Systems and methods for a stud plate connector end effector are disclosed. A system includes a first clamping gripper and a second clamping gripper configured to secure a first piece of lumber during a lumber joining process. An abutting gripper located perpendicular to the first and second clamping grippers is configured to secure a second piece of lumber during the lumber joining process. One end of the second piece of lumber is positioned in contact with the first piece of lumber. A fastening tool located on an opposite end from the abutting gripper is configured to attach the first and second pieces of lumber together. A vision system is configured to align the second piece of lumber to the first piece of lumber. The first, second and abutting grippers align the first and second pieces of lumber based on an alignment data from the vision system.

This disclosure provides systems, methods, and apparatuses, including computer programs encoded on computer storage media, that provide for training, implementing, or updated machine learning logic, such as an artificial neural network, to model a manufacturing process performed in a manufacturing robot environment. For example, the machine learning logic may be trained and implemented to learn from or make adjustments based on one or more operational characteristics associated with the manufacturing robot environment. As another example, the machine learning logic, such as a trained neural network, may be implemented in a semi-autonomous or autonomous manufacturing robot environment to model a manufacturing process and to generate a manufacturing result. As another example, the machine learning logic, such as the trained neural network, may be updated based on data that is captured and associated with a manufacturing result. Other aspects and features are also claimed and described.

A method of assembling a plurality of subcomponents to form a finished component comprises gripping a first subcomponent with a first end-of-arm tool, wherein the first end-of-arm tool is attached to a first robot arm and grasping a second subcomponent with a second end-of-arm tool, wherein the second end-of-arm tool is attached to a second robot arm. Moving the first and second end-of-arm tools to position the first subcomponent relative to the second subcomponent in a pre-assembly position and then moving the first and second end-of-arm tools to engage interface surfaces of the first and second subcomponents. Forming a joint between the first subcomponent and the second subcomponent with a joining tool attached to a joining robot arm to thereby assemble the finished component.

Disclosed are a robot system for assembling components and a control method thereof. The control method compares location coordinates of a robot in a vision coordinate system with location coordinates in a robot coordinate system and calculates a first correction value, calculates a second correction value from a difference between location coordinates of a correction tool and a component, and calculates a third correction value from location coordinates of components located at predetermined spaced locations and spacing coordinates, thereby precisely assembling components and performing inspection of the assembling.

A method of assembling a plurality of subcomponents to form a finished component comprises gripping a first subcomponent with a first end-of-arm tool, wherein the first end-of-arm tool is attached to a first robot arm and grasping a second subcomponent with a second end-of-arm tool, wherein the second end-of-arm tool is attached to a second robot arm. Moving the first and second end-of-arm tools to position the first subcomponent relative to the second subcomponent in a pre-assembly position and then moving the first and second end-of-arm tools to engage interface surfaces of the first and second subcomponents. Forming a joint between the first subcomponent and the second subcomponent with a joining tool attached to a joining robot arm to thereby assemble the finished component.

Disclosed are a robot system for assembling components and a control method thereof. The control method compares location coordinates of a robot in a vision coordinate system with location coordinates in a robot coordinate system and calculates a first correction value, calculates a second correction value from a difference between location coordinates of a correction tool and a component, and calculates a third correction value from location coordinates of components located at predetermined spaced locations and spacing coordinates, thereby precisely assembling components and performing inspection of the assembling.

Systems and methods for a stud plate connector end effector are disclosed. A system includes a first clamping gripper and a second clamping gripper configured to secure a first piece of lumber during a lumber joining process. An abutting gripper located perpendicular to the first and second clamping grippers is configured to secure a second piece of lumber during the lumber joining process. One end of the second piece of lumber is positioned in contact with the first piece of lumber. A fastening tool located on an opposite end from the abutting gripper is configured to attach the first and second pieces of lumber together. A vision system is configured to align the second piece of lumber to the first piece of lumber. The first, second and abutting grippers align the first and second pieces of lumber based on an alignment data from the vision system.

A manufacturing method for joining first and second members to create a joined piece using a robot with pre-inputted instruction data. The method includes operating the robot to hold the second member for joining to the first member and photographing the second member to obtain an image of the second member at the holding position; comparing the image to a reference image of a joining position of a reference second member joined to a reference first member; determining a deviation amount by which the holding position of the second member deviates from the joining position in the reference image; determining a correction amount for correcting the holding position of the second member is to be corrected in order to reduce the deviation amount of the holding position of the second member; correcting the holding position of the second member according to the correction amount, and then subsequently joining the first and second members.

An embodiment includes a robotic welding system for generating a motion program, having a programmable robot controller of a robot having a computer processor and a computer memory. The programmable robot controller is configured to digitally record, in the computer memory, a plurality of spatial points along an operator path in a 3D space taken by a calibrated tool center point (TCP) of the robot as an operator manually moves a robot arm of the robot along the operator path from a start point to a destination point within the 3D space. The programmable robot controller is also configured to identify and eliminate extraneous spatial points from the plurality of spatial points as digitally recorded, leaving a subset of the plurality of spatial points as digitally recorded, where the extraneous spatial points are a result of extraneous movements of the robot arm by the operator.

This disclosure provides systems, methods, and apparatuses, including computer programs encoded on computer storage media, that provide for training, implementing, or updated machine learning logic, such as an artificial neural network, to model a manufacturing process performed in a manufacturing robot environment. For example, the machine learning logic may be trained and implemented to learn from or make adjustments based on one or more operational characteristics associated with the manufacturing robot environment. As another example, the machine learning logic, such as a trained neural network, may be implemented in a semi-autonomous or autonomous manufacturing robot environment to model a manufacturing process and to generate a manufacturing result. As another example, the machine learning logic, such as the trained neural network, may be updated based on data that is captured and associated with a manufacturing result. Other aspects and features are also claimed and described.