Method and apparatus for autonomously plugging a charging plug into a charging socket of a vehicle
Technologies and techniques for autonomously plugging a charging plug into a charging socket of a vehicle, wherein the charging plug is installed on a programmable robot arm of a charging station. A camera is used to locate the charging socket using image analysis of acquired images of the charging socket and the surroundings of the charging station are represented as a digital map including a charging socket region in which the charging socket is located. The charging plug is moved into a plug-in position at a distance from the charging socket and the digital map is processed into a modified digital map having a remote charging socket region. A plugging-in operation is then performed based on the modified digital map.
1 . A method for autonomously plugging a charging plug of a programmable robot arm into a charging socket of a vehicle, comprising:
visually identifying the charging socket using image analysis of created images of the charging socket;
processing image data of a surrounding area of the charging station to generate a digital map comprising a charging socket region in which the charging socket is configured;
moving, via the programmable robot arm, the charging plug into a plug-in position, spaced apart from the charging socket;
processing the digital map to generate a modified digital map comprising a removed charging socket region; and
plugging, via the programmable robot arm, the charging plug into the charging socket from the plug-in position, wherein the plug-in process is carried out based on the modified digital map.
2 . The method according to claim 1 , wherein the image analysis is carried out via a neural network pre-trained on the charging socket.
3 . The method according to claim 1 , further comprising:
determining pose data, based on the image analysis, to determine a pose of the charging socket using a Perspective-n-Point (PnP) algorithm; and
moving the charging plug into an intermediate position based on the determined pose data.
4 . The method according to claim 3 , wherein the pose is determined by additionally determining the mean value of the pose data.
5 . The method according to claim 3 , further comprising:
generating a depth image of the charging socket corresponding to the current position of the charging plug when the charging plug is in the intermediate position;
processing the generated depth image with a reference depth image corresponding to a reference position to determine a position deviation between the current position of the charging plug and the reference position; and
moving the charging plug into the plug-in position based on the determined position deviation.
6 . The method according to claim 5 , wherein the reference depth image comprises a reference depth image recorded from a predefined distance and/or position with respect to the charging socket.
7 . The method according to claim 5 , wherein the position deviation is determined using an Iterative Closest Point (ICP) algorithm.
8 . An apparatus for autonomously operating a charging station, comprising:
a programmable robot arm comprising a charging plug, wherein the programmable arm is configured for autonomous operation;
a camera unit, operatively coupled to the programmable robot arm; and
a processing apparatus, operatively coupled to the camera unit, wherein the processing apparatus is configured to
visually identify a charging socket using image analysis of created images via the camera unit;
process image data of a surrounding area of the charging station to generate a digital map comprising a charging socket region in which the charging socket is configured;
move, via the programmable robot arm, the charging plug into a plug-in position, spaced apart from the charging socket;
process the digital map to generate a modified digital map comprising a removed charging socket region; and
plug, via the programmable robot arm, the charging plug into the charging socket from the plug-in position, wherein the plug-in process is carried out based on the modified digital map.
9 . The apparatus according to claim 8 , wherein the processing apparatus is configured to carry out the image analysis via a neural network pre-trained on the charging socket.
10 . The apparatus according to claim 8 , wherein the processing apparatus is further configured to:
determine pose data, based on the image analysis, to determine a pose of the charging socket using a Perspective-n-Point (PnP) algorithm; and
move the charging plug into an intermediate position, based on the determined pose data.
11 . The apparatus according to claim 10 , wherein the processing apparatus is further configured to determine the pose by additionally determining the mean value of the pose data.
12 . The apparatus according to claim 10 , wherein the processing apparatus is further configured to:
generate a depth image of the charging socket corresponding to the current position of the charging plug when the charging plug is in the intermediate position;
process the generated depth image with a reference depth image corresponding to a reference position to determine a position deviation between the current position of the charging plug and the reference position; and
move the charging plug into the plug-in position based on the determined position deviation.
13 . The apparatus according to claim 12 , wherein the reference depth image comprises a reference depth image recorded from a predefined distance and/or position with respect to the charging socket.
14 . The apparatus according to claim 12 , wherein the processing apparatus is further configured to determine the position deviation using an Iterative Closest Point (ICP) algorithm.
15 . A method for autonomously plugging a charging plug of a programmable robot arm into a charging socket of a vehicle, comprising:
visually identifying the charging socket using image analysis of created images of the charging socket, wherein the image analysis is carried out via a neural network pre-trained on the charging socket;
processing image data of a surrounding area of the charging station to generate a digital map comprising a charging socket region in which the charging socket is configured;
moving, via the programmable robot arm, the charging plug into a plug-in position, spaced apart from the charging socket;
processing the digital map to generate a modified digital map comprising a removed charging socket region; and
plugging, via the programmable robot arm, the charging plug into the charging socket from the plug-in position, wherein the plug-in process is carried out based on the modified digital map.
16 . The method according to claim 15 , further comprising:
determining pose data, based on the image analysis, to determine a pose of the charging socket using a Perspective-n-Point (PnP) algorithm; and
moving the charging plug into an intermediate position based on the determined pose data.
17 . The method according to claim 16 , wherein the pose is determined by additionally determining the mean value of the pose data.
18 . The method according to claim 16 , further comprising:
generating a depth image of the charging socket corresponding to the current position of the charging plug when the charging plug is in the intermediate position;
processing the generated depth image with a reference depth image corresponding to a reference position to determine a position deviation between the current position of the charging plug and the reference position; and
moving the charging plug into the plug-in position based on the determined position deviation.
19 . The method according to claim 18 , wherein the reference depth image comprises a reference depth image recorded from a predefined distance and/or position with respect to the charging socket.
20 . The method according to claim 18 , wherein the position deviation is determined using an Iterative Closest Point (ICP) algorithm.