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 vehicle control system, comprising:
a camera included in a vehicle, the camera configured to capture one or more images of an object, wherein the one or more captured images include a plurality of visual features of the object;
a computing system operatively coupled to the camera, the computing system comprising: a processor configured to determine locations of the plurality of visual features within the one or more images, and determine a location of the camera with respect to the object based on the determined locations of the plurality of visual features within the one or more images; and
a controller configured to move the vehicle to a particular location with respect to the object based on the determined location of the camera with respect to the object;
wherein the processor is further configured to identify a first visual feature in the one or more images, and then select a portion of the one or more images to analyze to determine the locations of the plurality of visual features, wherein the portion of the one or more images is offset from the first visual feature by a predetermined amount.
2. The vehicle control system of claim 1 , wherein: the memory is further configured to store a position and an orientation of the camera with respect to the vehicle; and
the processor is further configured to determine a location of the vehicle with respect to the object based on the position and the orientation of the camera with respect to the vehicle.
3. The vehicle control system of claim 1 , wherein the location of the camera with respect to the object comprises one or more of a distance of the camera from the object, a lateral angle of the camera with respect to the object, and a heading angle of the camera with respect to the object.
4. The vehicle control system of claim 3 , wherein the camera's distance from the object is determined based on a first location of a first visual feature of the plurality of visual features within the one or more images of the object and a second location of a second visual feature of the plurality of visual features within the one or more images of the object.
5. The vehicle control system of claim 4 , wherein determining the camera's distance from the object further comprises:
determining a distance between the first visual feature and the second visual feature in the one or more images;
in accordance with a determination that the distance between the first visual feature and the second visual feature is a first distance, determining that the camera's distance from the object is a second distance; and
in accordance with a determination that the distance between the first visual feature and the second visual feature is a third distance, different from the first distance, determining that the camera's distance from the object is a fourth distance, different from the second distance.
6. The vehicle control system of claim 5 , wherein the first distance is greater than the third distance and the second distance is less than the fourth distance.
7. The vehicle control system of claim 3 , wherein the camera's lateral angle with respect to the object is determined based on a first location of a first visual feature within the one or more images of the object, a second location of a second visual feature within the one or more images of the object, and a third location of a third visual feature within the one or more images of the object.
8. The vehicle control system of claim 7 , wherein determining the camera's lateral angle with respect to the object further comprises:
determining a first distance between the first visual feature and the second visual feature, determining a second distance between the first visual feature and the third visual feature, and determining a ratio of the first distance and the second distance;
in accordance with a determination that the ratio is a first ratio, determining that the camera's lateral angle with respect to the object is a first lateral angle; and
in accordance with a determination that the ratio is a second ratio, different from the first ratio, determining that the camera's lateral angle with respect to the object is a second lateral angle, different from the first lateral angle.
9. The vehicle control system of claim 3 , wherein the camera's heading angle with respect to the object is determined based on a location of a first visual feature within the one or more images of the object.
10. The vehicle control system of claim 9 , wherein determining the camera's heading angle with respect to the object further comprises:
in accordance with a determination that the location of the first visual feature is a first location, determining that the camera's heading angle with respect to the object is a first heading angle; and
in accordance with a determination that the location of the first visual feature is a second location, different from the first location, determining that the camera's heading angle with respect to the object is a second heading angle, different from the first heading angle.
11. The vehicle control system of claim 1 , wherein the computing system further comprises a memory configured to store a baseline image corresponding to the particular location, and wherein the controller is configured to move the vehicle based at least on the baseline image and the one or more images captured by the camera.
12. The vehicle control system of claim 1 , wherein the computing system is further configured to identify the object based on one of the plurality of visual features.
13. The vehicle control system of claim 1 , wherein the plurality of visual features comprises a first edge between a first portion of the object and a second portion of the object, a second edge between two parts of the first portion, and a third edge, different from the first edge, between the first portion and the second portion.
14. The vehicle control system of claim 1 , wherein the object comprises a cylinder having a first part with a first visual characteristic and a second part, different from the first part, with a second visual characteristic, different from the first visual characteristic.
15. The vehicle control system of claim 1 , wherein the locations of the plurality of visual features within the one or more images are absolute locations.
16. The vehicle control system of claim 1 , wherein the particular location with respect to the object is pre-defined.
17. A method of controlling a vehicle, comprising:
capturing, with a camera included in the vehicle, one or more images of an object having a plurality of visual features, wherein the one or more captured images include the plurality of visual features of the object;
determining locations of the plurality of visual features within the one or more images;
determining a location of the camera with respect to the object based on the determined locations of the plurality of visual features within the one or more images;
moving the vehicle to a particular location with respect to the object based on the determined location of the camera with respect to the object; and
identifying a first visual feature in the one or more images, and then selecting a portion of the one or more images to analyze to determine the locations of the plurality of visual features, wherein the portion of the one or more images is offset from the first visual feature by a predetermined amount.
18. The method of claim 17 , further comprising: storing a position and an orientation of the camera with respect to the vehicle; and determining a location of the vehicle with respect to the object based on the position and the orientation of the camera with respect to the vehicle.
19. A non-transitory computer-readable medium including instructions, which when executed by one or more processors, cause the one or more processors to perform a method comprising:
capturing, with a camera included in the vehicle, one or more images of an object having a plurality of visual features, wherein the one or more captured images include the plurality of visual features of the object;
determining locations of the plurality of visual features within the one or more images;
determining a location of the camera with respect to the object based on the determined locations of the plurality of visual features within the one or more images;
moving the vehicle to a particular location with respect to the object based on the determined location of the camera with respect to the object; and
identifying a first visual feature in the one or more images, and then selecting a portion of the one or more images to analyze to determine the locations of the plurality of visual features, wherein the portion of the one or more images is offset from the first visual feature by a predetermined amount.