshortcut name identifiers. The name is sent, to a cloud server maintaining a geoshortcut service, in a request for geoshortcut information regarding the geoshortcut. The geoshortcut information regarding the geoshortcut is received from the cloud server responsive to the request, the geoshortcut information including data identifying the physical location in a native format as received, data identifying the physical location in a predefined location format available across geoshortcuts, and expiration data indicative of for how long the data identifying the physical location is deemed valid. The geoshortcut information is utilized to determine the physical location referenced by the name of the geoshortcut.

Abstract: A vehicle may be configured to detect an object within an interior of the vehicle using a vehicle sensor. The vehicle may further determine whether the object should be removed, based on a determined object value, such as may be determined by comparison of an object characteristic to a database of objects. Also, responsive to determining the object should be removed, the vehicle may schedule removal at an automated object-removal center. The vehicle may also wirelessly notify the object-removal center of vehicle arrival when the vehicle arrives at the object-removal center, including sending identification of the object, receiving indication from the object-removal center that the object has been removed, and confirming removal of the object by attempting to detect the object using the vehicle sensor, the confirmation occurring based on non-detection of the object by the vehicle that originally detected the object and requested removal.

Abstract: A vehicle includes a controller programmed to identify tag phrases for locations that express a relationship between the location and a learned location tag. The tag phrases are based on words and word sequences learned from prior selections and inputs of a user. The controller is programmed to communicate the tag phrases to the user and provide trip assistance based on a selected tag phrase chosen by the user. The locations and tag phrases are accessible to devices such that locations are identified with common tag phrases on each of the devices.

Abstract: A vehicle may be configured to detect an object within an interior of the vehicle using a vehicle sensor. The vehicle may further determine whether the object should be removed, based on a determined object value, such as may be determined by comparison of an object characteristic to a database of objects. Also, responsive to determining the object should be removed, the vehicle may schedule removal at an automated object-removal center. The vehicle may also wirelessly notify the object-removal center of vehicle arrival when the vehicle arrives at the object-removal center, including sending identification of the object, receiving indication from the object-removal center that the object has been removed, and confirming removal of the object by attempting to detect the object using the vehicle sensor, the confirmation occurring based on non-detection of the object by the vehicle that originally detected the object and requested removal.

Abstract: A memory stores call records to a plurality of contacts. A processor is programmed to determine probabilities of calling contacts according to current contextual information and call inferences determined from clusters of a context-encoded model created from the call records, each cluster corresponding to a unique combination of ranges of values of the contextual information; and identify the most likely next contact to call as the one of the plurality of contacts having a highest of the probabilities.

Abstract: An example method of crowd-sourcing energy consumption data for vehicles includes controlling a vehicle in response to a predicted energy consumption that is continually updated based on a difference between a previous predicted energy consumption and a previous actual base energy consumption. Another example method of routing a vehicle includes changing a route for a vehicle in response to a predicted energy consumption for the vehicle when travelling the route, the predicted energy consumption based on a difference between a previous predicted energy consumption and a previous actual base energy consumption.