Abstract: A system for contribution-aware federated learning is provided. The system includes a server and a plurality of vehicles. Each of the plurality of vehicles includes a controller programmed to: train a local machine learning model using first local data; obtain metadata for hardware elements of corresponding vehicle; transmit the trained local machine learning model and the metadata to a server; receive an aggregated machine learning model from the server; and train the aggregated machine learning model using second local data. The server generates the aggregated machine learning model based on the trained local machine learning models and the metadata received from the plurality of vehicles.

Abstract: System, methods, and other embodiments described herein relate to selecting servers and allocating resources concurrently for offloading computing tasks from vehicles. In one embodiment, a method includes acquiring characteristics of a vehicle and a server for an offloading request, wherein the offloading request is associated with a computing task of the vehicle. The method also includes, upon satisfying criteria for optimization associated with executing the computing task remotely, determining server selection and resource allocation by processing the characteristics using modeling. The method also includes communicating the server selection and the resource allocation to the vehicle.

Abstract: An edge device for providing an HD map to a vehicle is provided. The edge device includes a controller programmed to obtain an HD map request including a task type from a vehicle, obtain a status of a wireless channel between the vehicle and the edge device, determine an HD map version among a plurality of versions based on the status of the wireless channel and the task type, and transmit the determined HD map version to the vehicle.

Abstract: A method is provided including receiving a planned route of a vehicle and a request to download content from a cloud server, the planned route traveling through an area covered by a plurality of edge servers, determining a state comprising possible connections between the vehicle and each of the plurality of edge servers at a plurality of time steps during the planned route, inputting the state to a trained model, the model being trained to output an action comprising a partition of the content across the plurality of edge servers that minimizes latency of transmission of the content from the cloud server to the vehicle via the plurality of edge servers, based on the state, and partitioning the content across the plurality of edge servers based on the action out by the trained mode.

Abstract: An edge device for providing an HD map to a vehicle is provided. The edge device includes a controller programmed to: obtain a head pose of an occupant of a vehicle; obtain a location of the vehicle following an original route; analyze the head pose and the location of the vehicle to determine a potential route for the vehicle, the potential route being different from the original route, and transmit HD map information corresponding to the potential route to the vehicle in response to determining the potential route.

Abstract: A server includes a controller programmed to obtain information about a first perception model installed in a vehicle. The controller is further programmed to determine a value of updating the first perception model. The controller is further programmed to determine whether the first perception model needs to be updated to a second perception model based on the value of updating the first perception model. The controller is further programmed to transmit the second perception model to the vehicle in response to determining that the first perception model needs to be updated to the second perception model.

Abstract: A method includes receiving features associated with an object to be tracked, receiving an estimated location of the object, determining a region of interest with respect to a first connected vehicle that includes the estimated location of the object, transmitting the features and the region of interest to the first connected vehicle, receiving object data associated with the object from the first connected vehicle, the object data comprising a location of the object, and updating an object track associated with the object based on the object data, the object track comprising the location of the object at a plurality of time steps.

Abstract: A method is provided including receiving a planned route of a vehicle and a request to download content from a cloud server, the planned route traveling through an area covered by a plurality of edge servers, determining a state comprising possible connections between the vehicle and each of the plurality of edge servers at a plurality of time steps during the planned route, inputting the state to a trained model, the model being trained to output an action comprising a partition of the content across the plurality of edge servers that minimizes latency of transmission of the content from the cloud server to the vehicle via the plurality of edge servers, based on the state, and partitioning the content across the plurality of edge servers based on the action out by the trained mode.

Abstract: System, methods, and other embodiments described herein relate to improving scheduling tasks within an edge-computing environment. In one embodiment, a method includes, upon establishing a communication connection with a vehicle by an edge device of the edge-computing environment, collecting offloading information about the vehicle including task information describing at least a vehicle task that is to be offloaded to the edge device and context information about aspects relating to operation of the vehicle. The method includes triggering offloading of the vehicle task to the edge device in response to determining that at least the context information satisfies a scheduling threshold. The method includes providing, by the edge device, a result of executing the vehicle task to the vehicle.

Abstract: Systems, methods, and other embodiments described herein relate to determining an optimal data offloading rate for one or more connected mobile devices. In one embodiment, a method includes receiving mobile device transmission information and receiving edge server resource information. The method includes determining an offloading rate for a mobile device to an edge server based on the mobile device transmission information, the edge server resource information, and a mean-field game algorithm. The method includes outputting the offloading rate to the mobile device.

Abstract: A server includes a controller programmed to obtain information about a first perception model installed in a vehicle. The controller is further programmed to determine a value of updating the first perception model. The controller is further programmed to determine whether the first perception model needs to be updated to a second perception model based on the value of updating the first perception model. The controller is further programmed to transmit the second perception model to the vehicle in response to determining that the first perception model needs to be updated to the second perception model.

Abstract: In accordance with one embodiment of the present disclosure, a system for generating surrounding views includes a controller. The controller may be programmed to perform operations including receiving a status information from a remote source, receiving a surround view system (SVS) request having a set of requirements from a vehicle, identifying one or more remote sources based on the status information of the one or more remote sources and the set of requirements of the SVS request, and directing the one or more remote sources to stream SVS data to the vehicle.

Abstract: Systems, methods, and other embodiments described herein relate to determining an optimal data offloading rate for one or more connected mobile devices. In one embodiment, a method includes receiving mobile device transmission information and receiving edge server resource information. The method includes determining an offloading rate for a mobile device to an edge server based on the mobile device transmission information, the edge server resource information, and a mean-field game algorithm. The method includes outputting the offloading rate to the mobile device.

Abstract: Systems and methods for maintaining a service session in an automotive edge computing environment are disclosed herein. One embodiment computes a first estimation result pertaining to computation resources of a current edge server with which a vehicle is in communication; computes a second estimation result pertaining to link quality; computes a third estimation result pertaining to service quality; compares the first, second, and third estimation results with first, second, and third predetermined thresholds, respectively; selects a new edge server with which to maintain the service session and initiates a service migration request, when the first predetermined threshold is triggered; initiates a wireless access handover request, when only the second predetermined threshold is triggered; and selects a new edge server with which to maintain the service session and initiates a service migration request, when only the third predetermined threshold is triggered and one of two predetermined conditions is met.

Abstract: Systems and methods described herein relate to simulating edge-computing deployment in diverse terrains. One embodiment receives a layer-selection input specifying which layers among a plurality of layers in a simulation model of an edge-computing deployment are to be included in a simulation experiment; receives a set of input parameters for each of the layers specified by the layer-selection input, the set of input parameters for one of the layers specified by the layer-selection input including selection of a vehicular application whose performance in the edge-computing deployment is to be evaluated via the simulation experiment; executes the simulation experiment in accordance with the layer-selection input and the set of input parameters for each of the layers specified by the layer-selection input; and outputs, from the simulation experiment, performance data for the selected vehicular application in the edge-computing deployment.

Abstract: System, methods, and other embodiments described herein relate to selecting servers and allocating resources concurrently for offloading computing tasks from vehicles. In one embodiment, a method includes acquiring characteristics of a vehicle and a server for an offloading request, wherein the offloading request is associated with a computing task of the vehicle. The method also includes, upon satisfying criteria for optimization associated with executing the computing task remotely, determining server selection and resource allocation by processing the characteristics using modeling. The method also includes communicating the server selection and the resource allocation to the vehicle.

Abstract: A system for coordinating data offloading includes a controller. The controller is configured to at least receive a set of data metrics corresponding to a set of vehicles, generate a set of vehicle clusters based on the set of data metrics, determine a thread distribution based on the set of vehicle clusters, and transmit a data offloading control signal to each of the set of vehicles according to the thread distribution.

Abstract: Systems and methods for scheduling environment perception-based data offloading for numerous connected vehicles are disclosed. In one embodiment, a method for offloading data includes capturing an image of a view of interest from a vehicle, segmenting the image into a plurality of blocks, and determining a scheduling priority for each of one or more blocks among the plurality of blocks based on block values, wherein the block values relate to one or more objects of interest contained in each of the one or more blocks. The method further includes offloading, from the vehicle to a server, one or more blocks based on the scheduling priority of the one or more blocks.

Abstract: Systems and methods described herein relate to generating a task offloading strategy for a vehicular edge-computing environment. One embodiment simulates a vehicular edge-computing environment in which one or more vehicles perform computational tasks whose data is partitioned into segments and performs, for each of a plurality of segments, a Deep Reinforcement Learning (DRL) training procedure that includes receiving state-space information regarding the one or more vehicles and one or more intermediate network nodes; inputting the state-space information to a policy network; generating, from the policy network, an action concerning a current segment; and assigning a reward to the policy network for the action in accordance with a predetermined reward function. This embodiment produces, via the DRL training procedure, a trained policy network embodying an offloading strategy for segmentation offloading of computational tasks from vehicles to one or more of an edge server and a cloud server.

Abstract: Systems and methods described herein relate to simulating edge-computing deployment in diverse terrains. One embodiment receives a layer-selection input specifying which layers among a plurality of layers in a simulation model of an edge-computing deployment are to be included in a simulation experiment; receives a set of input parameters for each of the layers specified by the layer-selection input, the set of input parameters for one of the layers specified by the layer-selection input including selection of a vehicular application whose performance in the edge-computing deployment is to be evaluated via the simulation experiment; executes the simulation experiment in accordance with the layer-selection input and the set of input parameters for each of the layers specified by the layer-selection input; and outputs, from the simulation experiment, performance data for the selected vehicular application in the edge-computing deployment.