Machine learning driven computer numerical control of a robotic machine tool

One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause the one or more computing devices to:

• generate, by one or more sensors, sensor signals representing a manufacturing environment in which a modular robotic apparatus is located, the modular robotic apparatus comprising a robotic machine tool and a machine learning module, the machine learning module comprising a machine learning model;
• generate, by the machine learning model, a computer numerical control (CNC) configuration, the machine learning model trained based on one or more manufacturing parameters defining a manufacturing task to be performed by the modular robotic apparatus;
• adjust, by the machine learning model, the CNC configuration based on the sensor signals;
• and
• operate, by the robotic machine tool, an end effector of the robotic machine tool in accordance with the adjusted CNC configuration to perform the manufacturing task,
• wherein, if the machine learning model determines that one or more additional modular robotic apparatuses are required to perform the manufacturing task, the machine learning module adjusts the CNC configuration to cause the modular robotic apparatus to coordinate operations with the one or more additional robotic modular apparatuses,
• wherein determining whether one or more additional modular robotic apparatuses are required to perform the manufacturing task comprises (i) measuring a parameter of a workpiece being manipulated as part of the manufacturing task, (ii) determining whether the measured parameter of the workpiece exceeds a predetermined threshold value, and (iii) based on determining that the measured parameter of the workpiece exceeds the predetermined threshold value, determining that one or more additional modular robotic apparatuses are required to perform the manufacturing task.

A method comprising:

• generating, by one or more sensors, sensor signals representing a manufacturing environment in which a modular robotic apparatus is located, the modular robotic apparatus comprising a robotic machine tool and a machine learning module, the machine learning module comprising a machine learning model;
• generating, by the machine learning model, a computer numerical control (CNC) configuration, the machine learning model trained based on one or more manufacturing parameters defining a manufacturing task to be performed by the modular robotic apparatus;
• adjusting, by the machine learning model, the CNC configuration based on the sensor signals;
• and
• operating, by the robotic machine tool, an end effector of the robotic machine tool in accordance with the adjusted CNC configuration to perform the manufacturing task,
• wherein, if the machine learning model determines that one or more additional modular robotic apparatuses are required to perform the manufacturing task, the machine learning module adjusts the CNC configuration to cause the modular robotic apparatus to coordinate operations with the one or more additional robotic modular apparatuses,
• wherein determining whether one or more additional modular robotic apparatuses are required to perform the manufacturing task comprises (i) measuring a parameter of a workpiece being manipulated as part of the manufacturing task, (ii) determining whether the measured parameter of the workpiece exceeds a predetermined threshold value, and (iii) based on determining that the measured parameter of the workpiece exceeds the predetermined threshold value, determining that one or more additional modular robotic apparatuses are required to perform the manufacturing task.