| CPC B25J 9/1697 (2013.01) [B23K 9/0956 (2013.01); B23K 37/0229 (2013.01); B23K 37/0258 (2013.01); B23K 37/04 (2013.01); B25J 9/161 (2013.01); B25J 9/1666 (2013.01); B25J 9/1671 (2013.01); B25J 11/005 (2013.01); B25J 13/08 (2013.01); B25J 15/0019 (2013.01); G06T 7/0004 (2013.01); G06T 7/70 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 2207/10028 (2013.01); G06T 2207/20084 (2013.01); G06V 2201/06 (2022.01)] |
| AS A RESULT OF REEXAMINATION, IT HAS BEEN DETERMINED THAT: |
| The patentability of claims 1-20 is confirmed. |
| New claims 21-29 are added and determined to be patentable. |
|
1. An autonomous robotic welding system comprising:
a controller configured to:
instruct one or more sensors to capture multiple images of a workspace, the workspace including:
one or more fixtures configured to temporarily secure first and second weldable objects on a positioner in a way that aligns the first and second weldable objects to form a seam; and
a robotic arm coupled to a welding tool, the welding tool configured to perform a welding operation along the seam;
identify at least the one or more fixtures and the seam based on one or more images of the multiple images;
generate a welding path for a robot to follow when welding the seam, wherein the welding path is planned considering whether the welding tool or the robotic arm is predicted to collide with the one or more fixtures; and
instruct the robot to weld the seam according to the generated welding path.
|
|
[ 21. The autonomous robotic welding system of claim 1, wherein the welding path is planned considering whether the welding tool or the robotic arm is predicted to collide with the one or more fixtures by evaluating a plurality of waypoint-node pairs of the robot along the seam, wherein each waypoint-node pair of the plurality of waypoint-node pairs represents a possible orientation of the weld head at that waypoint along the seam, wherein considering whether the welding tool or the robotic arm is predicted to collide with the one or more fixtures comprises comparing a 3D model of the fixture and a 3D model of the robotic arm for each of the waypoint-node pairs.]
|
|
[ 22. The welding robotic system of claim 8, further comprising the one or more sensors, wherein at least one of the one or more sensors is positioned on the robotic arm, wherein the welding path is generated based upon comparing a 3D model of the fixture and a 3D model of the robotic arm, based upon the image data associated with the one or more images and received from the at least one of the one or more sensors positioned on the robotic arm.]
|
|
[ 23. The computer-implemented method of claim 16, wherein generating the welding path comprises considering whether the welding tool or the robotic arm is predicted to collide with the fixture by evaluating a plurality of waypoint-node pairs of the robot along the seam, wherein the welding path omits a subset of the plurality of waypoint-node pairs for which the welding tool or the robotic arm is predicted to collide with the fixture.]
|
|
[ 24. An autonomous robotic welding system comprising:
a controller configured to:
instruct one or more sensors to capture multiple images of a workspace, the workspace including:
one or more adjustable fixtures configured to temporarily secure first and second weldable objects on a positioner in a way that aligns the first and second weldable objects to form a seam; and
a robotic arm coupled to a welding tool, the welding tool configured to perform a welding operation along the seam;
identify at least the one or more adjustable fixtures and the seam based on one or more images of the multiple images;
generate a welding path for a robot to follow when welding the seam, wherein the welding path is planned considering whether the welding tool and the robotic arm are predicted to collide with the one or more adjustable fixtures; and
instruct the robot to weld the seam according to the generated welding path.]
|
|
[ 25. The autonomous robotic welding system of claim 24, wherein the welding path is planned considering whether the welding tool and the robotic arm are predicted to collide with the one or more adjustable fixtures by evaluating a plurality of waypoint-node pairs of the robot along the seam, wherein each waypoint-node pair of the plurality of waypoint-node pairs represents a possible orientation of the weld head at that waypoint along the seam.]
|
|
[ 26. The autonomous robotic welding system of claim 25, wherein the welding path omits a subset of the plurality of waypoint-node pairs for which the welding tool or the robotic arm would collide with the one or more adjustable fixtures.]
|
|
[ 27. The autonomous robotic welding system of claim 26, wherein considering whether the welding tool or the robotic arm is predicted to collide with the one or more adjustable fixtures comprises comparing a three-dimensional representation of the adjustable fixture and a three-dimensional representation of the robotic arm and determining whether the three-dimensional representation of the adjustable fixture is likely to overlap with the three-dimensional representation of the robotic arm.]
|
|
[ 28. The autonomous robotic welding system of claim 27, further comprising the one or more sensors and the robotic arm, wherein the one or more sensors is positioned on the robotic arm.]
|
|
[ 29. The autonomous robotic welding system of claim 24, wherein the controller is configured to identify the at least one adjustable fixture and the seam based on at least one of a pixel-wise classification technique performed on the multiple images or a point-wise classification technique performed on a point cloud generated using the multiple images.]
|