Abstract: Load volume predication for slung loads of aerial vehicles are disclosed. A system can identify parameters of a load. The system can determine a volume occupied by a superposition of locations of the cone. The system can receive from sensors or models, characteristics of an environment associated with the aerial vehicle or the load. The system can detect an obstacle in the environment. The system can take a navigational action in response to detecting the obstacle.

Abstract: Offline task-based feature processing for aerial vehicles is provided. A system can extract features from a world model generated using sensor information captured by sensors mounted on an aerial vehicle. The system generates a label for each of the features and identifies identify processing levels based on the features. The system selects a processing level for each feature of a subset of features based on a task performed by the aerial vehicle and the label associated with the feature. The system generates one or more processed features by applying the processing level to a respective feature of the subset of the plurality of features. The system presents the one or more processed features on a display device of the aerial vehicle.

Abstract: This disclosure relates to apparatuses, systems, and methods for controlling an aircraft. A computing system may identify a first command signal received via a flight control at a time point to control navigation of the aircraft through an environment. The computing system may attenuate the first command signal using a fade function over a time window relative to the time point to generate a second command signal. The computing system may input the second command signal to a model to generate predicted paths for the aircraft through the environment over the time window. The computing system may determine that at least one predicted path intersects with an obstacle in the environment during the time window. The computing system may generate a location to which to navigate the aircraft to avoid the obstacle. The computing system may perform an action to direct the aircraft to the location.

Abstract: A wind estimation system for an aircraft includes a first sensor configured to sense a first position associated with an aircraft control component in a wind condition, a second sensor configured to sense a first configuration associated with a rotor system of the aircraft in the wind condition, and at least one controller in communication with at least one of the first sensor or the second sensor. The at least one controller is configured to determine a tip-path-plane angle of the aircraft based on the first position and the first configuration, and determine at least one of a current wind speed or current wind direction based on the tip-path-plane angle.

Abstract: A technique relates to autonomous obstacle avoidance. A vehicle is controlled on a route to a destination, the route being a three-dimensional route. An obstruction is determined on the global route. A local route including alternate points to avoid the obstruction is autonomously determined. The local route is autonomously converged back to the global route in response to avoiding the obstruction.

Abstract: This disclosure relates to apparatuses, systems, and methods for handling faults on vehicles. One or more processors in a vehicle may receive, from a control unit in response to a detection of a fault in the vehicle, an indication of a degradation in a performance constraint of the vehicle. The processors may determine, responsive to the degradation in the performance constraint, that the vehicle is unable to execute a set of commands to control a movement of the vehicle along a trajectory. The processors may generate, in accordance with the degradation in the performance constraint, a modified set of commands that the vehicle is able to execute to control the movement of the vehicle along at least a portion of one or more trajectories. The processors may provide the modified set of commands to the control unit of the vehicle to control the movement of the vehicle.

Abstract: A flight control system for a rotary-wing aircraft includes a shape sensor and a controller. The shape sensor is configured to measure a shape of a rotor blade during movement of the rotor blade. The controller is communicably coupled to the shape sensor and is configured to (i) receive, from the shape sensor, a first signal indicative of a first blade shape; (ii) receive a blade characteristic regarding the rotor blade; and (iii) determine at least one of a moment or force associated with the rotor blade based on the first signal and the blade characteristic.

Abstract: Systems and methods for controlling a coaxial rotary-wing aircraft including a co-axial main rotor assembly and a pusher-propeller. One system includes an electronic controller configured to receive a reference velocity of the aircraft and receive a reference flight path angle of the aircraft. The electronic controller is also configured to simultaneously control the co-axial main rotor assembly and the pusher-propeller based on the reference velocity of the aircraft and the reference flight path angle of the aircraft, by simultaneously generating a commanded thrust of the pusher-propeller and a commanded thrust of the co-axial main rotor assembly using a multiple input, multiple output algorithm applying dynamic inversion.

Abstract: Offline task-based feature processing for aerial vehicles is provided. A system can extract features from a world model generated using sensor information captured by sensors mounted on an aerial vehicle. The system generates a label for each of the features and identifies identify processing levels based on the features. The system selects a processing level for each feature of a subset of features based on a task performed by the aerial vehicle and the label associated with the feature. The system generates one or more processed features by applying the processing level to a respective feature of the subset of the plurality of features. The system presents the one or more processed features on a display device of the aerial vehicle.

Abstract: A technique relates to route planning. Points associated with a start location and a destination location are received. It is determined whether the points comprise one or more hard points, one or more soft points, or both. At least one obstruction to avoid is determined. A route is autonomously generated comprising the points and segments associated with the points, the segments comprising rhumb lines, great-circle arcs, or both. Responsive to the points comprising the one or more soft points, the at least one obstruction is avoided by permitting a distance associated with the one or more soft points to be reached and adding at least one free waypoint. Responsive to the points comprising the one or more hard points, the at least one obstruction is avoided by requiring the one or more hard points to be reached and adding the at least one free waypoint.

Abstract: A technique relates to autonomous obstacle avoidance. A vehicle is controlled on a route to a destination, the route being a three-dimensional route. An obstruction is determined on the global route. A local route including alternate points to avoid the obstruction is autonomously determined. The local route is autonomously converged back to the global route in response to avoiding the obstruction.