Disclosed is a configuration to control automatic return of an aerial vehicle. The configuration stores a return location in a storage device of the aerial vehicle. The return location may correspond to a location where the aerial vehicle is to return. One or more sensors of the aerial vehicle are monitored during flight for detection of a predefined condition. When a predetermined condition is met a return path program may be loaded for execution to provide a return flight path for the aerial vehicle to automatically navigate to the return location.

Methods, systems and apparatus, including computer programs encoded on computer storage media for unmanned aerial vehicle beyond visual line of sight (BVLOS) flight operations. In an embodiment, a flight planning system of an unmanned aerial vehicle (UAV) can identify handoff zones along a UAV flight corridor for transferring control of the UAV between ground control stations. The start of the handoff zones can be determined prior to a flight or while the UAV is in flight. For handoff zones determined prior to flight, the flight planning system can identify suitable locations to place a ground control station (GCS). The handoff zone can be based on a threshold visual line of sight range between a controlling GCS and the UAV. For determining handoff zones while in flight, the UAV can monitor RF signals from each GCS participating in the handoff to determine the start of a handoff period.

A piloting device arranged to be integrated in a pre-existing aircraft that includes original systems comprising both a flight control system and an autopilot system is distinct from and autonomous relative to the original systems and includes a positioning unit and a control unit. The positioning unit is arranged to produce positioning data for the pre-existing aircraft. The control unit is arranged to perform a geofencing function from the positioning data produced by the positioning unit and to produce an alternative piloting setpoint for the pre-existing aircraft. The alternative piloting setpoint is adapted to supplement both a manual piloting setpoint produced by a pilot of the pre-existing aircraft via the flight control system and also an autopilot setpoint produced by the autopilot system.

The present invention relates to the field of unmanned aerial vehicle safety protection technologies, and in particular, to an unmanned aerial vehicle safety protection method and apparatus and an unmanned aerial vehicle. The method includes: obtaining ultrasonic information and a flight status of an unmanned aerial vehicle, where the flight status includes a normal flight state and a descending state; and performing safety protection on the unmanned aerial vehicle according to the ultrasonic information and the flight status. The implementation can reduce an occurrence probability that an unmanned aerial vehicle crashes at a high altitude when ultrasound encounters abnormalities to get out of control at the high altitude and fail to descend, rise, move to the left or move to the right and land without slowing down to violently hit the ground, so that the safety of the unmanned aerial vehicle is enhanced, and user experience is improved.

The systems and methods described herein relate to fully or partially autonomous or remotely operated aerial pollination vehicles that use computer vision and artificial intelligence to automatically detect plants, orient the vehicle to a pollen dispensing position above each plant, and pollinate the individual plants.

A method, preferably including: sampling inputs, determining aircraft conditions, and/or acting based on the aircraft conditions. A method, preferably including: sampling inputs, determining input reliability, determining guidance, and/or controlling aircraft operation. A method, preferably including: operating the vehicle, planning for contingencies, detecting undesired flight conditions, and/or reacting to undesired flight conditions. A system, preferably an aircraft such as a rotorcraft, configured to implement the method.

Described herein are systems for roof scan using an unmanned aerial vehicle. For example, some methods include capturing, using an unmanned aerial vehicle, an overview image of a roof of a building from above the roof; presenting a suggested bounding polygon overlaid on the overview image to a user; determining a bounding polygon based on the suggested bounding polygon and user edits; based on the bounding polygon, determining a flight path including a sequence of poses of the unmanned aerial vehicle with respective fields of view at a fixed height that collectively cover the bounding polygon; fly the unmanned aerial vehicle to a sequence of scan poses with horizontal positions matching respective poses of the flight path and vertical positions determined to maintain a consistent distance above the roof; and scanning the roof from the sequence of scan poses to generate a three-dimensional map of the roof.

A system may include a user interface and a processor. The processor may be configured to (a) pre-arm multiple actions according to a conditional timeline and any associated trigger events, and (b) output commands to cause the multiple actions to be completed at times consistent with the conditional timeline and any associated trigger events.

Methods and systems for unmanned aerial vehicles are provided. One method includes receiving, by a control system, sensor data from a mobile ground-based platform and sensor data from a ground-based radar surveillance system, the control system configured to communicate with a first UAV and a second UAV; detecting, by the control system, an object likely to impede the second UAV flight within a flight path, the object detected based on the sensor data received from the mobile ground-based platform, the ground-based radar surveillance system or both the ground-based radar surveillance system and the mobile ground-based platform; generating, by the control system, an indicator indicating an object in the flight path; and transmitting, by the control system, the indicator to the first UAV.

A method includes identifying a first image. The method also includes determining a distribution based at least partially upon an intensity of each pixel in the first image. The method also includes determining that the distribution is bimodal. The method also includes dividing the first image to produce a second image in response to determining that the distribution is bimodal. The second image includes a plurality of first pixels and a plurality of second pixels. The method also includes determining that a horizon is defined between the plurality of first pixels and the plurality of second pixels.