Automated electric vehicle charging system and method

1. A method for charging an electric vehicle, comprising:

identifying vehicle information corresponding to the electric vehicle based on an electronic image of the electric vehicle,

wherein identifying the vehicle information comprises comparing the electronic image of the electric vehicle with a plurality of vehicle model candidates stored in an electronic database;

calculating a similarity score for each of the vehicle model candidates stored in the electronic database;

selecting a vehicle model candidate having a highest similarity score, wherein the vehicle information is identified using the selected vehicle model candidate;

retrieving from the electronic database a location of a charging port on the electric vehicle based on the selected vehicle model candidate; and

robotically moving a charging connector according to the retrieved location to engage the charging port of the electric vehicle to charge a battery.

2. The method of claim 1 , further comprising:

acquiring a plurality of two-dimensional (2D) images of a field of view;

determining whether the electric vehicle has entered the field of view based on an analysis of the plurality of images;

extracting a plurality of features of the electric vehicle from each image; and

tracking a position and pose of the electric vehicle while the electric vehicle is in motion using the extracted features.

3. The method of claim 2 , further comprising:

constructing a three-dimensional (3D) model of the electric vehicle using the plurality of 2D images, wherein

identifying the vehicle information is based on a comparison of features in the 3D model of the electric vehicle with corresponding features in a plurality of 3D vehicle model candidates stored in the database.

4. The method of claim 2 , further comprising:

rotating each of a plurality of three-dimensional (3D) vehicle model candidates stored in the database to match a pose of the electric vehicle in each of the plurality of 2D images; and

converting each rotated 3D vehicle model candidate to a 2D vehicle model candidate,

wherein identifying the vehicle information is based on a comparison of features in each of the plurality of 2D images with corresponding features in each 2D vehicle model candidate.

5. The method of claim 2 , wherein the position and pose of the electric vehicle are different in each of the plurality of 2D images, and the position and pose of the electric vehicle in each image are used to identify the vehicle information.

6. The method of claim 2 , further comprising:

acquiring an additional plurality of 2D images, wherein the additional plurality of 2D images have a viewpoint different from the plurality of 2D images of the field of view, and include the charging connector and the charging port;

verifying the location of the charging port on the electric vehicle using the additional plurality of 2D images; and

guiding the charging connector towards the charging port using the additional plurality of 2D images.

7. The method of claim 2 , further comprising:

using background-subtraction to determine whether the electric vehicle has entered the field of view.

8. The method of claim 1 , wherein the identified vehicle information includes a make of the electric vehicle, a model of the electric vehicle, and a year of the electric vehicle, and

the location of the charging port on the electric vehicle is identified using a vehicle model candidate stored in the database having a same make, model and year as the electric vehicle.

9. The method of claim 1 , further comprising:

robotically disengaging the charging connector from the charging port on the electric vehicle.

10. The method of claim 1 , further comprising:

robotically removing a door covering the charging port on the electric vehicle prior to engaging the charging connector into the charging port; and

robotically covering the charging port with the door subsequent to disengaging the charging connector from the charging port.

11. The method of claim 1 , further comprising:

receiving customer billing information using a radio-frequency identification (RFID) tag mounted on the electric vehicle; and

transmitting the customer billing information to a remote billing system.

12. The method of claim 1 , further comprising:

downloading an update to the electronic database from a remote system upon determining that the update is available.

13. A system for charging an electric vehicle, comprising;

a first camera, configured to acquire an electronic image of the electric vehicle;

an electronic database;

a processor, configured to:

identify vehicle information corresponding to the electric vehicle based on the electronic image of the electric vehicle, wherein identifying the vehicle information comprises comparing the electronic image of the electric vehicle with a plurality of vehicle model candidates stored in the electronic database;

calculate a similarity score for each of the vehicle model candidates stored in the electronic database;

select a vehicle model candidate having a highest similarity score, wherein the vehicle information is identified using the selected vehicle model candidate; and

retrieve from the electronic database a location of a charging port on the electric vehicle based on the selected vehicle model candidate; and

a robotic arm, configured to move a charging connector according to the retrieved location to engage the charging port of the electric vehicle to charge a battery.

14. The system of claim 13 , further comprising:

an actuator disposed on the robotic arm, configured to open a door covering the charging port of the electric vehicle prior to engaging the charging connector into the charging port, and close the door covering the charging port upon disengaging the charging connector from the charging port.

15. The system of claim 13 , wherein:

the first camera is further configured to acquire a plurality of images of a field of view; and

the processor is further configured to determine whether the electric vehicle has entered the field of view based on an analysis of the plurality of images, extract a plurality of features of the electric vehicle from each image, and track a position and pose of the electric vehicle while the electric vehicle is in motion using the extracted features.

16. The system of claim 15 , further comprising:

a second camera disposed on the robotic arm, configured to acquire an additional plurality of images,

wherein the additional plurality of images have a viewpoint different from the plurality of images of the field of view and include the charging connector and the charging port, and are used to verify the location of the charging port on the electric vehicle and guide the charging connector towards the charging port.

17. The system of claim 13 , further comprising:

a communication link configured to download an update to the electronic database from a remote system upon determining that the update is available.