Robert Boschgmbh

Oren Spector

Dotan Di Castro

Vladimir Tchuiev

A method for controlling a robot to perform a task. The method includes acquiring, for each target of a sequence of targets comprising at least one intermediate target of the task and a final target of a task, a target image data element comprising at least one target image from a perspective of an end-effector of the robot at a respective target position of the robot and successively according to the sequence of targets, for each target in the sequence, acquiring, for the target, an origin image data element, supplying the origin image data element and the target image data to a machine learning model configured to derive a delta movement between the origin current position and the target position and controlling the robot to move according to the delta movement.

Device and control method using machine learning for a robot to perform an insertion task

A method for training a neural network to derive, from a force and a moment exerted on an object when pressed on a plane in which an insertion for inserting the object is located, a movement vector to insert an object into an insertion. The method includes, for a plurality of positions in which the object or the part of the object held by the robot touches a plane in which the insertion is located, controlling the robot to move to the position, controlling the robot to press the object onto the plane, measuring the force and moment experienced by the object, scaling the pair of force and moment by a number randomly chosen between zero and a predetermined positive maximum number and labelling the scaled pair by a movement vector between the position and the insertion, and training the neural network using the labelled pairs of force and moment.

Device and method for training a neural network for controlling a robot for an inserting task

A method for training a neural network to derive, from an image of a camera mounted on a robot, a movement vector for the robot to insert an object into an insertion. The method includes controlling the robot to hold the object, bringing the robot into a target position in which the object is inserted in the insertion, for a plurality of positions different from the target position controlling the robot to move away from the target position to the position, taking a camera image by the camera and labelling the camera image by a movement vector to move back from the position to the target position and training the neural network using the labelled camera images.

A method for controlling a robot to perform a task. The method includes acquiring a target image data element comprising at least one target image from a perspective of an end-effector of the robot at a target position of the robot in which the robot has performed the task, acquiring an origin image data element comprising at least one origin image from the perspective of the end-effector of the robot at an origin position of the robot, supplying the origin image data element and the target image data element to a machine learning model configured to derive a delta movement between the origin current position and the target position and controlling the robot to move according to the delta movement to perform the task.

Device and method for controlling a robot to perform a task

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.

Device and method for training a machine learning model to derive a movement vector for a robot from image data

A method for training a neural network to derive, from an image of a camera mounted on a robot, a movement vector to insert an object into an insertion. The method includes, for a plurality of positions in which the object held by the robot touches a plane in which the insertion is located controlling the robot to move to the position, taking a camera image by the camera and labelling the camera image with a movement vector between the position and the insertion in the plane and training the neural network using the labelled camera images.

Growing community of inventors

Modiin Maccabim Reut, Israel

Oren Spector