Methods, systems and apparatus, including computer programs encoded on computer storage medium, for processing parts using machine tool workstations. The machine tool workstations are grouped into multiple groups, where each group includes workstations of the same type. For each of the multiple groups, data representing parts to be processed by the type of workstations included in the group are transmitted to a combinatorial optimization problem solver. Data representing a sequence of ordered subsets of the multiple parts that produce a reduced setup time for the workstations in the group are received from the solver. An average delay time associated with the generated sequence of ordered subsets of the collection of parts is computed. If the average delay time is less than the predetermined threshold, parts are released according to the generated sequence of ordered subsets of the collection of parts to the group for processing.

A method to control a robot to perform at least one Cartesian or joint space task comprises using quadratic programming to determine joint forces, in particular joint torques, and/or joint accelerations of said robot based on at least one cost function which depends on said task.

Presented herein are systems and methods for receiving video data associated with at least one task performed by at least one worker and executing, based on the received video data, a human action recognition program to identify at least one action associated with the at least one task and executing an object detection program to identify at least one object associated with the at least one task, identifying, based on a combination of the identified at least one action and the identified at least one object associated with the at least one task, at least one subtask of the at least one task, and generating at least first and second labels for the identified at least one subtask based on at least first and second labels, respectively, associated from a first set of existing labels for identified actions and from a second set of existing labels for identified objects, respectively.

A robot may include: a multi-tool module having redundancy, the multi-tool module including a guide tube and a plurality of tools configured to operate while interacting with the guide tube and extended from the guide tube; and/or a controller configured to generate a control signal regarding motion of the multi-tool module in a joint space based on motion instruction information regarding distal ends of the plurality of tools in a task space. The redundancy may reflect that a number of degrees of freedom of the multi-tool module in the joint space is greater than a number of degrees of freedom of the task space. The control signal may be generated using the redundancy.

A program for a numerical control device is disclosed that determines path points to be approached by an end effector. A control signal group is ascertained for each path point that contains its set point value for each position-controlled axis. Those values are output to the axes, moving the end effector. The degrees of freedom are fewer than the position-controlled axes. The control signal groups are ascertained so that the end effector approaches the path points at least approximately. The control signal groups are ascertained gradually during the activation of the axes. The set point values are ascertained by minimizing an objective function. The objective function that is minimized includes at least the set point values for a path point only to be approached in the future. The sequence between the currently approached point and the point approached in the future has at least one further path point.

Presented herein are systems and methods for receiving video data associated with at least one task performed by at least one worker and executing, based on the received video data, a human action recognition program to identify at least one action associated with the at least one task and executing an object detection program to identify at least one object associated with the at least one task, identifying, based on a combination of the identified at least one action and the identified at least one object associated with the at least one task, at least one subtask of the at least one task, and generating at least first and second labels for the identified at least one subtask based on at least first and second labels, respectively, associated from a first set of existing labels for identified actions and from a second set of existing labels for identified objects, respectively.