Various gripped objects having different sizes, weights, centers of gravity, and the like are continuously and stably moved at a high speed. A control device includes: a state information generation unit that generates and updates state information on a robot and a gripped object; and a control information generation unit that generates, based on the state information and a base trajectory generated in advance on which the robot is configured to move the gripped object from a start point to an end point, control information for controlling the robot.

A robot device, a method for training a robot control model, and a method for controlling a robot device. The method for training includes: supplying an image showing object(s), to a first and second prediction model to produce a first and second pickup prediction that has, for each pixel of the image, a first and second pickup robot configuration vector with an assigned first and second success probability; supplying the first and second pickup prediction to a blending model of the robot control model to produce a third pickup prediction that has, for each pixel of the image: a third pickup robot configuration vector that is a weighted combination of the first and second pickup robot configuration vector, and a third success probability that is a weighted combination of the first and second success probability; and training the robot control model by adapting the first and second weighting factors.

Provided is an alimentary-product assembling and dispensing device comprising: a plurality of alimentary-ingredient dispensers positioned to dispense respective ingredients in a plurality of different locations of a robotic work environment; a robot configured to receive an open-top vessel from an open-top-vessel dispenser and move the open-top vessel to the different locations to receive different ingredients from the plurality of alimentary-ingredient dispensers, wherein the robot comprises four or fewer degrees of freedom; and a vending aperture through which consumers retrieve vended alimentary products assembled by the robot from ingredients dispensed from the plurality of alimentary-ingredient dispensers.

The disclosure provides a gripping position determination device, a gripping position determination system, a gripping position determination method, and a recording medium. The gripping position determination device for a robot hand having a plurality of multi joint fingers includes: a frictional force distribution calculation part estimating, from a predictive control of a gripping force when an object is gripped by at least two fingers, a frictional force between one of the gripping fingers and the object, and calculates a frictional force distribution where grapping of the object is possible on a surface of the object based on a value related to a frictional force calculated by using the estimated frictional force; a grippable region selection part selecting, from the frictional force distribution, at least one grippable region; and a gripping position calculation part calculating, from the selected grippable region, a gripping position where stable gripping of the object is possible.

A system and methods are disclosed for precision placement or insertion of an object using robotic manipulation. A robotic tool includes at least three members, including a first member and a second member that grip the object between opposing faces and a third member that exerts a force on a proximate end of the object to push the object out of the robotic tool. A series of maneuvers is performed with the robotic tool in order to place the object on a surface or insert the object in a hole. The maneuvers include positioning the object against the surface, rotating the object around a contact point between the object and the surface, rotating the robotic tool around a contact point between the object and either the first or second member of the robotic tool, sliding the object horizontally along a surface, and tucking the object into a final desired position.

A robot system includes a robot main body, a plurality of first control devices provided in the robot main body, and a detection unit configured to detect a state of the robot main body. In a case where one of the plurality of first control devices determines that the robot main body is in a predetermined state based on a detection result of the detection unit, the one of the plurality of first control devices outputs information indicating that the robot main body is in the predetermined state to another one of the plurality of first control devices other than the one of the plurality of first control devices.

The present invention relates to systems and methods for accounting for edge cases (i.e. tail data) in automated decision making systems, for example automated robotic picking systems. The systems and methods provide for retraining machine learning (ML) models so that the edge cases can be handled in a manner that requires less (or no) human intervention. The disclosed systems and methods create updated ML models, replacement ML models, and/or supplementary ML models that can provide better performance (e.g. improved automated robotic picking) when edge cases are encountered. Furthermore, the present inventions disclose systems and methods for obtaining training data faster and in a more cost effective manner, which enables the systems and methods disclosed herein to update models at a faster rate, thereby enabling broader, system-wide handling of edge cases in a more effective and efficient manner.

In a robot (industrial robot) system, a robot holds a workpiece by pinching the workpiece between movable claws. A controller, which controls the robot, includes a host controller that controls the robot to perform a positioning operation for positioning the hand to a grip position and a gripping operation for displacing each of the movable claws toward each other at the grip position. In the controller, a machine learning device acquires stop reference data set for gripping of the workpiece, distance data indicating a distance between each of the movable claws of the hand positioned at the grip position and the workpiece, and comparison data indicating a deformation amount of the workpiece before and after the gripping operation. The machine learning device performs machine learning using such acquired data, resulting in constructing a model used for setting an operation mode of the gripping operation.

Exemplary embodiments relate to user-assisted robotic control systems, user interfaces for remote control of robotic systems, vision systems in robotic control systems, and modular grippers for use by robotic systems. The systems, methods, apparatuses and computer-readable media instructions described interact with and control robotic systems, in particular pick and place systems using soft robotic actuators to grasp, move and release target objects.

A picking apparatus in an embodiment includes: a gripper, an arm, a detector, and a control unit. The gripper picks and grips an object to be conveyed. The arm moves the gripper and causes the gripper to convey the object to be conveyed. The detector is attached to the arm and senses a force applied to the gripper. The control unit controls an operation of the gripper and the arm. The control unit includes a calculator and a subtractor. The calculator calculates a gravitational force and an inertial force applied to the gripper when the gripper grips and moves the object to be conveyed using an arithmetic expression including a coefficient determined in accordance with a mass of the object to be conveyed. The subtractor subtracts the gravitational force and the inertial force calculated by the calculator from a force applied to the gripper sensed by the detector.