Abstract: A system for producing a map of a parking facility can include a processor and a memory. The memory can store an ensemble of experts module and a communications module. The ensemble of experts module can include instructions that cause the processor to: (1) segment, operating at least one first neural network-based model, a remote sensing image of the parking facility to produce bounding boxes of parking blocks, (2) segment, operating at least one second neural network-based model, an object, in the remote sensing image, associated with obscuring the bounding boxes, and (3) modify, to produce the map of the parking facility, the bounding boxes to account for an effect of the object. The communications module can include instructions that cause the processor to communicate the map to a device associated with a vehicle to control an operation of the device.

Abstract: Embodiments of systems and methods for vehicle environment detection include a vehicle and one or more processors. The vehicle includes a camera operable to generate an image of an environment surrounding the vehicle. The environment includes one or more parking spaces and an object removably attached to the vehicle. The one or more processors are operable to identify the object, generate, using a pre-trained depth algorithm, a depth map based on the image, generate a boundary of the parking spaces based on the depth map excluding the object, determine whether a distance between the boundary of the parking spaces and the vehicle is less than a threshold value, and output an alert in response to determining that the distance is less than the threshold value.

Abstract: Systems and methods are provided for streaming driving scenes. The systems and methods may retrieve a driving scene from a database of sensor data of a plurality of vehicles. The driving scene may include a plurality of images corresponding to a selected view. The systems and methods may determine a trajectory of an ego vehicle. The trajectory of the ego vehicle may be based on at least one of an acceleration, suspension, speed, breaking, maneuvering, direction, driving pattern, road condition, and environmental condition encountered by the ego vehicle during travel. The systems and methods may synchronize the driving scene according to the trajectory. Synchronizing the driving scene according to the trajectory may include arranging the plurality of images to align with a movement of travel of the ego vehicle. The systems and methods may output the synchronized driving scene to a surface of a cabin of the ego vehicle.

Abstract: Embodiments of systems and methods for generating see-through images include a vision sensor configured to generate an image of an environmental scene surrounding a vehicle, and one or more processors operable to generate, using a pre-trained neural network, a depth map of the environmental scene based on the image, determine whether the environmental scene includes a blocking object by comparing the depth map with historical depth information of the environmental scene, in response to determining that the environmental scene includes the blocking object, update, using the pre-trained neural network, the depth map by replacing depth information of the blocking object with the historical depth information of the environmental scene at an area of the blocking object, and project the updated depth map into a see-through image of the environmental scene.

Abstract: Systems and methods are provided for the reduction or elimination of redundant, uninteresting, and/or inefficient communications to remote devices (e.g. cloud servers) from vehicles collecting observation data. In-vehicle examples of the systems and methods are provided, wherein the associated methods for reducing or eliminating such redundant, uninteresting, and/or inefficient communications are performed on a vehicle. Cloud-based examples of the systems and methods are provided, wherein the associated methods for reducing or eliminating such redundant, uninteresting, and/or inefficient communications are performed on a remote device (e.g. a cloud server).

Abstract: A system includes sensors that determine one or more attributes associated with operation of a vehicle when the vehicle is in a operational status and to capture sensor data associated with operation of the vehicle. The system includes one or more datastores, one or more processors, and a memory storing instructions that, when executed by the one or more processors, cause the system to perform operations. The operations include obtaining the captured sensor data, inferring a hierarchical criteria to implement selective retaining of the obtained sensor data based on the obtained attributes, selectively retaining a subset of the obtained sensor data according to the inferred hierarchical criteria, reformatting the selectively retained subset of the obtained sensor data; and persisting the reformatted and selectively retained subset of the obtained sensor data to the one or more datastores.

Abstract: Embodiments provide systems and methods that tailor, based on driving scenario for a vehicle: (1) operation of a neural network (used to process image data obtained during the driving scenario) to skip a determined number of neural layers; and (2) input scale for image data provided to the neural network. In this way, systems and methods can scale computational power and efficiency for image processing tasks as needed based on the nature and relative complexity of different driving scenarios.

Abstract: Embodiments of systems and methods for adapted vehicle geometry include a vehicle and one or more processors. The vehicle includes a camera operable to generate an image of an environment surrounding the vehicle. The environment includes a parking space and an object removably attached to the vehicle. The one or more processors operable to identify the object as attached to the vehicle, generate, using a pre-trained depth algorithm, a depth map based on the image, generate a boundary of the parking space and a boundary of the vehicle combined with the object based on the depth map, determine whether a distance between the boundary of the parking space and the boundary of the vehicle combined with the object is less than a threshold value, and output an alert in response to determining that the distance is less than the threshold value.

Abstract: Systems and methods are provided for the reduction or elimination of redundant, uninteresting, and/or inefficient communications to remote devices (e.g. cloud servers) from vehicles collecting observation data. In-vehicle examples of the systems and methods are provided, wherein the associated methods for reducing or eliminating such redundant, uninteresting, and/or inefficient communications are performed on a vehicle. Cloud-based examples of the systems and methods are provided, wherein the associated methods for reducing or eliminating such redundant, uninteresting, and/or inefficient communications are performed on a remote device (e.g. a cloud server).

Abstract: Systems and methods described herein relate to configuring a hierarchical traffic management system. One embodiment receives, at a cloud server, a request from an application, the request including requirements and implicating configuration of a hierarchical traffic management system; determines, based on information received from one or more connected vehicles in an area of interest pertaining to the request, a minimum density of connected vehicles in the area of interest to meet the requirements; calculates an optimum number of connected vehicles to assign to a section manager in the hierarchical traffic management system; calculates the size of a section of the roadway to be managed by the section manager in the area of interest based, at least in part, on the minimum density of connected vehicles and the optimum number of connected vehicles; and activates the hierarchical traffic management system in accordance with the calculated size of the section.

Abstract: Systems and methods are provided for generating a real-time lane-level traffic map based on outbound sensor information. In particular, some embodiments generate lane-level traffic maps using radar sensor information. The populated real-time lane-level traffic maps are shared to other vehicles and may be used by autonomous vehicle systems to maneuver the vehicle.

Abstract: System, methods, and other embodiments described herein relate to improving the protection of a first vehicle using a second vehicle. In one embodiment, a method includes determining a predicted distance to at least one object using an image acquired by a camera of a vehicle, inferring a contextual feature about the image, and in response to determining the contextual feature is associated with a correction factor, correcting the predicted distance using the distance correction factor.

Abstract: Embodiments of systems and methods for adapted vehicle geometry include a vehicle and one or more processors. The vehicle includes a camera operable to generate an image of an environment surrounding the vehicle. The environment includes a parking space and an object removably attached to the vehicle. The one or more processors operable to identify the object as attached to the vehicle, generate, using a pre-trained depth algorithm, a depth map based on the image, generate a boundary of the parking space and a boundary of the vehicle combined with the object based on the depth map, determine whether a distance between the boundary of the parking space and the boundary of the vehicle combined with the object is less than a threshold value, and output an alert in response to determining that the distance is less than the threshold value.

Abstract: Embodiments of systems and methods for vehicle environment detection include a vehicle and one or more processors. The vehicle includes a camera operable to generate an image of an environment surrounding the vehicle. The environment includes one or more parking spaces and an object removably attached to the vehicle. The one or more processors are operable to identify the object, generate, using a pre-trained depth algorithm, a depth map based on the image, generate a boundary of the parking spaces based on the depth map excluding the object, determine whether a distance between the boundary of the parking spaces and the vehicle is less than a threshold value, and output an alert in response to determining that the distance is less than the threshold value.

Abstract: A vehicle system of a vehicle may include comprising a controller programmed to obtain rotational speeds of a plurality of wheels of the vehicle at a plurality of time steps, determine a difference between speeds of one or more front wheels of the vehicle and speeds of one or more rear wheels of the vehicle at the plurality of time steps to generate wheel speed differential data, perform a wavelet transform of the wheel speed differential data to generate a continuous wavelet transform spectrum, identify one or more hot spots in the continuous wavelet transform spectrum comprising a plurality of data points having an amplitude within a predetermined frequency range greater than a predetermined detection threshold, and determine locations of one or more speed bumps based on the identified one or more hot spots.

Abstract: Systems and methods are provided for the reduction or elimination of redundant, uninteresting, and/or inefficient communications to remote devices (e.g. cloud servers) from vehicles collecting observation data. In-vehicle examples of the systems and methods are provided, wherein the associated methods for reducing or eliminating such redundant, uninteresting, and/or inefficient communications are performed on a vehicle. Cloud-based examples of the systems and methods are provided, wherein the associated methods for reducing or eliminating such redundant, uninteresting, and/or inefficient communications are performed on a remote device (e.g. a cloud server).

Abstract: Systems and methods are provided for prioritizing downlink vehicle communication. Such systems and methods leverage transit-impacting event category determinations, and transit-impacting event category-specific parameters to quickly (and efficiently) provide tailored downlink vehicle communication priority orders to requesting transit-related services.

Abstract: Systems and methods are provided for multi-object tracking, for example by vehicles, with data source prioritization. Some embodiments of the present disclosure are directed to multi-vehicle, multi-object tracking and prioritization based on vehicle or sensor capabilities or accuracy levels.

Abstract: Systems and methods described herein relate to configuring a hierarchical traffic management system. One embodiment receives, at a cloud server, a request from an application, the request including requirements and implicating configuration of a hierarchical traffic management system; determines, based on information received from one or more connected vehicles in an area of interest pertaining to the request, a minimum density of connected vehicles in the area of interest to meet the requirements; calculates an optimum number of connected vehicles to assign to a section manager in the hierarchical traffic management system; calculates the size of a section of the roadway to be managed by the section manager in the area of interest based, at least in part, on the minimum density of connected vehicles and the optimum number of connected vehicles; and activates the hierarchical traffic management system in accordance with the calculated size of the section.

Abstract: Systems and methods are provided for generating a real-time lane-level traffic map based on outbound sensor information. In particular, some embodiments generate lane-level traffic maps using radar sensor information. The populated real-time lane-level traffic maps are shared to other vehicles and may be used by autonomous vehicle systems to maneuver the vehicle.