User interaction with an autonomous unmanned aerial vehicle

A method for controlling image capture by an autonomous aerial vehicle, the method comprising:

• receiving, by a computer system, first images of a physical environment captured by a mobile user device;
• processing, by the computer system, the images to detect a physical object in the physical environment and estimate a position of the physical object in the physical environment;
• and
• causing, by the computer system, based on the estimated position of the physical object, the autonomous aerial vehicle to maneuver to capture second images of the physical environment that include the physical object.

A method for controlling an autonomous aerial vehicle, the method comprising:

• receiving, by a computer system, from a user device, a signal indicative of a user selection of a virtual navigation object located in a shared virtual environment that is representative of a physical environment, the shared virtual environment generated in part based on perception inputs from one or more sensors in the physical environment, the shared virtual environment accessible to a plurality of network-connected devices including the user device;
• generating, by the computer system, a planned trajectory through the shared virtual environment relative to the virtual navigation object;
• and
• causing, by the computer system, the autonomous aerial vehicle to maneuver through the physical environment along a path that corresponds with the planned trajectory.

An aerial vehicle comprising:

• a sensor device;
• and
• a computer system communicatively coupled to the sensor device, the computer system configured to:
• receive perception inputs generated by the sensor device while the aerial vehicle is in flight through a physical environment;
• process the perception inputs to detect a physical object that is in the physical environment;
• estimate a position of the detected physical object in the physical environment;
• update a shared virtual environment that is representative of the physical environment to include a virtual representation of the physical object at a virtual location in the shared virtual environment that corresponds to the estimated position of the physical object in the physical environment;
• and
• wherein the shared virtual environment is accessible to a plurality of network-connected devices.