The present invention provides a method for robot action imitation learning in a three-dimensional space and a system thereof, relates to the technical fields of artificial intelligence and robots. A method based on a series-parallel multi-layer backpropagation (BP) neural network is designed for robot action imitation learning in a three-dimensional space, which applies an imitation learning mechanism to a robot learning system, under the framework of the imitation learning mechanism, to train and learn by transmitting demonstrative information generated from a mechanical arm to the series-parallel multi-layer BP neural network representing a motion strategy. The correspondence between a state characteristic matrix set of the motion and an action characteristic matrix set of the motion is learned, to reproduce the demonstrative action, and generalize the actions and behaviors, so that when facing different tasks, the method does not need to carry out action planning separately, thereby achieving high intelligence.

A method includes determining motion imitation information for causing a system to imitate a physical task using a first machine learning model that is trained using motion information that represents a performance of the physical task, determining a predicted correction based on the motion information and a current state from the system using a second machine learning model that is trained using the motion information, determining an action to be performed by the system based on the motion imitation information and the predicted correction; and controlling motion of the system in accordance with the action.

A control device includes: first circuitry that generates a command to cause a robot to autonomously grind a grinding target portion; second circuitry that generates a command to cause the robot to grind a grinding target portion according to manipulation information from an operation device; third circuitry that controls operation of the robot according to the command; storage that stores image data of a grinding target portion and operation data of the robot corresponding to the command; and forth circuitry that performs machine learning by using image data of a grinding target portion and the operation data for the grinding target portion, receives the image data as input data, and outputs an operation correspondence command corresponding to the operation data as output data. The first circuitry generates the command, based on the operation correspondence command.

A trajectory plan generation device executes a first search process for searching for a plurality of position candidates which are movement destinations of the tip portion within a predetermined distance from first trajectory information indicating positions and postures of the tip portion between the start point and the end point, a second search process for searching for a plurality of posture candidates of the tip portion that change within an allowable range by spherical interpolation based on postures of the tip portion at the start point and the end point, a determination process for determining second trajectory information indicating positions and postures of movement destinations of the tip portion from the first trajectory information based on the plurality of position candidates searched for by the first search process and the plurality of posture candidates searched for by the second search process, and an output process.

Embodiments of the present disclosure are directed to methods, computer program products, and computer systems of a robotic apparatus with robotic instructions replicating a food preparation recipe. In one embodiment, a robotic control platform, comprises one or more sensors; a mechanical robotic structure including one or more end effectors, and one or more robotic arms; an electronic library database of minimanipulations; a robotic planning module configured for real-time planning and adjustment based at least in part on the sensor data received from the one or more sensors in an electronic multi-stage process file, the electronic multi-stage process recipe file including a sequence of minimanipulations and associated timing data; a robotic interpreter module configured for reading the minimanipulation steps from the minimanipulation library and converting to a machine code; and a robotic execution module configured for executing the minimanipulation steps by the robotic platform to accomplish a functional result.

Embodiments of the present disclosure are directed to methods, computer program products, and computer systems of a robotic apparatus with robotic instructions replicating a food preparation recipe. In one embodiment, a robotic control platform, comprises one or more sensors; a mechanical robotic structure including one or more end effectors, and one or more robotic arms; an electronic library database of minimanipulations; a robotic planning module configured for real-time planning and adjustment based at least in part on the sensor data received from the one or more sensors in an electronic multi-stage process file, the electronic multi-stage process recipe file including a sequence of minimanipulations and associated timing data; a robotic interpreter module configured for reading the minimanipulation steps from the minimanipulation library and converting to a machine code; and a robotic execution module configured for executing the minimanipulation steps by the robotic platform to accomplish a functional result.

A method includes: controlling actuators of a robot manipulator to compensate for influence of gravity; during a manual guidance of the robot manipulator detecting an orientation of an end effector; and controlling at least part of the actuators in such a way that during manual guidance of the end effector, the end effector: within a first range of a first rotation, opposes no or a speed-dependent resistance and outside the first range opposes a rotation angle-dependent resistance to the manual guidance, wherein the first rotation is a rotation angle of the end effector about its longitudinal axis; and within a second range of the second rotation, opposes no or a speed-dependent resistance to the manual guidance, and outside the second range, opposes a deflection-dependent resistance to the manual guidance, wherein the second rotation is a rotational deflection of the end effector from its original longitudinal axis or a vertical axis.

A technique allows efficient registration of an accurate gripping position of a robot hand with an auxiliary view appearing on a screen in accordance with the robot hand. A user selects a hand type to be used in gripping a gripping target and designates an auxiliary view to be rendered in accordance with the hand. In response to a two-finger hand being selected (step S11), a plane (step S13), a cylinder (step S14), or a rectangular prism (step S15) is rendered based on the view designated by the user (step S12). In response to a suction hand being selected, a plane is rendered (step S16).

A conversion device includes: a unit attribute update unit that specifies a unit associated with a representative value approximating a feature vector for a biological signal, and updates a representative value and energy of the specified unit; a unit update unit that, when a plurality of feature vectors outside a predetermined range of a representative value of a unit of the unit data are acquired within a predetermined time, adds data for a new unit identifier to unit data; a class update unit that, when there is no class including a unit having energy within a predetermined range of energy of the new unit, adds data for a new class identifier to class data; and a motion update unit that updates motion data by associating, with an identifier of a class acquired after updating the class data, an identifier of a motion corresponding to the class.

A robot teaching device includes: an image acquisition device configured to acquire, as a moving image, a distance image representing distance information of an imaging object, or a two-dimensional image of the imaging object; a trajectory detection section configured to detect a movement trajectory of an operator's hand depicted as the imaging object in the moving image by using the moving image; an identification section configured to identify whether the detected movement trajectory represents a linear movement or a rotational movement; and a command generation section configured to output a command for translating a predetermined movable part of the robot based on the movement trajectory when the movement trajectory is identified as representing a linear movement, and to output a command for rotating the predetermined movable part based on the movement trajectory when the movement trajectory is identified as representing a rotational movement.