An aircraft includes a plurality of stereo cameras. The aircraft further includes one or more processors and one or more memory devices. The one or more memory devices store instructions that are executable by the one or more processors to perform operations including generating a three-dimensional depth map based on a plurality of outputs of the plurality of stereo cameras. The instructions include detecting one or more objects represented in the plurality of outputs. The instructions further include transmitting one or more taxi control signals based on the three-dimensional depth map and the one or more objects.

An aircraft includes a plurality of stereo cameras. The aircraft further includes one or more processors and one or more memory devices. The one or more memory devices store instructions that are executable by the one or more processors to perform operations including generating a three-dimensional depth map based on a plurality of outputs of the plurality of stereo cameras. The instructions include detecting one or more objects represented in the plurality of outputs. The instructions further include transmitting one or more taxi control signals based on the three-dimensional depth map and the one or more objects.

In some embodiments, a computer-implemented method of controlling autonomous movement of a mobile object in an aircraft operating area is provided. An autonomous control computing system receives an image from a digital camera positioned to view at least a portion of the mobile object. The autonomous control computing system provides the image to a machine learning model to detect within the image one or more self objects and one or more intruder objects. The one or more self objects are affixed to the mobile object. The autonomous control computing system predicts future locations for the self objects based on a navigation path for the mobile object. In response to detecting an overlap between the future locations for the self objects and the intruder objects, the autonomous control computing system alters the navigation path to prevent a collision between the self objects and the intruder objects.

The method can include performing inference using the system; and can optionally include training the system components. The method functions to automatically interpret flight commands from a stream of air traffic control (ATC) radio communications. The method can additionally or alternatively function to train and/or update a natural language processing system based on ATC communications. Additionally, the method can include or be used in conjunction with collision avoidance and/or directed perception for traffic detection associated therewith.

A method includes obtaining medial axes of buffers around guidance lines of taxiways of an airport. The buffers define a taxiway polygon representation of the taxiways. The method includes identifying a plurality of intersection points of the medial axes. The method includes segmenting the taxiway polygon into taxiway segments with segment lines based on the plurality of intersection points, where a particular segment line associated with an intersection point is offset a distance from the intersection point and is at a particular angle relative to a medial axis extending from the intersection point. The method further includes generating a map of the airport that includes the taxiway segments.

A system may include a display and a processor communicatively coupled to the display. The processor may be configured to: output, to the display, a view of an airport moving map (AMM); receive aircraft state data and airport surface data; at least based on the current position of the aircraft and at least one factor, obtain commonly used taxi route data from a data structure, the data structure including taxi route data, the taxi route data including information of commonly used taxi routes for the airport, wherein the commonly used taxi route data includes information of a commonly used taxi route for the aircraft on the airport surface; based at least on the commonly used taxi route data, the aircraft state data, and the airport surface data, generate taxi routing guidance content; and output, to the display, the taxi routing guidance content.

A system may include a display and a processor communicatively coupled to the display. The processor may be configured to: output, to the display, a view of an airport moving map (AMM); receive aircraft state data and airport surface data; at least based on the current position of the aircraft and at least one factor, obtain commonly used taxi route data from a data structure, the data structure including taxi route data, the taxi route data including information of commonly used taxi routes for the airport, wherein the commonly used taxi route data includes information of a commonly used taxi route for the aircraft on the airport surface; based at least on the commonly used taxi route data, the aircraft state data, and the airport surface data, generate taxi routing guidance content; and output, to the display, the taxi routing guidance content.

A computing device is provided comprising a processor and a memory storing instructions executable by the processor. The instructions are executable by the processor to monitor location information for a plurality of aircraft in a geographic region. Geospatial data is received for the geographic region. The geospatial data comprises, for each of one or more physical objects in the geographic region, a virtual representation of the physical object. The instructions are further executable to determine that the location information meets a threshold difference compared to expected location information for a selected virtual representation of a physical object. An indication of an anomaly is output based at least on the determination that the location information meets the threshold difference.

A method for managing taxiing paths of an aircraft includes at least one computer system, the method being implemented by the computer system. The method includes the following steps: editing an initial path; displaying a route of the initial path on a screen using a first route symbolism; obtaining a validation of the initial path; displaying a route of the validated initial path on the screen using a second route symbolism; implementing the validated initial path in a taxiing setpoint of the aircraft. The method further includes an editing process and an independent display process.

A ground obstacle collision-avoidance system includes a plurality of radar sensor modules that each receive at a radar detector radar return signals corresponding to reflections of the emitted signal from a ground obstacle, and transmits radar information associated with the received radar signal reflections reflected from the ground obstacle, wherein each of the plurality of radar sensor modules are uniquely located on a surface of an aircraft that is at risk for collision with a ground obstacle if the aircraft is moving; a gateway unit that receives the radar information transmitted from the radar sensor module and transmits information associated with the received radar information; a processing system configured to determine a distance from the installation aircraft to a detected ground object detected; and a display configured to present a plan view indicating an aircraft icon and a graphical ground obstacle icon that is associated with the detected ground obstacle.