A robotic assembly cell is configured to generate a physical mesh of physical polygons based on a simulated mesh of simulated triangles. A control application configured to operate the assembly cell selects a simulated polygon in the simulated mesh and then causes a positioning robot in the cell to obtain a physical polygon that is similar to the simulated polygon. The positioning robot positions the polygon on the physical mesh, and a welding robot in the cell then welds the polygon to the mesh. The control application captures data that reflects how the physical polygon is actually positioned on the physical mesh, and then updates the simulated mesh to be geometrically consistent with the physical mesh. In doing so, the control application may execute a multi-objective solver to generate an updated simulated mesh that meets specific design criteria.

A method for controlling a modeling device that corrects a target position of a welding torch in the modeling device. The method includes acquiring a reference profile prepared in advance and including a shape of a positioning index body implemented by at least a part of a base metal or a weld bead, a step of measuring a shape of the positioning index body by a shape measurement unit attached to the welding torch or a manipulator to acquire an actual profile, comparing the reference profile with the actual profile of the positioning index body to obtain a deviation amount of the target position of the welding torch based on a positional deviation of the positioning index body between the reference profile and the actual profile, and outputting an operation correction command of the manipulator for correcting the target position of the welding torch according to the deviation amount.

There is provided a machining system in which for automation of loading and unloading of an article with respect to a machining device, an operation of a robot can be easily set from a machine controller of the machining device. The machining system includes a machine controller and a robot controller. The machine controller includes a communication section configured to read from a storage section setting data and a robot operation program which correspond to the type of the machined article as set by a setting section when a determination section determines that the moving robot is disposed at a predetermined position, and transmit the same to the robot controller.

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.

A system and method for manufacturing and/or reconditioning side frames and bolsters for railway cars includes at least one robot adapted to access positions along the length of the part. A map of the part dimensions, which may be obtained by a probe or scanner on the robot(s), allows a processor to determine where welding and machining are required to meet certain dimensional tolerances, leveraging novel reference surfaces on the part which cannot be leveraged using conventional gauges. The robot(s) may locate and mount welding and material removal tools to carry out the welding and material removal operations determined by the processor.

An offline teaching device has a calculation unit which calculates a second position of a second tool on a work line which is separated by a predetermined distance from a first position of a first tool on the work line, calculates a workpiece position where the first tool in the first position contacts or adjoins the workpiece, and calculates a workpiece position and posture such that the second tool in the second position contacts or adjoins the workpiece by changing the posture of the workpiece from the workpiece position with respect to the first tool, while maintaining the work posture of the first tool, and has a generation unit which generates a robot teaching position based on the position and posture of the workpiece and the holding position of the workpiece, and generates a program such that the first tool and the second tool pass along the work line.

A robot system includes a first robot for operation to which a work tool is attached, a second robot for delivery to which a hand is attached, a first visual sensor attached to the first robot, a first control device for controlling the first robot, and a second control device for controlling the second robot. The first control device detects the position of a workpiece when an operation is performed based on the image captured by the first imaging device. The second control device includes a second correction unit for calculating the amount of correction in the second robot which relates to a deviation of the position of the workpiece relative to the hand, based on the position of the workpiece which is acquired from the first control device.

A robotic welding system comprises a supporting arm for attaching to a repositionable support structure, the supporting arm comprising a first mounting portion connectable to the repositionable support structure, and a second mounting portion rotatably coupled to the first mounting portion. A yaw rotary actuator rotates the second mounting portion about a yaw axis. A welding arm comprises a third mounting portion rotatably coupled to the second mounting portion of the supporting arm. A pitch rotary actuator rotates the third mounting portion about a pitch axis generally perpendicular to the yaw axis. A roll rotary actuator rotates a torch holder shaft about a roll axis generally perpendicular to the pitch axis. The shaft has a torch mounting portion for mounting a welding torch at an end thereof. A controller is operably coupled to the actuators to cause the welding torch to execute a welding pattern.

A robotic welding system comprises a supporting arm for attaching to a repositionable support structure, the supporting arm comprising a first mounting portion connectable to the repositionable support structure, and a second mounting portion rotatably coupled to the first mounting portion. A yaw rotary actuator rotates the second mounting portion about a yaw axis. A welding arm comprises a third mounting portion rotatably coupled to the second mounting portion of the supporting arm. A pitch rotary actuator rotates the third mounting portion about a pitch axis generally perpendicular to the yaw axis. A roll rotary actuator rotates a torch holding portion having a torch mount at an end thereof configured for mounting a welding torch about a roll axis generally perpendicular to the pitch axis. A controller is operably coupled to the actuators to cause the welding torch to execute a welding pattern.

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.