Abstract: Systems and methods for analyzing the in-lane driving behavior of an external road agent are disclosed herein. One embodiment generates a sequence of sparse 3D point clouds based on a sequence of depth maps corresponding to a sequence of images of a scene; performs flow clustering based on the sequence of depth maps and a sequence of flow maps to identify points across the sequence of sparse 3D point clouds that belong to a detected road agent; generates a dense 3D point cloud by combining at least some of the points across the sequence of sparse 3D point clouds that belong to the detected road agent; detects one or more lane markings and projects them into the dense 3D point cloud to generate an annotated 3D point cloud; and analyzes the in-lane driving behavior of the detected road agent based, at least in part, on the annotated 3D point cloud.

Abstract: A system, method, and non-transitory computer-readable medium allows for value-anticipating task offloading. The system may include one or more processors and a memory having a task manager module. The task manager module causes the one or more processors to receive a task identifier of a computational task for an application being utilized by a vehicle processor of a vehicle and a state vector describing at least one state of the vehicle and determine, using a utility function, a utility score of the computational task using the task identifier and the state vector which represents an improvement in a functioning of the application if the computational task is offloaded to an external system for processing. Based on the utility score, the one or more processors may offload the computational task to the external system, process the computational task by the vehicle processor of the vehicle, or discard the computational task.

Abstract: The disclosure includes embodiments for resolving vehicle application version differences for connected vehicles. A method includes determining a common vehicle application that is installed in both a remote connected vehicle and an ego vehicle and identifying version differences in a common vehicle application installed in both the ego vehicle and the remote connected vehicle. The method includes forming a vehicular micro cloud. The method includes determining a maximum possible functionality of the common vehicle application. The method includes determining a set of tasks to be completed to achieve the maximum possible functionality. The method includes assigning a first subset of the set of tasks to the ego vehicle and a second subset of the set of tasks to the remote connected vehicle. The method includes using the vehicular micro cloud to cause the ego vehicle to complete the first subset and the remote connected vehicle to complete the second subset.

Abstract: Systems and methods for vehicular-network-assisted federated machine learning are disclosed herein. One embodiment transmits first metadata from a connected vehicle to at least one other connected vehicle; receives, at the connected vehicle, second metadata from the at least one other connected vehicle; receives, at the connected vehicle based on analysis of the first and second metadata, a notification that the connected vehicle has been elected to participate in the current training phase of a federated machine learning process; receives, at the connected vehicle, instructions to prepare the connected vehicle for the next training phase; trains a machine learning model to perform a task at the connected vehicle during the current training phase to produce a locally trained machine learning model; and submits the locally trained machine learning model for aggregation with at least one other locally trained machine learning model to produce an aggregated locally trained machine learning model.

Abstract: A method comprises determining a plurality of available parking spaces within a threshold distance of a destination; determining an initial utility score for each of the available parking spaces based on a distance between each of the available parking spaces and the destination; determining a safety score associated with each of the available parking spaces based on crime data and a distance between each of the parking spaces and a major street, an entrance to a parking facility in which each available parking space is located, or an entrance to a point of interest; determining an adjusted utility score for each of the available parking spaces based on the initial utility score and the safety score associated with each of the available parking spaces; and selecting a parking space among the plurality of available parking spaces based on the adjusted utility score for the parking space.

Abstract: System, methods, and embodiments described herein relate to creating and utilizing one or more vehicular micro clouds to assist in responding to a traffic event. At least one disclosed method includes receiving report information indicating a detection of a traffic event and including a location of the traffic event, defining a region of interest based at least in part on the report information, forming a dependent vehicular micro cloud in the region of interest, determining guidance information based at least in part on the report information, and transmitting the guidance information to the dependent vehicular micro cloud. The dependent vehicular micro cloud executes at least one responsive action based on the guidance information.

Abstract: The disclosure includes embodiments for processing a set of wireless messages by an ego vehicle. A method includes determining a location of an object of interest in a roadway environment that includes the ego vehicle and a set of remote connected vehicles. The method includes segmenting the roadway environment into a plurality of segments. The method includes assigning priority scores to each of the segments based on (1) whether the forward-facing sensors of the remote connected vehicles present in the segment are capable of measuring the object of interest and (2) proximity of the remote connected vehicles in the segment to the object of interest, wherein segments have higher priority scores if the remote connected vehicles present in the segment have forward-facing sensors that are capable of measuring the object of interest and the remote connected vehicles present in the segment are closer to the object of interest.

Abstract: A method includes receiving first environment information related to a first vehicular task from a host vehicle, comparing the first environment information to second environment information captured when a member vehicle performed a second vehicular task corresponding to the first vehicular task using a second set of operating criteria, and determining a first set of operating criteria for performing the first vehicular task based on a similarity score between the first environment information and the second environment information and a success or accuracy rate of the second vehicular task performed by the member vehicle.

Abstract: Systems and methods described herein relate to identifying available parking spaces using connected vehicles. One embodiment performs one of (1) receiving, from a connected vehicle, vehicle position data and vehicle detection and tracking data including at least one bounding box transition event in which a bounding box associated with a particular detected parked vehicle crosses an image-frame boundary; and (2) receiving, from the connected vehicle, the vehicle position data and sensor data, performing object detection and tracking on the sensor data to generate the vehicle detection and tracking data, and detecting the at least one bounding box transition event; generates updated parking-space availability data by performing map matching to associate the vehicle position data and the at least one bounding box transition event with parking spaces in a parking map; and transmits the updated parking-space availability data to one or more participating connected vehicles.

Abstract: The disclosure includes embodiments for a connected vehicle to serve as a hub vehicle for a vehicular micro cloud that enables a set of vehicles to complete computational tasks that are more complicated than an individual vehicle can complete. In some embodiments, a method includes determining that an ego vehicle that includes the onboard vehicle computer is designated as a hub vehicle. The method includes broadcasting a wireless message that includes an invitation for remote vehicles in the limited geographic area to join a vehicular micro cloud managed by the ego vehicle. The method includes forming the vehicular micro cloud which includes the ego vehicle and a set of remote vehicles as members of the vehicular micro cloud. The method includes the ego vehicle serving as the hub vehicle for the vehicular micro cloud.

Abstract: A system and related method for transmitting data to one or more connected vehicles. The system includes one or more processors and a memory. The memory includes one or more modules that cause the one or more processors to establish a communication connection between the system and one or more of the connected vehicles, the connected vehicles forming a vehicular micro cloud and having a shared identification, send a first portion of data to one or more of the connected vehicles, the data having the first portion and a remaining portion, receive acknowledgment data from one or more of the connected vehicles, the acknowledgment data including the shared identification, validate the acknowledgment data, and in response to the acknowledgment data being validated, send the remaining portion of data to one or more of the connected vehicles.

Abstract: The disclosure includes embodiments for an ego vehicle to offload a responsibility for executing an environmental perception analysis of a roadway environment to a different endpoint of a vehicular micro cloud that includes the ego vehicle. A method includes generating sensor data describing whether the sensor has a clear field of view of the roadway environment. The method includes determining performance data describing a computing performance ability of the different endpoint. The method includes determining network data describing an end-to-end latency of transmitting a wireless communication to the different endpoint. The method includes determining that the ego vehicle should offload the responsibility to the different endpoint based on a comparison of the sensor data, performance data, and network data to conditions data describing conditions where the ego vehicle should offload the responsibility.

Abstract: A method for optimizing a parking spot database is provided including determining a utility score of a candidate route to a candidate parking spot of a plurality of parking spots of a parking spot database based on an availability status of a non-candidate parking spot along the candidate route, and selecting the candidate route from a plurality of candidate routes based on the utility score.

Abstract: A method comprises determining a plurality of available parking spaces within a threshold distance of a destination; determining an initial utility score for each of the available parking spaces based on a distance between each of the available parking spaces and the destination; determining a safety score associated with each of the available parking spaces based on crime data and a distance between each of the parking spaces and a major street, an entrance to a parking facility in which each available parking space is located, or an entrance to a point of interest; determining an adjusted utility score for each of the available parking spaces based on the initial utility score and the safety score associated with each of the available parking spaces; and selecting a parking space among the plurality of available parking spaces based on the adjusted utility score for the parking space.

Abstract: A method for performing correlation-based parking availability estimation is provided. The method includes retrieving a plurality of parking availability correlation models, wherein each of the parking availability correlation models estimates parking availability for a target parking block based on parking availability for one or more other parking blocks; selecting a subset of the parking availability correlation models, wherein the subset comprises parking availability correlation models that estimate parking availability of the target parking block based on parking availability for one or more other parking blocks for which current parking availability is known; selecting a parking availability correlation model from the subset based on a model quality indicator associated with each parking availability correlation model; and estimating parking availability for the target parking block based on the selected parking availability correlation model.

Abstract: A parking seeker detection system and method for updating an availability of one or more parking spots of a parking spot database is provided. The method includes determining whether a target vehicle is a registered member vehicle, and in response to determining that the target vehicle is not a registered member vehicle, identifying a target parking spot in which the target vehicle is intending to park and updating an availability of a parking spot of a parking spot database corresponding to the target parking spot.

Abstract: System, methods, and embodiments described herein relate to controlling a vehicular micro cloud, which may include a plurality of vehicle members each having respective positions in a formation and in which two or more of the vehicle members collaboratively execute at least one micro cloud operation. Control may be implemented to monitor performance of the at least one micro cloud operation, monitor operational capabilities of the vehicle members, determine, based at least in part on the operational capabilities of the vehicle members, a change in formation position for at least one of the vehicle members, wherein the change in formation position improves the performance of the at least one micro cloud operation and transmit one or more commands to cause the vehicle members to execute the change in formation position.

Abstract: System, methods, and embodiments described herein relate to managing a vehicular micro cloud. A disclosed method may include determining join/leave protocols for a vehicular micro cloud and transmitting the join/leave protocols to a local vehicle in a vicinity of the vehicular micro cloud prior to the local vehicle joining the vehicular micro cloud. The join/leave protocols can define at least: 1) a procedure for the local vehicle to join the vehicular micro cloud and contribute computing resources to a collaborative micro cloud task, and 2) a protocol for handing an incomplete task when the local vehicle leaves the vehicular micro cloud.

Abstract: The disclosure includes embodiments for message management by an ego vehicle for a Vehicle-to-Everything (V2X) channel used in V2X messages for providing a cooperative driving service. In some embodiments, the method includes receiving a first V2X message including remote sensor data recorded by a remote vehicle. The method includes causing an onboard sensor set of the ego vehicle to record ego sensor data. The method includes determining a channel busy ratio of the V2X channel. The method includes determining a set of factors affecting a state of a recipient vehicle that receives a second V2X message. The method includes selecting a cooperation message species class and an aggregation message species class of the second V2X message based on the set of factors and the state of the recipient vehicle. The method includes selecting, from a set of available classes, a specific class of the second V2X message.

Abstract: A system, method, and non-transitory computer-readable medium allows for value-anticipating task offloading. The system may include one or more processors and a memory having a task manager module. The task manager module causes the one or more processors to receive a task identifier of a computational task for an application being utilized by a vehicle processor of a vehicle and a state vector describing at least one state of the vehicle and determine, using a utility function, a utility score of the computational task using the task identifier and the state vector which represents an improvement in a functioning of the application if the computational task is offloaded to an external system for processing. Based on the utility score, the one or more processors may offload the computational task to the external system, process the computational task by the vehicle processor of the vehicle, or discard the computational task.