A robot control apparatus for controlling a robot manipulating a target object includes a measurement unit configured to measure a change of a gripping unit configured to grip the target object when the gripping unit contacts the target object, a first acquisition unit configured to acquire the change of the gripping unit measured by the measurement unit, a second acquisition unit configured to acquire a gripping state, which is a state of gripping of the target object by the gripping unit, based on the change of the gripping unit acquired by the first acquisition unit, and a control unit configured to control an action of the robot based on the gripping state acquired by the second acquisition unit.

A learning method is performed by a computers The method includes: receiving a first image that includes an object; generating a first rectangle in the first image, the first rectangle including therein a figure, that is set in advance to have a first inclination and that represents a gripping position of an object, and having a side parallel to a first direction; inputting the first image to a model, which outputs, from the input image, a rectangle parallel to the first direction and an inclination, to cause the model to output a second rectangle and a second inclination; and updating the model such that errors of the second rectangle and the second inclination with respect to the first rectangle and the first inclination respectively decrease.

A non-transitory computer-readable storage medium storing a position detection program which causes a processor to perform processing for object recognition, the processing includes: acquiring a plurality of pieces of three-dimensional data of simple shapes that are not similar to each other; carrying out learning by using the plurality of acquired pieces of data; acquiring an image obtained by imaging by an imaging unit; and detecting a position of an object from the acquired image by using a first learning model generated based on the learning.

A learning method is performed by a computer. The method includes: inputting a first image to a model, which outputs, from an input image, candidates for a specific region and confidences indicating probabilities of the respective candidates being the specific region, to cause the model to output a plurality of candidates for the specific region and confidences for the respective candidates; calculating a first value for each of candidates whose confidences do not satisfy a certain criterion among the candidates output by the model, the first value increasing as the confidence increases; calculating a second value obtained by weighting the first value such that the second value decreases as the confidence increases; and updating the model such that the second value decreases.

Disclosed is a system having a robotic welding system, a controller, a camera, and a processor. The robotic welding system is configured to weld metal sections together in accordance with a plurality of welding variables. The controller is configured to automatically control the robotic welding system. The camera captures sequential images of the welding performed by the robotic welding system. According to an embodiment, the processor is configured to process the sequential images to determine when a selected welding state is to change to a next welding state based on the selected welding state and multiple consistent determinations of the next welding state, and to signal that change to the controller to effect a change in how the welding is performed by the robotic welding system. By considering multiple consistent determinations of the next welding state, there can be a high probability that the next welding state is correct.

Embodiments of the present disclosure relates to an electronic device, a vision-based operation method and system for a robot. The electronic device includes at least one processing unit; and a memory coupled to the at least one processing unit and storing computer program instructions therein, the instructions, when executed by the at least one processing unit, causing the electronic device to perform acts including: obtaining an image containing a tool of a robot and an object to be operated by the tool, the image being captured by a camera with a parameter, obtaining a command for operating the tool, the command generated based on the image; and controlling the robot based on the command and the parameter. Embodiments of the present disclosure can greatly improve the accuracy, efficiency and safety of an operation of a robot.

A robot system is provided that includes a base, an articulable arm, a visual acquisition unit, and at least one processor. The articulable arm extends from the base and is configured to be moved toward a target. The visual acquisition unit is mounted to the arm or the base, and acquires environmental information. The at least one processor is operably coupled to the arm and the visual acquisition unit, the at least one processor configured to: generate an environmental model using the environmental information; select, from a plurality of planning schemes, using the environmental model, at least one planning scheme to translate the arm toward the target; plan movement of the arm toward the target using the selected at least one planning scheme; and control movement of the arm toward the target using the at least one selected planning scheme.

The present method for moving a tip of a line-like object is a method for moving a tip of a line-like object grasped by a robot hand to a target position, the method including: measuring a position of the tip of the line-like object grasped by the robot hand; and moving the tip to the target position based on the measured position of the tip.

An image inspecting apparatus includes at least one image capturing part, a lighting part, a control part including a moving part, a searching part analyzing an image captured by the image capturing part under a first image capturing condition and searching for a defect candidate from an object under inspection, and a determining part. When the searching part finds the defect candidate from the object under inspection, the control part controls an image capturing condition such that a part where the defect candidate is found by the searching part is photographed under a second image capturing condition that is clearer than the first image capturing condition. The determining part analyzes an image captured by the image capturing part under the second image capturing condition and determines whether the defect of the object under inspection is present or absent.

A control apparatus, comprising: an image obtaining unit configured to obtain an image in which a control target that a robot controls and a target position to which the control target is to be moved are imaged by an imaging apparatus that is attached to the robot; an axial direction obtainment unit configured to obtain an axial direction of a rotational axis of the control target; a target position detection unit configured to detect the target position in the image; an operation generation unit configured to generate an operation for the control target so that the target position is present in the axial direction and to further generate an operation by which the control target becomes closer to the target position in the axial direction; and a control unit configured to control the control target in accordance with the operation.