The present invention relates to a method of adjusting control commands for moving a medical camera connected to a motorized support structure, wherein the adjustment is based on images provided by the camera. Based on a comparison of at least two images provided by the camera, an actual motion of the camera is determined and compared with an intended motion defined by a control command forwarded to the motorized support structure. In case a deviation between the intended motion and the actual motion is determined, a correction is applied to the control command such that the actual motion of the camera coincides with the intended motion.

A controller calculates a correction amount of a position of a robot 1 at a movement point in a first movement path, and drives the robot 1 in a second movement path obtained by correcting the first movement path. The controller includes a second camera configured to detect a shape of a part after a robot apparatus performs a task, and a variable calculating unit configured to calculate, based on an output of the second camera, a quality variable representing quality of a workpiece. When the quality variable deviates from a predetermined determination range, a determination unit of the controller determines that the position or an orientation of the robot 1 needs to be modified based on a correlation between the correction amount of the position in the first movement path and the quality variable.

The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

A method for adaptable machining includes (a) providing one or more images with a digital imaging system of each of a series of work pieces, (b) for each of the work pieces, selectively modifying a preprogrammed cutting tool path with regard to the image of the respective work piece, and (c) for each of the work pieces, performing a machining operation according to the respective selectively modified preprogrammed cutting tool path.

A teaching method for a transfer mechanism is provided. The teaching method includes (a) placing a first substrate or an edge ring on a fork of the transfer mechanism, transferring the first substrate or the edge ring to a target position, and placing the first substrate or the edge ring onto the target position; (b) placing a second substrate having a position detection sensor on the fork, and transferring the second substrate to a position directly above or below the target position; (c) detecting an amount of deviation between the first substrate or the edge ring and the target position using the position detection sensor of the second substrate; and (d) correcting transfer position data of the transfer mechanism for the first substrate or the edge ring to be transferred next, based on the detected amount of deviation.

In a teaching method for a transfer mechanism that transfers a substrate to a mounting table, the method includes: transferring an inspection substrate having a plurality of imaging devices on an outer peripheral edge thereof to a transfer position where the substrate is transferred between the transfer mechanism and the mounting table; imaging a part of the mounting table which includes an outer periphery of the mounting table at the transfer position by the imaging devices; calculating a central position of the mounting table based on the image obtained by the imaging devices; and correcting the transfer position based on the central position of the mounting table which is calculated in the calculating and a central position of the inspection substrate at the transfer position.

A controller calculates a correction amount of a position of a robot 1 at a movement point in a first movement path, and drives the robot 1 in a second movement path obtained by correcting the first movement path. The controller includes a second camera configured to detect a shape of a part after a robot apparatus performs a task, and a variable calculating unit configured to calculate, based on an output of the second camera, a quality variable representing quality of a workpiece. When the quality variable deviates from a predetermined determination range, a determination unit of the controller determines that the position or an orientation of the robot 1 needs to be modified based on a correlation between the correction amount of the position in the first movement path and the quality variable.

The present disclosure relates to systems and methods that use computer-vision processing systems to improve patient safety during surgical procedures. Computer-vision processing systems may train machine-learning models using machine-learning techniques. The machine-learning techniques can be executed to train the machine-learning models to recognize, classify, and interpret objects within a live video feed. Certain embodiments of the present disclosure can control (or facilitate control of) surgical tools during surgical procedures using the trained machine-learning models.

A target path is corrected using an imaging result of a workpiece and a moving distance of a control object for each control cycle is kept constant. The PLC generates a connected path for each control cycle so that a length of the corrected path for each control cycle substantially matches a length of a normative path for each control cycle.