Autonomous tracking based on radius
Disclosed is a configuration of an autonomous vehicle for autonomously following a moving subject based on a radius of a virtual sphere surrounding the autonomous vehicle. The autonomous vehicle may be an unmanned ground vehicle or an unmanned aerial vehicle, which autonomously follows the subject (e.g., a device, a live entity, or any object) based on the virtual sphere. The radius of the virtual sphere may be dynamically configured according to a velocity of the autonomous vehicle or configurations of a camera coupled to the autonomous vehicle. Accordingly, the autonomous vehicle can follow the subject along a smooth trajectory, and capture images of abrupt movements of the subject in a cinematically pleasing manner.
1. A vehicle comprising:
a camera;
a radius generator configured to:
dynamically generate a virtual sphere that surrounds the vehicle, and
dynamically determine a radius based on velocity data and camera configuration data;
a vehicle controller interface configured to move the vehicle towards a target position; and
a target position generator that determines the target position of the vehicle based on the radius determined by the radius generator.
2. The vehicle of claim 1 , wherein the vehicle is located on a center of the virtual sphere that surrounds the vehicle.
3. The vehicle of claim 1 , further comprising:
a radius tracking controller that receives data from an input interface module.
4. The vehicle of claim 3 , wherein the radius tracking controller determines an updated target position of the vehicle and an updated configuration of the camera.
5. The vehicle of claim 1 , wherein the vehicle controller interface is further configured to:
compare a first position of the vehicle, a second position of the vehicle, and the virtual sphere; and
determine the target position of the vehicle based on the comparison of the first position, the second position, and the virtual sphere.
6. The vehicle of claim 5 , wherein the first position of the vehicle is a current position of the vehicle and the second position of the vehicle is a previous position of the vehicle.
7. A method comprising:
generating a virtual sphere around a vehicle;
determining, using a radius generator, a radius of the virtual sphere based upon velocity data of the vehicle and camera configuration data of a camera carried on the vehicle;
determining, using a target position generator, a target position of the vehicle based on the radius determined by the radius generator; and
controlling the vehicle via a vehicle controller interface that causes the vehicle to move towards the target position.
8. The method of claim 7 , further comprising:
locating the vehicle on a center of the virtual sphere.
9. The method of claim 7 , further comprising:
receiving data from an interface module that communicates with a radius tracking controller.
10. The method of claim 9 , wherein the radius tracking controller determines an updated target position of the vehicle based on an updated configuration from the camera.
11. The method of claim 7 , further comprising:
determining, using the vehicle controller, a pitch and a heading of the camera to face an anticipated position of a subject of an image based on the target position.
12. The method of claim 11 , further comprising:
determining the target position of the vehicle based on the virtual sphere;
comparing a first position of the vehicle, a second position of the vehicle, and the virtual sphere; and
determining the target position of the vehicle based on the comparison of the first position, the second position, and the virtual sphere.
13. The method of claim 12 , wherein the first position of the vehicle is a current position of the vehicle and the second position of the vehicle is a previous position of the vehicle.
14. A method comprising:
generating a target position of a vehicle with a target position generator;
determining a radius of a virtual sphere surrounding the vehicle; and
controlling the vehicle via a vehicle controller interface configured to move the vehicle towards the target position,
wherein the target position generator operates in at least two states that include an out-state and an in-state; and
wherein the out-state is where a distance between a previous target position and a measured portion of the vehicle is greater than the radius of the virtual sphere.
15. The method of claim 14 , further comprising:
dynamically determining, using a radius generator, the radius based on velocity data and camera configuration data detected by a camera of the vehicle.
16. The vehicle of claim 1 , further comprising:
a gimbal control interface module configured to move a gimbal connected to the camera while the vehicle moves towards the target position.
17. The method of claim 7 , further comprising:
determining when the target position is located within the virtual sphere around the vehicle; and
determining an intersection between the target position and a position of the vehicle.
18. The method of claim 14 , wherein the target position generator determines an updated target position to direct the vehicle towards a subject along a smooth trajectory.
19. The method of claim 14 , further comprising:
determining that the distance is less than the radius, and
operating a radius tracking controller in the in-state.
20. The method of claim 19 , wherein in the in-state, the radius tracking controller determines an intersection between the previous target position and a position of a subject.