Methods of assembling a controller for a commissioning device are provided. A method includes extending a delivery table in a first horizontal direction, the delivery table having a storage end and a retrieval end, disposing two elongated clamping jaws above the delivery table, extending, in a second horizontal direction perpendicular to the first horizontal direction, a first guide and a second guide that are parallel and spaced from one another in the first horizontal direction, coupling at least four clamping jaw carriages to the first and second guides, wherein at least two clamping jaw carriages separated from one another in the first horizontal direction are coupled to a single clamping jaw, respectively, and coupling at least four drive elements to a clamping jaw drive unit.

A method and a robot controller for controlling a robot arm, where the robot arm comprises a plurality of robot joints connecting a robot base and a robot tool flange, where each of the robot joints comprises an output flange movable in relation to a robot joint body and a joint motor configured to move the output flange in relation to the robot joint body. The robot arm is controlled based on vibrational properties of at least one external object connected to the robot arm, where the vibrational properties are received via an external object installation interface by generating control signals for said robot arm based on a target motion and the received vibrational properties of the at least one external object, the control signal comprises control parameters for said joint motor.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a robot to perform a custom real-time action that uses a callback function. One of the methods comprises receiving a definition of a custom real-time control function that specifies a custom callback function, an action, and a custom reaction that references the custom callback function; providing a command to initiate the action; repeatedly executing, by the control layer of the real-time robotics control framework, the custom real-time control function at each tick of a real-time robotics system driving one or more physical robots, including: obtaining current values of one or more state variables, evaluating the custom reaction specified by the custom real-time control function according to the current values of the one or more state variables, and whenever the one or more conditions of the custom reaction are satisfied, invoking the custom callback function.

A system and method for facilitating communication between a control server and robotic devices are provided. An integration engine of the system identifies protocol schemes and message schemes that are supported by the control server and robotic devices. When the protocol schemes and message schemes of the control server and the robotic devices are same, the integration engine facilitates transmission and reception of instructions between the control server and the robotic devices through identified communication interfaces. When the protocol schemes and message schemes of the control server and the robotic devices are different, the integration engine translates the protocol schemes and message schemes that are received from one of the control server and the robotic devices to facilitate communication between the control server and the robotic devices through identified communication interfaces.

A model generator implements a data-driven approach to generating a robot model that describes one or more physical properties of a robot. The model generator generates a set of basis functions that generically describes a range of physical properties of a wide range of systems. The model generator then generates a set of coefficients corresponding to the set of basis functions based on one or more commands issued to the robot, one or more corresponding end effector positions implemented by the robot, and a sparsity constraint. The model generator generates the robot model by combining the set of basis functions with the set of coefficients. In doing so, the model generator disables specific basis functions that do not describe physical properties associated with the robot. The robot model can subsequently be used within a robot controller to generate commands for controlling the robot.

A bilateral teleoperation system includes: a primary-end operation platform and a secondary-end operation platform. The primary-end operation platform includes: a primary-end support, primary-end mechanical arms, a mechanical hand control assembly, and a first controller, a root end of the primary-end mechanical arm being arranged on the primary-end support, and a tail end of the primary-end mechanical arm being connected to the mechanical hand control assembly. The secondary-end operation platform includes: a secondary-end support, secondary-end mechanical arms, secondary-end mechanical hands, and a second controller, a root end of the secondary-end mechanical arm being arranged on the secondary-end support, and a tail end of the secondary-end mechanical arm being connected to the secondary-end mechanical hand; the primary-end mechanical arm and the secondary-end mechanical arm are homogeneous mechanical arms, and the first controller in the primary-end operation platform is communicatively connected to the second controller in the secondary-end operation platform.

Robotics control system (10) and method for training said robotics control system are provided. Disclosed embodiments make a gracefully blended utilization of Reinforcement Learning (RL) with conventional control by way of a dynamically adaptive interaction between respective control signals (20, 24) generated by a conventional feedback controller (18) and an RL controller (22). Additionally, disclosed embodiments make use of an iterative approach for training a control policy by effective use of virtual sensor and actuator data (60) interleaved with real-world sensor and actuator data (54). This is effective to reducing a training sample size to fulfill a blended control policy for the conventional feedback controller and the reinforcement learning controller. Disclosed embodiments may be used in a variety of industrial automation applications.

A method and apparatus for controlling an operation of a service robot is disclosed. The method includes measuring, by processing circuitry, an evaluation index of the service robot based on sensor data in a service mode; determining, by the processing circuitry, an operation mode of the service robot from a set of at least two operation modes based on the measured evaluation index; selecting, by the processing circuitry, a behavior to be applied to the operation of the service robot from a set of at least two behaviors based on the operation mode; and controlling, by the processing circuitry, the operation of the service robot based on the behavior.

Control for controlling a robot that allows selection from among multiple gaits is provided. The control apparatus includes a cost map creation unit that creates a cost map for each of gaits of the robot that allows selection from among multiple gaits, and a path creation unit that creates a path including gait switching for the robot by using the cost maps created by the cost map creation unit. The path creation unit searches for the shortest path by using the cost map of the gait that is high in traversing performance among the multiple gaits, performs search for a gait switching point on the path found out, and researches, in a case where there is a gait switching point, for a path on the cost map of the gait selected by an objective function, by using the gait switching point as a sub goal.

A method for simulating a braking operation of a robot wherein a dynamic model of the robot is used to determine, for a given initial state of the robot, a final state range with a plurality of possible final states of the robot as a result of the simulated braking operation.