Camera based auto drive auto charge
A vehicle control system for moving a vehicle to a target location is disclosed. According to examples of the disclosure, a camera captures one or more images of a known object corresponding to the target location. An on-board computer having stored thereon information about the known object can process the one or more images to determine vehicle location with respect to the known object. The system can use the vehicle's determined location and a feedback controller to move the vehicle to the target location.
1. A method of moving a vehicle to a target location, the method comprising:
capturing, with a camera of the vehicle, one or more images of an object having a plurality of visual features;
performing, by a processor of the vehicle, image processing on the one or more images to identify one or more visual indicators associated with the object;
determining, by the processor, a distance error, heading error, and lateral error using the one or more visual indicators;
providing, by the processor, the distance error, heading error, and lateral error to a vehicle control system of the vehicle; and
automatically moving, by the vehicle control system, the vehicle to reduce one or more of the distance error, heading error, and lateral error if at least one of the distance error, heading error, and lateral error is outside of a predefined error threshold.
2. The method of claim 1 , wherein the object comprises a cylindrical portion.
3. The method of claim 2 , wherein performing image processing on the one or more images further comprises identifying visual indicators comprising a left edge, center edge, and right edge of the cylindrical portion.
4. The method of claim 3 , wherein identifying a left edge, center edge, and right edge of the cylindrical portion further comprises determining where the left edge and the right edge of the cylindrical portion fall within each of the one or more images.
5. The method of claim 4 , wherein identifying a left edge, center edge, and right edge of the cylindrical portion further comprises determining where the center edge of the cylindrical portion is located within each of the one or more images.
6. The method of claim 5 , further comprising determining a distance at which the vehicle located with respect to the object by mapping an amount by which a size of the cylindrical portion in one of the images differs from a calibration size.
7. The method of claim 4 , wherein performing image processing on the one or more images further comprises detecting a relative location of the center edge within one of the images to determine a vehicle heading angle.
8. The method of claim 4 , wherein performing image processing on the one or more images further comprises comparing a position of the center edge in at least one of the images to a calibration position of the center edge.
9. The method of claim 8 , further comprises determining a heading angle of the vehicle with respect to the object by mapping an amount by which the position of the center edge differs from the calibration position to an absolute heading angle.
10. The method of claim 4 , further comprises detecting a relative sizes of each half of the cylindrical portion of the object.
11. The method of claim 10 , further comprises determining a lateral angle of the vehicle from a ration of the relative sizes of the each half of the cylindrical portion of the object.
12. The method of claim 10 , further comprises determining a lateral angle of the vehicle by mapping the positions of the left edge, right edge, and center edge to an absolute lateral angle.
13. The method of claim 12 , further comprises capturing the absolute lateral angle when the vehicle is in the target location.
14. A vehicle position calibration method comprising:
positioning a vehicle in a desired location by a vehicle control system of the vehicle;
capturing an image of an object using a camera of the vehicle;
performing imaging processing on the captured image using a processor of the vehicle;
locating by the processor, a left edge, a center edge, and a right edge of a portion of the object;
storing in a memory of the vehicle, locations of the left edge, center edge, and right edge; and
calculating one or more of a baseline distance, heading angle, and lateral angle using the stored locations of the left edge, center edge, and right edge.
15. The vehicle position calibration method, wherein performing imaging processing on the captured image comprises calculating a vertical projection.
16. The vehicle position calibration method of claim 14 , wherein the portion of the object is cylindrical.