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 grasping system includes a robotic arm having a gripper. A fixed sensor monitors a grasp area and an onboard sensor moves with the gripper also monitors the area. A controller receives information indicative of a position of an object to be grasped and operates the robotic arm to bring the gripper into a grasp position adjacent the object based on information provided by the fixed sensor. The controller is also programmed to operate the gripper to grasp the object in response to information provided by the first onboard sensor.

Control systems and methods for operating a robot are disclosed. The control system includes a robot comprising a fixed end and a manipulator movable relative to the fixed end. The robot is configured to move an elongated tool attached to an end effector of the manipulator within a robot space for aligning the elongated tool with an occluded target, wherein the robot space comprises a 3-dimensional (3D) space with the fixed end as a center. The control system further includes a processor communicatively coupled with the robot and a 3D imaging device. The 3D imaging device is configured to capture 3D images within an imaging space, wherein the imaging space comprises a 3D space with a fixed reference point on the 3D imaging device as a center. The processor is configured to process a preliminary 3D image of the end effector captured by the 3D imaging device to calibrate the robot by integrating the robot space with the imaging space. The processor is further configured to, based on the calibration of the robot, process a 3D image of a body containing the target captured by the 3D imaging device to obtain location data of the target in the integrated space. The processor is further configured to, based on the location data of the target in the integrated space, automatically control the manipulator to align a longitudinal axis of the elongated tool with the target.

A pallet building apparatus for automatically building a pallet load of pallet load article units onto a pallet support including a frame defining a pallet building base, at least one articulated robot to transport and place the pallet load article units, a controller to control articulated robot motion and effect therewith a pallet load build, at least one three-dimensional, time of flight, camera to generate three-dimensional imaging of the pallet support and pallet load build, wherein the controller registers, from the three-dimensional camera, real time three-dimensional imaging data embodying different corresponding three-dimensional images of the pallet support and pallet load build, to determine, in real time, from the corresponding real time three-dimensional imaging data, a pallet support variance or article unit variance and generate in real time an articulated robot motion signal, the articulated robot motion signal being generated real time so as to be performed real time.

Control systems and methods for operating a robot are disclosed. The control system includes a robot comprising a fixed end and a manipulator movable relative to the fixed end. The robot is configured to move an elongated tool attached to an end effector of the manipulator within a robot space for aligning the elongated tool with an occluded target, wherein the robot space comprises a 3-dimensional (3D) space with the fixed end as a center. The control system further includes a processor communicatively coupled with the robot and a 3D imaging device. The 3D imaging device is configured to capture 3D images within an imaging space, wherein the imaging space comprises a 3D space with a fixed reference point on the 3D imaging device as a center. The processor is configured to process a preliminary 3D image of the end effector captured by the 3D imaging device to calibrate the robot by integrating the robot space with the imaging space. The processor is further configured to, based on the calibration of the robot, process a 3D image of a body containing the target captured by the 3D imaging device to obtain location data of the target in the integrated space. The processor is further configured to, based on the location data of the target in the integrated space, automatically control the manipulator to align a longitudinal axis of the elongated tool with the target.

There is provided an information processing apparatus to estimate a position of a distal end of a movable unit with a reduced processing load, the information processing including a position computer that computes, on the basis of first positional information obtained from reading of a projected marker by a first visual sensor and second positional information including positional information obtained from reading of the marker by a second visual sensor that moves relative to the first visual sensor, a position of a movable unit in which the second visual sensor is disposed. This makes it possible to estimate the position of the distal end of the movable unit with a reduced processing load.

A machine learning device and a machine learning method are provided. A controller, which serves as the machine learning device and the machine learning method, is provided to perform machine learning of algorithms for arranging a flexible wire-like workpiece to a predetermined state using an industrial robot. In an embodiment, the machine learning device includes: an acquisition unit that acquires, as state variables, a state of the workpiece before arrangement starts and a state of the workpiece during arrangement; and a learning unit that performs machine learning of an algorithm for arranging the workpiece based on the state variables acquired by the acquisition unit.

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.

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 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.