A robot welding method based on semantic feature clustering; the method comprises: acquiring an image of a workpiece, and generating an image training sample set; performing semantic annotation on the image of the workpiece to generate a semantic training sample set; establishing a semantic clustering model, and training same by using the image training sample set and the semantic training sample set; by using the trained semantic clustering model, identifying an image of a workpiece to be welded, so as to obtain data of the workpiece to be welded; on the basis of the data of the workpiece to be welded and by using parameterized online programming, generating a welding program for the workpiece to be welded; and on the basis of the welding program, executing welding of the workpiece to be welded. By means of the robot welding method based on semantic feature clustering, neither teaching programming nor offline programming is required, thereby improving the precision, efficiency, universality and flexibility. Further provided is a robot welding system based on semantic feature clustering.

Robots capable of accommodating dynamic replacement of end effectors load and run software that allows the end effector to be operated without change to the main control program. The driver may be dynamically linked and run during program execution when the corresponding end effector is detected. Typically, the robot controller will store a library of drivers, and load the appropriate driver when a new end effector is detected.

A method including, at an autonomous vehicle: autonomously navigating across an outdoor terrain to locate a robotic arm and a set of objects proximal an install location; accessing an image from an optical sensor; detecting a set of install features at the install location based on the image; calculating a gross install pose of the object that locates an object proximal the install location and offset from the set of install features; defining a keep-in boundary proximal the install location and encompassing the gross install pose; autonomously navigating the robotic arm to retrieve the object from the set of objects and to locate the object in the gross install pose; detecting a series of forces applied to a distal end of the robotic arm; and navigating the object in directions of the series of forces while maintaining the object fully within the keep-in boundary.

A method including, at an autonomous vehicle: autonomously navigating across an outdoor terrain to locate a robotic arm and a set of objects proximal an install location; accessing an image from an optical sensor; detecting a set of install features at the install location based on the image; calculating a gross install pose of the object that locates an object proximal the install location and offset from the set of install features; defining a keep-in boundary proximal the install location and encompassing the gross install pose; autonomously navigating the robotic arm to retrieve the object from the set of objects and to locate the object in the gross install pose; detecting a series of forces applied to a distal end of the robotic arm; and navigating the object in directions of the series of forces while maintaining the object fully within the keep-in boundary.

Robots capable of accommodating dynamic replacement of end effectors load and run software that allows the end effector to be operated without change to the main control program. The driver may be dynamically linked and run during program execution when the corresponding end effector is detected. Typically, the robot controller will store a library of drivers, and load the appropriate driver when a new end effector is detected.

Robots capable of accommodating dynamic replacement of end effectors load and run software that allows the end effector to be operated without change to the main control program. The driver may be dynamically linked and run during program execution when the corresponding end effector is detected. Typically, the robot controller will store a library of drivers, and load the appropriate driver when a new end effector is detected.

A method including, at an autonomous vehicle: autonomously navigating across an outdoor terrain to locate a robotic arm and a set of objects proximal an install location; accessing an image from an optical sensor; detecting a set of install features at the install location based on the image; calculating a gross install pose of the object that locates an object proximal the install location and offset from the set of install features; defining a keep-in boundary proximal the install location and encompassing the gross install pose; autonomously navigating the robotic arm to retrieve the object from the set of objects and to locate the object in the gross install pose; detecting a series of forces applied to a distal end of the robotic arm; and navigating the object in directions of the series of forces while maintaining the object fully within the keep-in boundary.

A robot welding method based on semantic feature clustering; the method comprises: acquiring an image of a workpiece, and generating an image training sample set; performing semantic annotation on the image of the workpiece to generate a semantic training sample set; establishing a semantic clustering model, and training same by using the image training sample set and the semantic training sample set; by using the trained semantic clustering model, identifying an image of a workpiece to be welded, so as to obtain data of the workpiece to be welded; on the basis of the data of the workpiece to be welded and by using parameterized online programming, generating a welding program for the workpiece to be welded; and on the basis of the welding program, executing welding of the workpiece to be welded. By means of the robot welding method based on semantic feature clustering, neither teaching programming nor offline programming is required, thereby improving the precision, efficiency, universality and flexibility. Further provided is a robot welding system based on semantic feature clustering.