Abstract: A system for delivering items or packages to an unattended vehicle after receiving an order for delivery of an item or package to a vehicle is disclosed. The system determines identifying information for the vehicle, where the identifying information includes a wireless identifier of the vehicle. The system determines a delivery location of the vehicle. The system transmits a request to dispatch a delivery vehicle to deliver a package to the vehicle, wherein the request comprises the identifying information and the delivery location.

Abstract: Systems and methods are disclosed for providing portable containers for users of vehicle services. In an embodiment, a method includes associating a portable container with a user. The method also includes providing a plurality of storage areas disposed about a geographic area. The plurality of storage areas are configured to temporarily store the portable container. The method also includes receiving a request to pick up the portable container from one of the plurality of storage areas. In addition, the method includes delivering, by way of a vehicle service, the portable container to a user location, a specified location, a different storage area of the plurality of storage areas, or a carrier vehicle.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine a vehicle sensor object label, and a vehicle sensor confidence level for the vehicle sensor object label, by processing a vehicle sensor image with a neural network, determine a stationary sensor object label, and a stationary sensor confidence level for the stationary sensor object label, by processing a stationary sensor image with the neural network, and if the stationary sensor confidence level is greater than the vehicle sensor confidence level, operate a vehicle by determining a vehicle path based on the stationary sensor object label.

Abstract: A plurality of sets of sample data points from a vehicle sensor are determined, each set including a predetermined number of consecutive sample data points. Respective differences between pairs of consecutive sample data points in each set are determined. The differences are stored in respective subspaces of one of a plurality of memory spaces of the memory, each memory space in the plurality of memory spaces storing differences of one and only one of the plurality of sets of sample data points. The collected data are restored based on the stored differences in the plurality of memory spaces. A vehicle component is actuated based on the restored data.

Abstract: The present invention extends to methods, systems, and computer program products for delivering items to unattended vehicles. In general, aspects of the invention facilitate controlled access to one or more portions of a vehicle for item deliver. A vehicle is configured with partitions. The partitions can be deployed to close off portions of the vehicle from an area used to accept a delivered item. Partitions may be automatically deployed when a delivery arrives (from a delivery person or robot) to section off a compartment of the vehicle to limit access to the sectioned compartment. Partitions can be re-configured to prevent external access to the sectioned off compartment after a delivery is completed.

Abstract: A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine a vehicle sensor object label, and a vehicle sensor confidence level for the vehicle sensor object label, by processing a vehicle sensor image with a neural network, determine a stationary sensor object label, and a stationary sensor confidence level for the stationary sensor object label, by processing a stationary sensor image with the neural network, and if the stationary sensor confidence level is greater than the vehicle sensor confidence level, operate a vehicle by determining a vehicle path based on the stationary sensor object label.

Abstract: A method for autonomous vehicle localization. The method may include receiving, by an autonomous vehicle, millimeter-wave signals from at least two 5G transmission points. Bearing measurements may be calculated relative to each of the 5G transmission points based on the signals. A vehicle velocity may be determined by observing characteristics of the signals. Sensory data, including the bearing measurements and the vehicle velocity, may then be fused to localize the autonomous vehicle. A corresponding system and computer program product are also disclosed and claimed herein.

Abstract: A vehicle controller communicates with a cellular communication system to request content. The content is transmitted to one or more road side units with storage (RSS) lying on the vehicles known or inferred trajectory. When the vehicle passes by the RSS some or all of the content is transmitted to the vehicle using a short-range, high-bandwidth communication protocol. The content may be divided into segments and each segment sent to an RSS. The segments are sized according to a capacity of the RSS and the amount of time the vehicle is expected to spend traversing a range of the RSS. Content may be cached in the RSS for use by other vehicles.

Abstract: Systems, methods, and apparatuses are disclosed for providing routing and navigational information to users (e.g., visually handicapped users). Example methods may include determining, by one or more computer processors coupled to at least one memory, a first location of a user device and an orientation of a user device, and generating a first route based on the first location, the first orientation, and a destination location. Further, the method may include determining one or more obstacles on the first route using data corresponding to visual information and one or more artificial intelligence techniques; and generating a second route based on the one or more obstacles detected on the first route.

Abstract: Example delivery systems and methods are described. In one implementation, a method identifies multiple items for delivery to a vehicle and determines whether any of the items are temperature-sensitive. If any of the items are temperature-sensitive, the method determines whether the vehicle has a variable-temperature compartment to receive the temperature-sensitive items. If the vehicle has a variable-temperature compartment, the vehicle is notified of an estimated delivery time for the temperature-sensitive items.

Abstract: Systems, methods, and apparatuses are disclosed for providing routing and navigational information to users (e.g., visually handicapped users). Example methods may include determining, by one or more computer processors coupled to at least one memory, a first location of a user device and an orientation of a user device, and generating a first route based on the first location, the first orientation, and a destination location. Further, the method may include determining one or more obstacles on the first route using data corresponding to visual information and one or more artificial intelligence techniques; and generating a second route based on the one or more obstacles detected on the first route.

Abstract: Systems and methods are disclosed for providing portable containers for users of vehicle services. In an embodiment, a method includes associating a portable container with a user. The method also includes providing a plurality of storage areas disposed about a geographic area. The plurality of storage areas are configured to temporarily store the portable container. The method also includes receiving a request to pick up the portable container from one of the plurality of storage areas. In addition, the method includes delivering, by way of a vehicle service, the portable container to a user location, a specified location, a different storage area of the plurality of storage areas, or a carrier vehicle.

Abstract: The present invention extends to methods, systems, and computer program products for delivering items to unattended vehicles. In general, aspects of the invention facilitate controlled access to one or more portions of a vehicle for item deliver. A vehicle is configured with partitions. The partitions can be deployed to close off portions of the vehicle from an area used to accept a delivered item. Partitions may be automatically deployed when a delivery arrives (from a delivery person or robot) to section off a compartment of the vehicle to limit access to the sectioned compartment. Partitions can be re-configured to prevent external access to the sectioned off compartment after a delivery is completed.

Abstract: A method for autonomous vehicle localization. The method may include receiving, by an autonomous vehicle, millimeter-wave signals from at least two 5G transmission points. Bearing measurements may be calculated relative to each of the 5G transmission points based on the signals. A vehicle velocity may be determined by observing characteristics of the signals. Sensory data, including the bearing measurements and the vehicle velocity, may then be fused to localize the autonomous vehicle. A corresponding system and computer program product are also disclosed and claimed herein.

Abstract: A system for delivering items or packages to an unattended vehicle after receiving an order for delivery of an item or package to a vehicle is disclosed. The system determines identifying information for the vehicle, where the identifying information includes a wireless identifier of the vehicle. The system determines a delivery location of the vehicle. The system transmits a request to dispatch a delivery vehicle to deliver a package to the vehicle, wherein the request comprises the identifying information and the delivery location.

Abstract: A vehicle controller communicates with a cellular communication system to request content. The content is transmitted to one or more road side units with storage (RSS) lying on the vehicles known or inferred trajectory. When the vehicle passes by the RSS some or all of the content is transmitted to the vehicle using a short-range, high-bandwidth communication protocol. The content may be divided into segments and each segment sent to an RSS. The segments are sized according to a capacity of the RSS and the amount of time the vehicle is expected to spend traversing a range of the RSS. Content may be cached in the RSS for use by other vehicles.

Abstract: Methods and systems for Beyond-the-Horizon Threat Indication (BHTI) for vehicles are described. A system and a method may involve receiving motion information of a first vehicle. The system and the method may also involve receiving vicinity data corresponding to a vicinity of the first vehicle. The system and the method may also involve determining whether the first vehicle is subject to a potential hazard within the vicinity based on the motion information and the vicinity data. The system and the method may further involves alerting the first vehicle about the potential hazard in response to the determining of the potential hazard.