A method for controlling a robot to pick up an object in various positions. The method includes: defining a plurality of reference points on the object; mapping a first camera image of the object in a known position onto a first descriptor image; identifying the descriptors of the reference points from the first descriptor image; mapping a second camera image of the object in an unknown position onto a second descriptor image; searching the identified descriptors of the reference points in the second descriptor image; ascertaining the positions of the reference points in the three-dimensional space in the unknown position from the found positions; and ascertaining a pickup pose of the object for the unknown position from the ascertained positions of the reference points.

A robot control method is executed in a control device connected to a robot that performs a work on a work object and a sensor mounted on the robot. First, environmental information indicating a peripheral environment of the robot is calculated based on a plurality of pieces of environment sensor information acquired for the peripheral environment by using the sensor at a plurality of positions and angles. Subsequently, first sensor information is acquired by the sensor, and a first step of calculating first control information causing the robot to approach a work goal based on work goal information indicating the work goal, the environmental information, and the first sensor information is executed. Second sensor information is acquired by the sensor, and a second step of calculating second control information causing the robot to approach the work goal based on the work goal information and the second sensor information is executed.

Disclosed herein is a robot arm control system of an automated medication dispensing apparatus, which includes a robot arm; a storage configured to store a mounting position of each of a plurality of medication cassettes, an operation control value of the robot arm for moving to the mounting position, and a reference position at which the marker is attached to each medication cassette in a medication cassette storage unit where a plurality of racks in which the plurality of medication cassettes with markers attached thereto are mounted are arranged; a camera configured to capture the marker attached to the medication cassette; and a control unit configured to control the robot arm to move to a mounting position of any one among the medication cassettes to unload the medication cassette.

A control system for a hand that is connectable to a robot arm and has a tip of which shape is deformable, includes an image acquisition unit that acquires an image of the hand, and a controller that detects at least one specific deformed shape of the hand based on the image acquired by the image acquisition unit, and performs a control on at least one of the hand and the robot arm according to the at least one specific deformed shape detected.

A system and method for motion planning is presented. The system is configured, when an object is or has been in a camera field of view of a camera, to receive first image information that is generated when the camera has a first camera pose. The system is further configured to determine, based on the first image information, a first estimate of the object structure, and to identify, based on the first estimate of the object structure or based on the first image information, an object corner. The system is further configured to cause an end effector apparatus to move the camera to a second camera pose, and to receive second image information for representing the object's structure. The system is configured to determine a second estimate of the object's structure based on the second image information, and to generate a motion plan based on at least the second estimate.

A robot system that performs work of coupling a flexible cable to a connector provided on a board, includes a robot in which a gripping unit that grips the cable and a force detection unit that detects a force acting on the gripping unit are provided, a control unit that controls the robot to perform a conveyance action to grip the cable using the gripping unit and convey the cable onto the board, and an insertion action to insert the cable into the connector by force control based on a detection result in the force detection unit, an insertion speed entry part in which an insertion speed of the cable into the connector at the insertion action is entered, and a determination unit that can determine force control information necessary for the force control in the insertion action according to the insertion speed.

A system and method for motion planning is presented. The system is configured, when an object is or has been in a camera field of view of a camera, to receive first image information that is generated when the camera has a first camera pose. The system is further configured to determine, based on the first image information, a first estimate of the object structure, and to identify, based on the first estimate of the object structure or based on the first image information, an object corner. The system is further configured to cause an end effector apparatus to move the camera to a second camera pose, and to receive second image information for representing the object's structure. The system is configured to determine a second estimate of the object's structure based on the second image information, and to generate a motion plan based on at least the second estimate.

Provided are a robot system and a control method with which it is possible to highly precisely acquire the thickness of an object. This robot system comprises an imaging unit that is mounted on a robot and that captures a two-dimensional image of an object, an image processing unit that acquires distance information pertaining to the object on the basis of the two-dimensional image, a distance image generation unit that generates a distance image on the basis of the distance information, and a thickness calculation unit that calculates the thickness of the object on the basis of the distance image, the imaging unit capturing the two-dimensional image of the object irrespective of the positional relationship between the side surface of the object and the imaging unit.

A method for training a machine learning model to derive a movement vector for a robot from image data. The method includes acquiring images from a perspective of an end-effector of the robot, forming training image data elements from the acquired images, generating augmentations of the training image data elements, training an encoder network using contrastive loss and training a neural network to reduce a loss between movement vectors output by the neural network in response to embedding outputs provided by the encoder network and respective ground truth movement vectors.

Provided are systems and method for automated handling of one or more objects.