Abstract: A system includes a computer on board a vehicle and a server remote from the vehicle. The computer and the server each store a network graph of actions performable by components of the vehicle that includes costs of transitioning between the actions. The computer is programmed to log a sequence of the actions; upon determining that a sub-sequence of the sequence constitutes a lowest-cost path from the beginning action to the final action based on the network graph, store a reduced sequence including a beginning action and a final action of the sub-sequence ordered immediately after the beginning action, the reduced sequence excluding at least one intermediate action from the sub-sequence; and transmit the reduced sequence to a server remote from the vehicle. The server is programmed to determine the sequence from the reduced sequence based on the network graph.

Abstract: Managing data transfer and privacy via a multi-channel transfer of information is provided. A query is received from a client device, the query indicating an access identifier corresponding to an entity for which data is stored. A consented data pool is accessed to identify a random value corresponding to the access identifier. A hash value is computed using a combination of both the access identifier and the random value. An anonymous data pool of stored data is queried to identify results from the stored data tagged with the hash value. The results are returned to the client device responsive to the query.

Abstract: A knowledge database describes a plurality of triggers, each trigger including a first condition for activating the trigger and a second condition for deactivating the trigger. A controller of the vehicle processes the triggers defined by the knowledge database, including to compare data elements of connected data messages with the conditions of the triggers. The controller augments the connected data messages that occur while the respective trigger is activated with a generated dynamic ID corresponding to the activating of the respective trigger.

Abstract: Intelligent ticketing and data offload planning is provided. A data center receives a ticket request from a vehicle requesting to perform a data upload of vehicle data over a communications network. An optimizer is utilized to generate a ticket, the ticket specifying a time and a location for the vehicle to perform the data upload. The ticket is received from the vehicle. The ticket is validated to ensure that the vehicle should still perform the data upload. The vehicle is indicated to perform the data upload over the communications network responsive to the optimizer confirming the data upload to proceed. The data upload is stored to a storage of the data center.

Abstract: The disclosure is generally directed to systems and methods for a mobile device including transmitting a request by the mobile device for a route that considers transportation modalities and route conditions, the request including location data of the mobile device, receiving a recommended route, the recommended route based on low energy hardware based classification of conditions associated with a plurality of available routes, and receiving a recommended transport modality vehicle and a list of known vehicle identifiers associated with the location data. Low energy wireless signals are received by the mobile device with low energy hardware based classifiers from a mobility vehicle including dedicated hardware including a being a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC) and/or hardware supporting a spiking neural network (SNN), the hardware receiving camera and microphone inputs.

Abstract: Systems and methods are provided herein for creating and building a model of a unique infrastructure, such as a parking structure. The model may be created through the identification of various triggers by a vehicle traversing the infrastructure. The triggers may include, for example, sensors or other devices capable of sensing the vehicle within the infrastructure. The triggers may also be information received from the vehicle itself. Based on the triggers, it may be inferred that various places exist throughout the infrastructure. For example, it may be inferred through two subsequent triggers that a place exists between the two triggers. The place may be added to the model of the infrastructure in between the two triggers. The model may continue to grow in this manner.

Abstract: An audio sample including speech and ambient sounds is transmitted to a vehicle computer. Recorded audio is received from the vehicle computer, the recorded audio including the audio sample broadcast by the vehicle computer and recorded by the vehicle computer and recognized speech from the recorded audio. The recognized speech and text of the speech are input to a machine learning program that outputs whether the recognized speech matches the text. When the output from the machine learning program indicates that the recognized speech does not match the text, the recognized speech and the text are included in a training dataset for the machine learning program.

Abstract: A system includes a computer on board a vehicle and a server remote from the vehicle. The computer and the server each store a network graph of actions performable by components of the vehicle that includes costs of transitioning between the actions. The computer is programmed to log a sequence of the actions; upon determining that a sub-sequence of the sequence constitutes a lowest-cost path from the beginning action to the final action based on the network graph, store a reduced sequence including a beginning action and a final action of the sub-sequence ordered immediately after the beginning action, the reduced sequence excluding at least one intermediate action from the sub-sequence; and transmit the reduced sequence to a server remote from the vehicle. The server is programmed to determine the sequence from the reduced sequence based on the network graph.

Abstract: A system includes a processor that determines a route. The processor determines a plurality of nodes along the route and alternative paths from one node to a successive node along the route through another node. The processor defines the route based on the plurality of nodes and removes at least one node between second and third nodes on the basis that the removed node lies along a least-cost path between the second and third nodes. The processor repeats removal of nodes until a set of minimum nodes to define the route with all non-least-cost path decisions is achieved as a compressed route and transmits the compressed route to at least one second processor that decompresses the compressed route through inclusion of removed nodes, the removed nodes being re-included on the basis of being nodes lying on a least-cost path between two nodes included sequentially in the compressed route.

Abstract: The disclosure is generally directed to systems and methods for a mobile device including transmitting a request by the mobile device for a route that considers transportation modalities and route conditions, the request including location data of the mobile device, receiving a recommended route, the recommended route based on low energy hardware based classification of conditions associated with a plurality of available routes, and receiving a recommended transport modality vehicle and a list of known vehicle identifiers associated with the location data. Low energy wireless signals are received by the mobile device with low energy hardware based classifiers from a mobility vehicle including dedicated hardware including a being a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC) and/or hardware supporting a spiking neural network (SNN), the hardware receiving camera and microphone inputs.

Abstract: Harvesting the high performance computing capabilities of vehicle processors while the vehicles are parked and/or charging may provide use to otherwise unused resources as well as offer a way to discount parking and/or charging costs for the vehicle owner/driver. To harvest the computing capabilities, a dispatcher is utilized that receives incoming complex processing requests and parses the requests into tasks. The dispatcher dispatches the tasks to vehicle processors that are within, for example, a parking garage to which the dispatcher has access. The dispatcher may prioritize requests and/or prioritize the vehicle processors to distribute the tasks to optimize the power consumption, time, and processing capabilities used. When the vehicle processors complete the tasks and return results to the dispatcher, the dispatcher finalizes the job results and provides the results to the requestor. The dispatcher may discount the parking and/or charging costs for the vehicles that performed the computational tasks.

Abstract: Intelligent ticketing and data offload planning is provided. A data center receives a ticket request from a vehicle requesting to perform a data upload of vehicle data over a communications network. An optimizer is utilized to generate a ticket, the ticket specifying a time and a location for the vehicle to perform the data upload. The ticket is received from the vehicle. The ticket is validated to ensure that the vehicle should still perform the data upload. The vehicle is indicated to perform the data upload over the communications network responsive to the optimizer confirming the data upload to proceed. The data upload is stored to a storage of the data center.

Abstract: Devices, systems, and methods for remote control of autonomous vehicles are disclosed herein. A method may include receiving, by a device, first data indicative of an autonomous vehicle in a parking area, and determining, based on the first data, a location of the autonomous vehicle. The method may include determining, based on a the location, first image data including a representation of an object. The method may include generating second image data based on the first data and the first image data, and presenting the second image data. The method may include receiving an input associated with controlling operation of the autonomous vehicle, and controlling, based on the input, the operation of the autonomous vehicle.

Abstract: A system that includes a computer and an unmanned aerial vehicle (UAV) is described. The computer may be programmed to receive, from the UAV, image data of a vehicle parking region; to process the data by identifying an actuation of a UAV indicator that occurs within a predetermined interval of a response of a vehicle in the region; and based on the identification, to determine a location of the vehicle.

Abstract: Managing data transfer and privacy via a multi-channel transfer of information is provided. A query is received from a client device, the query indicating an access identifier corresponding to an entity for which data is stored. A consented data pool is accessed to identify a random value corresponding to the access identifier. A hash value is computed using a combination of both the access identifier and the random value. An anonymous data pool of stored data is queried to identify results from the stored data tagged with the hash value. The results are returned to the client device responsive to the query.

Abstract: Methods and apparatus for vehicle climate control using distributed sensors are disclosed. A disclosed example method includes receiving data from sensors distributed within a vehicle at a first controller, processing the data at the first controller to identify an event associated with the interior of the vehicle and sending an instruction based on the event from the first controller to a second controller of the vehicle to affect an operation of a climate control system of the vehicle.

Abstract: Autonomous vehicles may utilize neural networks for image classification in order to navigate infrastructures and foreign environments, using context dependent transfer learning adaptation. Techniques include receiving a transferable output layer from the infrastructure, which is a model suitable for the infrastructure and the local environment. Sensor data from the autonomous vehicle may then be passed through the neural network and classified. The classified data can map to an output of the transferable output layer, allowing the autonomous vehicle to obtain particular outputs for particular context dependent inputs, without requiring further parameters within the neural network.

Abstract: An audio sample including speech and ambient sounds is transmitted to a vehicle computer. Recorded audio is received from the vehicle computer, the recorded audio including the audio sample broadcast by the vehicle computer and recorded by the vehicle computer and recognized speech from the recorded audio. The recognized speech and text of the speech are input to a machine learning program that outputs whether the recognized speech matches the text. When the output from the machine learning program indicates that the recognized speech does not match the text, the recognized speech and the text are included in a training dataset for the machine learning program.

Abstract: A user destination is identified based on received location information from a user. A first seat in a vehicle is assigned to the user based on the user destination. At least one of the first seat and a second seat in the vehicle is moved upon user entry until a distance between the first seat and the second seat is greater than a distance threshold.

Abstract: Methods and systems for vehicle localization are provided herein. An example method can include obtaining a map within an operating area. A location within the operating area is associated with a pattern of speed bumps that is configured to produce a vehicle pitch response from the vehicle when the vehicle travels over the pattern of speed bumps. The method can include obtaining motion sensor information from a vehicle sensor, determining when the motion sensor information matches the vehicle pitch response, and determining that the vehicle is in the location when the motion sensor information corresponds to the vehicle pitch response of the location.