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 method and a system for establishing a route of an unmanned aerial vehicle are provided. The method includes identifying an object from surface scanning data and shaping a space, which facilitates autonomous flight, as a layer, collecting surface image data for a flight path from the shaped layer, and analyzing a change in image resolution according to a distance from the object through the collected surface image data and extracting an altitude value on a flight route.

Provide is an agricultural chemical spraying drone with improved safety. An acceleration sensor and a contact detection sensor are combined to detect contact of a drone with an obstacle. In a case where the contact is detected, a retreat action such as hovering is taken. In addition, a message may be displayed on a control terminal, a warning sound may be generated, and a warning light may be turned on. Further, a structure capable of minimizing finger insertion accidents and minimizing interference with a rotor even in collision is adopted as a propeller guard.

An unmanned aerial vehicle (UAV) includes a sensor configured to detect an indicator of a geo-fencing device; and a flight controller configured to generate one or more signals that cause the UAV to operate in accordance with a set of flight regulations that are generated based on the detected indicator of the geo-fencing device.

Systems and methods for airspace management. One embodiment of an aerial vehicle, includes a first sensor for detecting a lateral field of view of the aerial vehicle and a vehicle computing device. The vehicle computing device may include a memory component and a processor. The memory component may store logic that, when executed by the processor, causes the aerial vehicle to calculate a detection boundary for the aerial vehicle to maintain a well clear requirement, wherein the detection boundary is based on instantaneous trajectory, planned future trajectory, and a capability of the aerial vehicle and utilize the capability of the aerial vehicle and data from the first sensor to maintain the vehicle within detection boundary. In some embodiments the logic may cause the vehicle to provide an instruction to maintain the aerial vehicle within the detection boundary.

A method of training a machine learning, ML, algorithm to control a watercraft is described. The watercraft is a submarine or a submersible submerged in water. The method is implemented, at least in part, by a computer, comprising a processor and a memory, aboard the watercraft. The method comprises: obtaining training data including respective sets of environmental parameters and corresponding actions of a set of communicatively isolated watercraft, including a first watercraft; and training the ML algorithm comprising determining relationships between the respective sets of environmental parameters and the corresponding actions of the watercraft of the set thereof. A method of controlling a watercraft by a trained ML algorithm is also described.

A method of training a machine learning, ML, algorithm to control a watercraft is described. The watercraft is a submarine or a submersible submerged in water. The method is implemented, at least in part, by a computer, comprising a processor and a memory, aboard the watercraft. The method comprises: obtaining training data including respective sets of environmental parameters and corresponding actions of a set of communicatively isolated watercraft, including a first watercraft; and training the ML algorithm comprising determining relationships between the respective sets of environmental parameters and the corresponding actions of the watercraft of the set thereof. A method of controlling a watercraft by a trained ML algorithm is also described.

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.

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.

Disclosed subject matter identifies, characterizes, and mitigates previously unforeseen safety hazards that are likely to be encountered by autonomous conveyancesfinding these hazards, assessing their potential safety impact, modifying the design to mitigate them should they occur, disseminating updated design programming to all units, including those under construction or those already in the field, and including those hazard mitigations of high severity that exceed the maximum capabilities of the controller as manufactured. These hazards can include rare, infrequent and unforeseen hazards by monitoring conveyances already in the field, gathering data from autonomous conveyances, such as those using a design being updated, and data obtained from those using other autonomous designs in the field. By obtaining data from non-autonomous conveyances, as supplied by their drivers and operators, reporting real-time via a smartphone application, categories of rare, infrequent or unforeseen hazards can be integrated into modified designs.