Abstract: A system includes a plurality of vehicles and at least one first processor in a first vehicle and at least one second processor in each other of the plurality of vehicles. The first vehicle wirelessly receives remote driving commands, from a remote computing system, instructing control of the first vehicle and executes the remote driving commands to control the first vehicle in accordance with the remote driving commands. The first vehicle wirelessly broadcasts the remote driving commands, including a location of the first vehicle where a given of the driving commands was executed. The second vehicle wirelessly receives the broadcast remote driving commands, stores the received remote driving commands in sequence, and executes the given of the driving commands when a location of the second vehicle corresponds to the location of the first vehicle where the given of the driving commands was executed.

Abstract: Data fusion of radio frequency (RF) and visual data is provided. Via a transceiver of a vehicle, a vehicle-to-everything (V2X) message is received from a remote road entity, the V2X message including one or more V2X data elements descriptive of the remote road entity. Using a camera of the vehicle, modulated light data is captured within a sensing area surrounding an ego road entity, the modulated light data being sent from the remote road entity. A modulated light transmission in the modulated light data is decoded to identify one or more light data elements in the modulated light data descriptive of the road entity. An association of the one or more V2X data elements is performed with the one or more light data elements to identify associated V2X camera objects where the V2X message and the modulated light data are fused into a combined representation of the remote road entity.

Abstract: Localization is performed using a dynamic mesh of vehicle-based Ultra-Wide Band (UWB) anchors. One or more vehicle-based UWB anchors are detected using fixed-location infrastructure UWB anchors, the one or more vehicle-based UWB anchors being components of a vehicle used for access control to the vehicle. The one or more vehicle-based UWB anchors are joined to a mesh of UWB anchors for locating mobile devices, the mesh of UWB anchors including both the fixed-location infrastructure UWB anchors and the dynamic vehicle-based UWB anchors. The mesh of UWB anchors is used to determine an absolute position of a mobile device.

Abstract: Managing vehicle application usage of computing resources is provided. A request for computing resources of a communications network is received from a vehicle application installed to a vehicle. An access point name (APN) is assigned to the vehicle application based on an application identifier corresponding to the vehicle application by accessing stored APN information including a mapping of application identifiers to corresponding APNs. The computing resources are accessed by the vehicle application connecting to the communications network using the APN.

Abstract: A system includes a plurality of vehicles and at least one first processor in a first vehicle and at least one second processor in each other of the plurality of vehicles. The first vehicle wirelessly receives remote driving commands, from a remote computing system, instructing control of the first vehicle and executes the remote driving commands to control the first vehicle in accordance with the remote driving commands. The first vehicle wirelessly broadcasts the remote driving commands, including a location of the first vehicle where a given of the driving commands was executed. The second vehicle wirelessly receives the broadcast remote driving commands, stores the received remote driving commands in sequence, and executes the given of the driving commands when a location of the second vehicle corresponds to the location of the first vehicle where the given of the driving commands was executed.

Abstract: Systems and methods for implementing edge computing assisted vehicle alerts. A multi-access edge computing (MEC) server may be configured to obtain a plurality of messages from one or more vehicles, determine formation of a traffic queue based on the plurality of messages, determine a plurality of zone-based speed limits, determine when a vehicle approaching the traffic queue may be traveling faster than desired based on its location relative to an applicable zone-based speed limit, and generate one or more alerts.

Abstract: A FODM for multi-radio access technology (RAT) vehicle-to-everything (V2X) communication is provided. One or more hardware components are configured to receive connected messages from vehicles, the connected messages specifying vehicle information including vehicle locations of the vehicles; receive perception objects from sensors of roadside infrastructure, the perception objects specifying object locations as perceived by the sensors; utilize a fusion component to combine the vehicle locations and the object locations to form a consolidated object database including data elements specifying each of the vehicles and the perception objects; utilize a sensor data sharing message (SDSM) generator to generate SDSMs describing each of the data elements of the consolidated object database; and utilize a message broker to publish the SDSMs to topics for retrieval by the vehicles.

Abstract: An autonomous vehicle may determine that it has an amount of power remaining projected to be needed to reach a recharging point by autonomously traveling with predefined systems disabled. The vehicle may disable the predefined systems and travel towards the recharging point. Subsequent to the disabling, the autonomous vehicle may determine that it no longer has the amount of power remaining projected to be needed to reach the recharging point. The vehicle may then communicate with a server and request assistance. The vehicle may then travel to an instructed rendezvous point with a second autonomous vehicle, the rendezvous received from the server. The two vehicles may then communicate to allow the first vehicle to leverage a capability of the second autonomous vehicle, responsive to the first and second autonomous vehicles being within communication range, allowing the first vehicle to reach the recharging point via the leveraging.

Abstract: A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive an input video of a scene and audio data associated with the input video, the input video being in a first domain; execute an encoder to map the input video and the audio data to a latent vector in a lower-dimensional latent space; and execute a generator to generate an output video of the scene from the latent vector, the output video being in a second domain. The encoder and the generator are trained to maintain temporal consistency between the input video and the output video by using the audio data.

Abstract: The disclosure generally pertains to systems and methods for providing targeted content to users. In an example method, audio data can be received from a device. Sensor data associated with the device may also be received, and the sensor data may include location data. Upon receiving the audio data, an intent associated with the audio data can be determined. At least one of a product, service, or entity may be determined based on the intent. Content may then be determined based on the sensor data and at least one of the product, service, or entity. The content may be associated with a vehicle. An indication of the content can then be sent to the device.

Abstract: Upon identifying image data associated with an object, radar data associated with the object is identified. A semantic point cloud image is generated based on the image data and the radar data. Transformed semantic point cloud image from a perspective of the object is determined with a variational auto-encoder neural network trained to accept the semantic point cloud image of the object and to generate the transformed semantic point cloud image from the perspective of the object. Physical characteristics of the object are determined based on the transformed semantic point cloud image.

Abstract: Managing vehicle application usage of computing resources is provided. A request for computing resources of a communications network is received from a vehicle application installed to a vehicle. An access point name (APN) is assigned to the vehicle application based on an application identifier corresponding to the vehicle application by accessing stored APN information including a mapping of application identifiers to corresponding APNs. The computing resources are accessed by the vehicle application connecting to the communications network using the APN.

Abstract: The disclosure generally pertains to systems and methods for providing targeted content to users. In an example method, audio data can be received from a device. Sensor data associated with the device may also be received, and the sensor data may include location data. Upon receiving the audio data, an intent associated with the audio data can be determined. At least one of a product, service, or entity may be determined based on the intent. Content may then be determined based on the sensor data and at least one of the product, service, or entity. The content may be associated with a vehicle. An indication of the content can then be sent to the device.

Abstract: A system includes a plurality of vehicles and at least one first processor in a first vehicle and at least one second processor in each other of the plurality of vehicles. The first vehicle wirelessly receives remote driving commands, from a remote computing system, instructing control of the first vehicle and executes the remote driving commands to control the first vehicle in accordance with the remote driving commands. The first vehicle wirelessly broadcasts the remote driving commands, including a location of the first vehicle where a given of the driving commands was executed. The second vehicle wirelessly receives the broadcast remote driving commands, stores the received remote driving commands in sequence, and executes the given of the driving commands when a location of the second vehicle corresponds to the location of the first vehicle where the given of the driving commands was executed.

Abstract: A system includes a multi-access edge computing camera that can determine characteristics of a group of waiting vehicle passengers based on machine-classification and count of individual elements of the group derived from imaging the group with the camera and supplement at least the count based on short-range wireless broadcast received from mobile devices possessed by members of the group. The camera conveys the characteristics to a dispatch process, and the dispatch process determines that a non-dispatched fleet vehicle has present capacity to accommodate the determined characteristics. The dispatch process determine that the characteristics meet a defined predicate for dispatch of the non-dispatched fleet vehicle and responsive to determining that the characteristics meet a defined predicate for dispatch of the non-dispatched fleet vehicle, dispatches the fleet vehicle.

Abstract: An autonomous vehicle may determine that it has an amount of power remaining projected to be needed to reach a recharging point by autonomously traveling with predefined systems disabled. The vehicle may disable the predefined systems and travel towards the recharging point. Subsequent to the disabling, the autonomous vehicle may determine that it no longer has the amount of power remaining projected to be needed to reach the recharging point. The vehicle may then communicate with a server and request assistance. The vehicle may then travel to an instructed rendezvous point with a second autonomous vehicle, the rendezvous received from the server. The two vehicles may then communicate to allow the first vehicle to leverage a capability of the second autonomous vehicle, responsive to the first and second autonomous vehicles being within communication range, allowing the first vehicle to reach the recharging point via the leveraging.

Abstract: Upon identifying image data associated with an object, radar data associated with the object is identified. A semantic point cloud image is generated based on the image data and the radar data. Transformed semantic point cloud image from a perspective of the object is determined with a variational auto-encoder neural network trained to accept the semantic point cloud image of the object and to generate the transformed semantic point cloud image from the perspective of the object. Physical characteristics of the object are determined based on the transformed semantic point cloud image.