Abstract: In some implementations, a device may receive spatial data corresponding to an interior of a building and objects located in the interior of the building. The device may generate a digital map of the interior of the building based on the spatial data. The device may generate a geographic coordinate map of the interior of the building. The device may receive, from a sensor mounted on an uncrewed aerial vehicle (UAV), sensor data indicating three-dimensional geographic points. The device may compare the sensor data to the geographic coordinate map to localize the UAV on the geographic coordinate map. The device may generate coordinate data indicating geographic coordinates associated with the geographic coordinate map and formatted in a global positioning system coordinate format and a National Marine Electronics Association format. The device may transmit, to a controller of the UAV, at least a subset of the coordinate data.

Abstract: An optical input polarization management device includes a polarization splitter and rotator (PSR) that directs a portion of incoming light having a first polarization through a first optical waveguide (OW). The PSR rotates a portion of the incoming light having a second polarization to the first polarization so as to provide polarization-rotated light. The PSR directs the polarization-rotated light through a second OW. Light within the first and second OW's is input to a first two-by-two optical splitter (2×2OS). A first phase shifter (PS) is interfaced with either the first or second OW. Light is output from the first 2×2OS into a third OW and a fourth OW. Light within the third and fourth OW's is input to a second 2×2OS. A second PS is interfaced with either the third or fourth OW. Light is output from the second 2×2OS into a fifth OW for further processing.

Abstract: An autonomous mobile device includes a processor to establish a Transmission Control Protocol Robot Operating System (TCPROS) connection over a Protocol Data Unit (PDU) session between the AMD and a Multi-Access Edge Computing (MEC) device that hosts an AMD controller in a cellular network, from the AMD the AMD controller. The processor may perform a mission in accordance with the mission plan while the AMD is connected to the AMD controller via the TCPROS connection.

Abstract: A device may include a memory storing instructions and processor configured to execute the instructions to receive information relating to a plurality of vehicles in an area. The device may be further configured to use a trained machine learning model to determine a likelihood of collision by one or more of the plurality of vehicles; identify one or more relevant vehicles of the plurality of vehicles that are in danger of collision based on the determined likelihood of collision; and send an alert indicating the danger of collision to at least one of the identified one or more relevant vehicles.

Abstract: A device may receive images identifying interiors of buildings and movable objects and unmovable objects located in the interiors, and may train a machine learning model with the images to generate a trained machine learning model. The device may receive an image identifying an interior portion of a building and objects located in the interior portion, and may process the image, with the trained machine learning model, to identify a movable object and an unmovable object. The device may disregard the movable object to generate an image in which data identifying the movable object has been disregarded, and may process the image in which the data identifying the movable object has been disregarded, with a visual positioning system, to determine a location of the user device in the interior portion of the building. The device may perform one or more actions based on the location of the user device.

Abstract: In some implementations, a device may receive spatial data corresponding to an interior of a building and objects located in the interior of the building. The device may generate a digital map of the interior of the building based on the spatial data. The device may generate a geographic coordinate map of the interior of the building. The device may receive, from a sensor mounted on an uncrewed aerial vehicle (UAV), sensor data indicating three-dimensional geographic points. The device may compare the sensor data to the geographic coordinate map to localize the UAV on the geographic coordinate map. The device may generate coordinate data indicating geographic coordinates associated with the geographic coordinate map and formatted in a global positioning system coordinate format and a National Marine Electronics Association format. The device may transmit, to a controller of the UAV, at least a subset of the coordinate data.

Abstract: A device may receive, from a vehicle device, a geographical (e.g., GNSS) location of a vehicle, and may utilize the GNSS location as a determined location of the vehicle when the GNSS location satisfies a first threshold. The device may receive, from the vehicle device, an image identifying reference points associated with the vehicle, and may process the image, with a VPS, to calculate a VPS location of the vehicle. The device may utilize the GNSS location of the vehicle as the determined location when the VPS location fails to satisfy a second threshold, and may calculate, when the VPS location of the vehicle satisfies the second threshold, coordinate sets based on groups of coordinate combinations from the GNSS location and the VPS location. The device may process the coordinate sets, with a model, to determine the determined location, and may perform actions based on the determined location.

Abstract: A device may include a memory storing instructions and processor configured to execute the instructions to receive information relating to a plurality of vehicles in an area. The device may be further configured to use a trained machine learning model to determine a likelihood of collision by one or more of the plurality of vehicles; identify one or more relevant vehicles of the plurality of vehicles that are in danger of collision based on the determined likelihood of collision; and send an alert indicating the danger of collision to at least one of the identified one or more relevant vehicles.

Abstract: A device may include a memory storing instructions and processor configured to execute the instructions to receive information relating to a plurality of vehicles in an area. The device may be further configured to use a trained machine learning model to determine a likelihood of collision by one or more of the plurality of vehicles; identify one or more relevant vehicles of the plurality of vehicles that are in danger of collision based on the determined likelihood of collision; and send an alert indicating the danger of collision to at least one of the identified one or more relevant vehicles.

Abstract: A device can be configured to receive flight data associated with an unmanned aerial vehicle (UAV), at least some of the flight data being received from the UAV; store the flight data; receive, from a requesting device, a flight data request, the flight data request including information identifying the UAV or a flight of the UAV; determine response data based on the flight data request and based on an entity associated with the requesting device, the response data including a subset of the flight data, which is available to be accessed by the entity; and perform an action associated with the response data.

Abstract: In some implementations, a device may receive status information for robotic devices. The status information may include locations and navigation plans of the robotic devices. The device may monitor, based on the status information, individual statuses of the robotic devices. The device may receive a mission request associated with performance of an operation. The device may select, based on the individual statuses, a first robotic device to perform the operation. The device may determine, based on a mapping of an environment, potential navigation plans associated with the first robotic device traversing the environment according to the operation. The device may select a navigation plan based on the locations and the navigation plans of the robotic devices. The device may stream navigation instructions associated with the selected navigation plan to the first robotic device to cause the first robotic device to traverse the environment according to the navigation plan.

Abstract: A device may receive images identifying interiors of buildings and movable objects and unmovable objects located in the interiors, and may train a machine learning model with the images to generate a trained machine learning model. The device may receive an image identifying an interior portion of a building and objects located in the interior portion, and may process the image, with the trained machine learning model, to identify a movable object and an unmovable object. The device may disregard the movable object to generate an image in which data identifying the movable object has been disregarded, and may process the image in which the data identifying the movable object has been disregarded, with a visual positioning system, to determine a location of the user device in the interior portion of the building. The device may perform one or more actions based on the location of the user device.

Abstract: A device may receive images identifying interiors of buildings and movable objects and unmovable objects located in the interiors, and may train a machine learning model with the images to generate a trained machine learning model. The device may receive an image identifying an interior portion of a building and objects located in the interior portion, and may process the image, with the trained machine learning model, to identify a movable object and an unmovable object. The device may disregard the movable object to generate an image in which data identifying the movable object has been disregarded, and may process the image in which the data identifying the movable object has been disregarded, with a visual positioning system, to determine a location of the user device in the interior portion of the building. The device may perform one or more actions based on the location of the user device.

Abstract: A device may receive, from a vehicle device, a geographical (e.g., GNSS) location of a vehicle, and may utilize the GNSS location as a determined location of the vehicle when the GNSS location satisfies a first threshold. The device may receive, from the vehicle device, an image identifying reference points associated with the vehicle, and may process the image, with a VPS, to calculate a VPS location of the vehicle. The device may utilize the GNSS location of the vehicle as the determined location when the VPS location fails to satisfy a second threshold, and may calculate, when the VPS location of the vehicle satisfies the second threshold, coordinate sets based on groups of coordinate combinations from the GNSS location and the VPS location. The device may process the coordinate sets, with a model, to determine the determined location, and may perform actions based on the determined location.

Abstract: A device may receive images identifying interiors of buildings and movable objects and unmovable objects located in the interiors, and may train a machine learning model with the images to generate a trained machine learning model. The device may receive an image identifying an interior portion of a building and objects located in the interior portion, and may process the image, with the trained machine learning model, to identify a movable object and an unmovable object. The device may disregard the movable object to generate an image in which data identifying the movable object has been disregarded, and may process the image in which the data identifying the movable object has been disregarded, with a visual positioning system, to determine a location of the user device in the interior portion of the building. The device may perform one or more actions based on the location of the user device.

Abstract: A device may include a memory storing instructions and processor configured to execute the instructions to receive information relating to a plurality of vehicles in an area. The device may be further configured to use a trained machine learning model to determine a likelihood of collision by one or more of the plurality of vehicles; identify one or more relevant vehicles of the plurality of vehicles that are in danger of collision based on the determined likelihood of collision; and send an alert indicating the danger of collision to at least one of the identified one or more relevant vehicles.

Abstract: A device can be configured to receive flight data associated with an unmanned aerial vehicle (UAV), at least some of the flight data being received from the UAV; store the flight data; receive, from a requesting device, a flight data request, the flight data request including information identifying the UAV or a flight of the UAV; determine response data based on the flight data request and based on an entity associated with the requesting device, the response data including a subset of the flight data, which is available to be accessed by the entity; and perform an action associated with the response data.

Abstract: A device can be configured to detect a physical connection with an unmanned aerial vehicle (UAV) flight controller through an interface. The device can identify a UAV identifier associated with the UAV flight controller and determine, based on the UAV identifier, an application programming interface (API) for communicating with the UAV flight controller. Using the API, the device can establish a communications link with the UAV flight controller and perform an action based on the communications link.

Abstract: A device can be configured to receive flight data associated with an unmanned aerial vehicle (UAV), at least some of the flight data being received from the UAV; store the flight data; receive, from a requesting device, a flight data request, the flight data request including information identifying the UAV or a flight of the UAV; determine response data based on the flight data request and based on an entity associated with the requesting device, the response data including a subset of the flight data, which is available to be accessed by the entity; and perform an action associated with the response data.

Abstract: In an example, an apparatus is described that includes a transparent platen, a substrate, an array of light sources, and a sensor. The substrate is positioned on one side of the platen and has substantially uniform reflective properties. The array of light sources is positioned on an opposite side of the platen from the substrate and includes a plurality of light sources that emits light in a visible spectrum and a light source that emits light in an invisible spectrum. The sensor is positioned on the opposite side of the platen from the substrate and detects reflected portions of the light in the visible spectrum and the light in the invisible spectrum.