A system comprises a database; at least one hardware processor coupled with the database; and one or more software modules that, when executed by the at least one hardware processor, receive at least one of sensory data from a robot and images from a camera, identify and build models of objects in an environment, wherein the model encompasses immutable properties of identified objects including mass and geometry, and wherein the geometry is assumed not to change, estimate the state including position, orientation, and velocity, of the identified objects, determine based on the state and model, potential configurations, or pre-grasp poses, for grasping the identified objects and return multiple grasping configurations per identified object, determine an object to be picked based on a quality metric, translate the pre-grasp poses into behaviors that define motor forces and torques, communicate the motor forces and torques to the robot in order to allow the robot to perform a complex behavior generated from the behaviors.

A control device includes a processor wherein the processor is configured to: receive designation of one or more frequency components, generate one or more second control signals obtained by reducing at least one of the frequency components from a first control signal, generate one or more third control signals obtained using two control signals among the first control signal and the one or more second control signals, output one control signal among the first control signal, the one or more second control signals, and the one or more third control signals, and generate and output a driving signal to drive a robot based on the one control signal.

The invention relates to a robot having: a moving manipulator driven by means of actuators, a first unit for determining external forces and/or external torques acting upon the manipulator, and a second unit for controlling or regulating the actuators as a function of the determined external forces and/or external torques acting upon the manipulator, wherein the second unit is designed to control/regulate the actuators for a predefined sub-space T1 of a working space AR of the manipulator such that the manipulator recedes flexibly into the sub-space T1 upon the application of a determined external force and/or of a determined external torque onto the manipulator along a projection {right arrow over (P)}.sub.T1 of the force and/or of the torque, wherein the following applies: T1.Math.AR and T1AR, and the working space AR specifies all permitted translations and/or rotations of the manipulator, and to determine, for a space TK1 complementary to the sub-space T1, a projection {right arrow over (P)}.sub.TK1 of the determined external force and/or of the determined external torque into the complementary space TK1, wherein the following applies: T1TK1={0}, T1.Math.AR, and TK1.Math.AR, to classify the projection {right arrow over (P)}.sub.TK1 into one of several predefined classes with respect to amount and/or direction and/or time curve, wherein at least one event-discrete and/or continuous setpoint control command and/or one setpoint control rule is stored for each predefined class, and to control/regulate the actuators as a function of the classification of the projection {right arrow over (P)}.sub.TK1 based on the respective setpoint control command and/or setpoint control rule.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing transformation mode switching in a robotics control system. One of the methods includes receiving data representing a state machine that defines one or more portions of a robotics task; executing a first control loop corresponding to a first node of the state machine, wherein executing the first control loop comprises providing commands to the robotic components computed from a first coordinate transformation process; determining, based on one or more status messages, that an exit condition for the first node has been satisfied; performing a mode switch between the first coordinate transformation process and a different second coordinate transformation process; and executing a second control loop corresponding to a second node of the state machine, wherein executing the second control loop comprises providing commands to the robotic components computed from the second coordinate transformation process.

A system for motion control is presented. In one embodiment, a motion control 3D projection system includes a projector; and a projection surface coupled to a robotic arm, where the robotic arm moves the projection surface through a set of spatial coordinates, and a 3D projection from the projector is projected onto a set of coordinates of the projection surface and matches the 3D projection to the set of coordinates of the projection surface as the projection surface moves through the set of spatial coordinates. In additional embodiments, a master control system may integrate additional robotic arms and other devices to create a motion control scene with a master timeline.

Provided is a robot including a hand and a control unit that operates the hand. The control unit rotates a first object around a predetermined position of the first object with the hand and moves the first object with respect to a second object, based on a captured image including the hand and the first object.

One aspect of the present invention provides a robot controller for end portion control of a multi-degree-of-freedom robot. The robot controller comprises: a first control interface, which is positioned at a first position around the robot end portion and receives a first control input for at least for directions; a second control interface, which is positioned at a second position around the robot end portion and receives a second control input for at least four directions; and an encoder, which interprets the combination of the first and second control inputs as a third control input about the robot end portion and provides the robot with a signal according to the third control input.

A method for switching a control of a robot into a manual operating mode, wherein the robot is movable by a user manually applying at least one of a force or a torque upon the robot, includes detecting at least one of joint forces or joint torques of the robot, and triggering an error reaction in response to the switching and based on at least one of the detected joint forces and/or joint torques, target joint forces and/or target joint torques, or a pose of the robot.

A method for controlling a mechanical system having a plurality of components interlinked by a plurality of driven joints, the method comprising: measuring torques or forces about or at the driven joints and forming a load signal representing the measured torques or forces; receiving a motion demand signal representing a desired state of the system; implementing an impedance control algorithm in dependence on the motion demand signal and the load signal to form a target signal indicating a target configuration for each of the driven joints; measuring the configuration of each of the driven joints and forming a state signal representing the measured configurations; and forming a set of drive signals for the joints by, for each joint, comparing the target configuration of that joint as indicated by the target signal to the measured configuration of that joint as indicated by the state signal.

A method for controlling a mechanical system having a plurality of components interlinked by a plurality of driven joints, the method comprising: measuring torques or forces about or at the driven joints and forming a load signal representing the measured torques or forces; receiving a motion demand signal representing a desired state of the system; implementing an impedance control algorithm in dependence on the motion demand signal and the load signal to form a target signal indicating a target configuration for each of the driven joints; measuring the configuration of each of the driven joints and forming a state signal representing the measured configurations; and forming a set of drive signals for the joints by, for each joint, comparing the target configuration of that joint as indicated by the target signal to the measured configuration of that joint as indicated by the state signal.