A method includes accessing RGB and depth image data representing a scene that includes at least a portion of a robotic limb. Using this data, a computing system may segment the image data to isolate and identify at least a portion of the robotic limb within the scene. The computing system can determine a current pose of the robotic limb within the scene based on the image data, joint data, or a 3D virtual model of the robotic limb. The computing system may then determine a desired goal pose, which may be based on the image data or the 3D virtual model. Based on the determined goal pose, the computing device determines the difference between the current pose and the goal pose of the robotic limb, and using this difference, provides a pose adjustment that for the robotic limb.

A wearable apparatus for assisting muscular strength includes: a main body mechanism extending in a vertical direction of a wearer's torso, and being fixed to a side of a wearer's torso under a wearer's shoulder; a fastening mechanism extending along an extension direction of a wearer's upper arm, and being disposed at and being in contact with a lower surface of the wearer's upper arm; a connecting mechanism having a first end coupled to the fastening mechanism and a second end movably coupled to the main body mechanism so as to be movable with respect to the main body mechanism; and a support mechanism movably coupled between the first end and the second end of the connecting mechanism to apply a support force to the connecting mechanism, and coupled to the main body mechanism and movable with respect thereto.

A robot includes an arm, one or more visual sensors provided on the arm, a storage unit that stores a first feature value regarding at least a position and an orientation of a following target, the first feature value being stored as target data for causing the visual sensors provided on the arm to follow the following target, a feature value detection unit that detects a second feature value regarding at least a current position and a current orientation of the following target, the second feature value being detected using an image obtained by the visual sensors, a movement amount calculation unit that calculates a movement command for the arm based on a difference between the second feature value and the first feature value, and a movement command unit that moves the arm based on the movement command.

A component mounting robot system includes a component transfer robot which transfers a mounting component including a mounting portion to a base component's mounting position; and a jig which corrects the mounting portion's position of the mounting component transferred by the component transfer robot to mounting position, wherein the jig includes a guide portion which corrects the mounting portion's position of the mounting component to the mounting position, and wherein the component transfer robot includes a holding section which holds the mounting component so that a posture of the mounting component is changeable. In this configuration, it becomes possible to construct the component mounting robot system which can correct position of the mounting portion of the mounting component, by changing the posture of the body of the mounting component and guiding the mounting portion to the mounting position even in a case where the mounting component has a cylindrical shape.

The application relates to a smart cabinet. The smart cabinet includes a cabinet body, a moving module, a controlling module and an assisting module. The moving module is positioned in the cabinet body; the controlling module is connected to the moving module. The moving module includes a base, a guiding wheel group disposed on the base, a plurality of drivers pivotally connected with the guiding wheel group, and a manipulator disposed on the base. The controlling module includes an input control unit, a guiding rope, and a pulley group. The input control module is electrically connected with the drivers and the manipulator. The pulley group includes a plurality of pulleys defining a movement range for the moving module. The assisting module includes a rope retractor and a sensor electrically coupled to the rope retractor. Two ends of the guiding rope are coupled to the rope retractor.

A robotic system and method for aligning a target to an equipped vehicle for calibration of a sensor on the equipped vehicle includes a vehicle support stand upon which an equipped vehicle is disposed in an established known position for calibration of the sensor, and a robotic manipulator having a multi-axis robotic arm configured to moveably hold a target. The robotic manipulator is configured to position the target into a calibration position relative to the sensor on the equipped vehicle by longitudinal movement of the robotic manipulator relative to the vehicle support stand and by movement of the robotic arm based on the established known position of the equipped vehicle on the vehicle support stand whereby the sensor is able to be calibrated using the target.

Systems and methods are disclosed for determining tool offset data for a tool attached to a robot at an attachment point. In an embodiment, a method includes controlling the robot to contact a reference object with the tool. The reference object is a rigid object with a known location. A force feedback sensor of the robot indicates when the tool has contacted the reference object. Once contact is made, data indicating robot position during tool contact is received. Additionally, the robot temporarily stops movement of the tool to prevent damage to the tool or the reference object. Next, tool offset data is determined based on the position of the reference object relative to the robot and the received robot position data. The tool offset data describes the distance between at least one point on the tool and the attachment point.

In a method for correcting a target position, a three-dimensional matrix is formed by piling up, in a Z-direction at predetermined intervals, matrix planes each formed by continuously connecting, in X- and Y-directions, quadrangular areas that are parallel to an XY-plane and each have a reference point, and a target position of a work robot designated in an operation space of the three-dimensional matrix is corrected. In this method, a first block and a second block are set which are individually contiguous with the specific block, and the target position is corrected based on respective reference points in the upper area and the lower area of the specific block, the first block, and the second block and the measured deviation amount of the work robot from the reference points.

An automatic alignment system of a robot manipulator is provided. The automatic alignment system includes a signal transmission module and a controller. The signal transmission module includes a first signal receiving and transmitting element and a second signal receiving and transmitting element. The first signal receiving and transmitting element is mounted on the robot manipulator. The second signal receiving and transmitting element is disposed neighboring to a target workpiece. A signal is transported between the signal receiving and transmitting elements. The controller is electrically connected with the signal transmission module for receiving the signal outputted from the signal transmission module. The controller acquires a relative position between the first signal receiving and transmitting element and the second signal receiving and transmitting element according to a variation in the signal. The controller controls the robot manipulator to be automatically aligned to the target workpiece in accordance with the relative position.

Method and apparatus for automated operations, such as pruning, harvesting, spraying and/or maintenance, on plants, and particularly plants with foliage having features on many length scales or a wide spectrum of length scales, such as female flower buds of the marijuana plant. The invention utilizes a convolutional neural network for image segmentation classification and/or the determination of features. The foliage is imaged stereoscopically to produce a three-dimensional surface image, a first neural network determines regions to be operated on, and a second neural network determines how an operation tool operates on the foliage. For pruning of resinous foliage the cutting tool is heated or cooled to avoid having the resins make the cutting tool inoperable.