Systems, methods, devices, and other techniques are described for planning motions of one or more robots to perform at least one specified task. In some implementations, a task to execute with a robotic system using a tool is identified. A partially constrained pose is identified for the tool that is to apply during execution of the task. A set of possible constraints for the unconstrained pose parameter are selected for each unconstrained pose parameter. The sets of possible constraints are evaluated for the unconstrained pose parameters with respect to one or more task execution criteria. A nominal pose is determined for the tool based on a result of evaluating the sets of possible constraints for the unconstrained pose parameters with respect to the one or more task execution criteria. The robotic system is then directed to execute the task, including positioning the tool according to the nominal pose.

A control apparatus includes an operation unit that teaches the robot a position, a posture changing instruction unit that instructs a position change when the robot passes through a singularity or its vicinity, a singularity passing motion request unit that instructs the robot to change its posture, a robot drive information request unit that acquires robot drive information, and a robot G-code generation unit that inserts a G-code from the robot drive information into a program. A robot includes a drive control unit that drives the robot, a singularity determination unit that determines passage through the singularity or its vicinity, a singularity passing pattern generation unit that generates a motion plan for passage through the singularity or its vicinity based on the changed posture, and a robot drive information output unit that transmits the robot drive information to the control apparatus.

A multi-type industrial robot control system may include: an automation controller; and a programmable logic controller (PLC)-robot bridge. The controller stores a general-purpose robot control function block generated using a unified design standard, calls a corresponding robot control function block for a robot and using robot state data and puts out corresponding first command data to the PLC-robot bridge. The PLC-robot bridge virtualizes robot interfaces of corresponding offline programming functions of different types of robot as a unified virtual interface, calls a corresponding offline programming function via the unified virtual interface according to the first command data, and generates second command data for output to a corresponding robot controller. The corresponding robot controller controls a corresponding robot. At the same time, robot state data from a corresponding type of robot is received via the unified virtual interface and the robot state data is fed back to the automation controller.

As opposed to a rigid approach, implementations disclosed herein utilize a flexible approach in automatically determining an action set to utilize in attempting performance of a task that is requested by natural language input of a user. The approach is flexible at least in that embedding technique(s) and/or action model(s), that are utilized in generating action set(s) from which the action set to utilize is determined, are at least selectively varied. Put another way, implementations leverage a framework via which different embedding technique(s) and/or different action model(s) can at least selectively be utilized in generating different candidate action sets for given NL input of a user. Further, one of those action sets can be selected for actual use in attempting real-world performance of a given task reflected by the given NL input. The selection can be based on a suitability metric for the selected action set and/or other considerations.

Drive unit of an automation component, in particular a gripping, clamping, changing, linear or pivoting unit, whereby the drive unit includes a drive for driving the movable parts of the automation component and a control unit which controls the drive, whereby the control unit includes at least one computing device, and the drive unit together with the drive, control unit and computing device is arranged in or on a base housing of the automation component.

A policy improvement method of improving a policy of reinforcement learning by a state value function, is executed by a computer and includes adding a plurality of perturbations to a plurality of components of a first parameter of the policy; estimating a gradient function of the state value function with respect to the first parameter, based on a result of an input determination performed for a control target in the reinforcement learning, the input determination being performed by using the policy that uses a second parameter obtained by adding the plurality of perturbations to the plurality of components; and updating the first parameter based on the estimated gradient function.

Example robotic process automation systems and methods are described. In one implementation, a processing system receives a first automation scenario, where the first automation scenario is for execution by the processing system. The processing system identifies a list of plugins in the first automation scenario and identifies a version number associated with each of the plugins in the first automation scenario. Additionally, the processing system verifies the list of plugins and their associated version numbers. If the list of plugins and their associated version numbers are verified, the processing system builds a first virtual environment for the plugins in the first automation scenario.

A user interface (UI) mapper for robotic process automation (RPA) is disclosed. The UI mapper may initially capture UI elements to fetch UI elements faster for later use and allow an RPA developer to “map” the UI elements for automating an application. This may enable subsequent developers who potentially do not have programming knowledge to build RPA workflows using these predefined “target” UI elements.

An automation task program is inspected for unsecure data flow. The task program is parsed to generate a parse tree, which is visited to generate control flow graphs of functions of the task program. The control flow graphs have nodes, which have domain-agnostic intermediate representations. The control flow graphs are connected to form an intermediate control flow graph. The task program is deemed to have an unsecure data flow when data is detected to flow from a data source to a data sink, with the data source and the data sink forming a source-sink pair that is indicative of an unsecure data flow.

An approach for fully automating the use of robotic devices in a laboratory workflow includes defining sequences for automating tasks and equipment involved in such a workflow, and calculating a path for each sequence that resolves get, handoff, and placement procedures. The approach develops a schedule that executes resolved pathways in and between each device. The approach is provided with an easy-to-use interface, in which a user drags and drops devices to automatically configure them, defines operations to be performed by these devices, and then runs the laboratory workflow. The interface also provides the ability to monitor progress of the workflow, and make modifications and adjustments as needed.