A visual positioning system, comprising a first visual sensor (501), a second visual sensor (502), and a position obtaining unit (503), wherein the first visual sensor (501) is used for obtaining a first image (G11) of a first position (A) of a target apparatus (7), a second visual sensor (502) is used for obtaining a second image of a second position (B) of the target apparatus (7), and the position obtaining unit (503) is used for obtaining position information of the target apparatus (7) according to the first image (G11) and the second image. Further disclosed are a battery swapping device and a battery swapping control method. Relatively high positioning accuracy is obtained in a visual manner, and accurate positioning between the battery swapping device and a vehicle for battery swap is implemented.

Provided are an odor sniffing device (11) and a vehicle-mounted security inspection apparatus for a container (1). The odor sniffing device (11) includes a primary sampling front end (116), which has a vent adapter (116-1) having a shape matching with a vent of the ventilator of the container, so that when the primary sampling front end (116) fits with the ventilator, the vent adapter (116-1) and the vent generally cooperate to achieve fluid communication. The vehicle-mounted security inspection apparatus (1) may perform imaging inspection and chemical inspection simultaneously.

A robot and a method of capturing an image applied to the robot, an electronic device for implementing the method of capturing the image, and a computer-readable storage medium are provided. The robot includes: a robot body; a workbench; a telescopic structure having one end pivotally connected to the robot body and the other end connected to the workbench; a driving mechanism arranged on the robot body and configured to drive the telescopic structure to extend, retract and/or move relative to the robot body; and an image capture device arranged on the workbench. The telescopic structure is configured to allow the image capture device to capture an image of a target object from different angles with the extension, retraction and/or movement of the telescopic structure.

A fenceless system and method for automatically moving one or more items between a structure at a source location and a destination using a robot is provided. The system comprises a robot having an end effector to selectively grasp an item. A trajectory planning controller directs the robot to move the item between a source location and a destination. A touch sensor detects a contact between an external object and a surface of the robot or a surface surrounding the end effector; and a proximity sensor detects a person in proximity to the robot. A vision sensor detects a location and orientation of items to be moved. The robot moves in proximity to a person without a safety fence preventing the person from contacting the robot. The system adjusts a speed of the robot in response to detecting a person in one of a plurality of zones around the robot.

A parts supply device includes a stage having a placement surface on which a plurality of parts is placed, an imaging system configured to image the plurality of parts from an obliquely upward direction with respect to the placement surface of the stage, and a parts detection unit configured to detect positions and orientations of the plurality of parts on the placement surface of the stage based on image information obtained by the imaging system.

A learning dataset generation device includes: a memory that stores three-dimensional CAD data of a workpiece and a container; and one or more processors including hardware, wherein the one or more processors are configured to use the three-dimensional CAD data of the workpiece and the container, stored in the memory, to generate, in a three-dimensional virtual space, a plurality of imaging objects in which a plurality of the workpieces are bulk-loaded in different forms inside the container, acquire a plurality of virtual distance images by measuring each of the generated imaging objects by means of a virtual three-dimensional measurement machine disposed in the three-dimensional virtual space, accept at least one teaching position for each of the acquired virtual distance images, and generate a learning dataset by associating the accepted teaching position with each of the virtual distance images.

A robot system according to an embodiment includes an arm mechanism that is articulated, a parallel link mechanism, an end effector, a detector, and a control device. The parallel link mechanism includes a fixed part mounted to a distal part of the arm mechanism, and a movable part that is mounted to the fixed part via multiple parallel links and is movable with respect to the fixed part. The end effector is mounted to the movable part. The detector is provided for detecting a position or orientation of a control point. The control device controls the arm mechanism and the parallel link mechanism. The control device performs a first operation of setting a posture of the control point to a first posture, and a second operation of setting the posture of the control point to a task posture in which the end effector performs a task.

An apparatus for correcting a process error includes: a frame; a machining unit formed inside or outside the frame with respect to the frame and performing a predetermined process; a conveying unit formed inside or outside the frame with respect to the frame and performing predetermined conveying; a sensing mark formed on the frame, the machining unit, or the conveying unit; an imaging unit formed inside or outside the frame and creating an original image by imaging the sensing mark; and a measuring unit deriving a 3D position variation value of the frame, the machining unit, or the conveying unit by deriving an image variation value of the sensing mark by analyzing the original image transmitted from the imaging unit imaging the sensing mark formed on the frame, the machining unit, or the conveying unit.

An estimation device includes a memory and at least one processor. The at least one processor is configured to acquire information regarding a target object. The at least one processor is configured to estimate information regarding a location and a posture of a gripper relating to where the gripper is able to grasp the target object. The estimation is based on an output of a neural model having as an input the information regarding the target object. The estimated information regarding the posture includes information capable of expressing a rotation angle around a plurality of axes.

A robot system includes a robot for performing predetermined processing to a treating object, a photographing device for photographing the treating object, a robot control device for performing position compensation of a moving destination of the robot so as to track the treating object, on a basis of previously-set information on positions of the robot, the photographing device and the treating object, and an image of the treating object photographed by the photographing device, and a display device for providing an AR space. The robot control device calculates a position of the photographing device on the basis of the information on the positions of the robot and the photographing device. The display device displays an image imitating the photographing device at a corresponding position in the AR space, on a basis of the calculated position of the photographing device.