643results about "Image feed-back" patented technology

New and Improved methods and apparatus for robotic path planning, selection, and visualization are described A path spline visually represents the current trajectory of the robot through a three dimensional space such as a room By altering a graphical representation of the trajectory—the path spline—an operator can visualize the path the robot will take, and is freed from real-time control of the robot Control of the robot is accomplished by periodically updating the path spline such that the newly updated spline represents the new desired path for the robot Also a sensor that may be located on the robot senses the presence of boundaries (obstacles) in the current environment and generates a path that circumnavigates the boundaries while still maintaining motion in the general direction selected by the operator The mathematical form of the path that circumnavigates the boundaries may be a spline

An object picking device, which is inexpensive and capable of speedily and accurately picking one object at a time from a random pile state. A target detecting part of an image processing part processes an image captured by a camera and detects objects. A target selecting part selects an object among the detected objects based on a certain rule. A view line direction calculating part calculates the direction of a view line extending to the selected object. A target position estimating part estimates the position including the height of the selected object based on size information of the object in the image. Then, a grip correction calculating part calculates an amount of correction of the movement of a robot so as to grip the object by using the robot.

An object picking system for picking up, one by one, a plurality of objects. The system includes a detecting section detecting, as an image, an object to be picked, among a plurality of objects placed in a manner as to be at least partially superimposed on each other; a storage section storing appearance information of a predetermined portion of a reference object having an outward appearance identical to an outward appearance of the object to be picked; a determining section determining, in the image of the object to be picked detected by the detecting section, whether an inspected portion of the object to be picked, corresponding to the predetermined portion of the reference object, is concealed by another object, based on the appearance information of the reference object stored in the storage section; a control section deciding a picking motion for the object to be picked and outputting a control signal of the picking motion, based on a determination result of the determining section; and a picking mechanism performing the picking motion on the object to be picked in accordance with the control signal output from the control section.

A work robot for executing a work for operating an object includes a robot body for capturing an image including the object. During a teach mode, the captured image is correlated with an operation content taught by an operator and held. During a work mode, the captured image is acquired, an image similar to the acquired image is searched, and the object is operated according to the operation content correlated with the image captured in the past which has been found as a result of the search.

Described is a robotic visual perception system for determining a position and pose of a three-dimensional object. The system receives an external input to select an object of interest. The system also receives visual input from a sensor of a robotic controller that senses the object of interest. Rotation-invariant shape features and appearance are extracted from the sensed object of interest and a set of object templates. A match is identified between the sensed object of interest and an object template using shape features. The match between the sensed object of interest and the object template is confirmed using appearance features. The sensed object is then identified, and a three-dimensional pose of the sensed object of interest is determined. Based on the determined three-dimensional pose of the sensed object, the robotic controller is used to grasp and manipulate the sensed object of interest.

An object gripping apparatus includes an image capturing unit for capturing a region including a plurality of works, an obtaining unit for obtaining distance information of the region, a measurement unit for measuring three-dimensional positions/orientations of a plurality of gripping-candidate works out of the plurality of works based on the image and distance information, thereby generating three-dimensional position/orientation information, a selection unit for selecting a gripping-target work based on the three-dimensional position/orientation information, a gripping unit for gripping the gripping-target work, and an updating unit for updating the three-dimensional position/orientation information by measuring three-dimensional positions/orientations of the gripping-candidate works at a time interval during gripping of the gripping-target work. When the gripping ends, the next gripping-target work is selected based on the updated three-dimensional position/orientation information of the gripping-candidate works.

A method and system for a robotic device comprising a propulsion mechanism, a sensor for sensing objects, a localization and mapping system, a processing facility comprising a processor and a memory, the processing facility configured to store a set of instructions that, when executed, cause the robotic device to upon selection by a user, place the robotic device in a mapping mode, wherein the mapping mode causes the robotic device to move through the service area and create a digital map, and upon selection by the user, place the robotic device in a service task mode, wherein while in service task mode the robotic device performs a service task in the service area based on sensing the service area with the sensor and utilizing the created digital map.

A method and an apparatus for processing three-dimensional vision measurement data are provided. The method includes: obtaining three-dimensional point cloud data measured by a three-dimensional machine vision measurement system and establishing a visualized space based thereon; establishing a new three-dimensional rectangular coordinate system corresponding to the visualized space, and performing coordinate translation conversion on the three-dimensional point cloud data; determining three basic observation planes corresponding to the visualized space and a rectangular coordinate system corresponding to the basic observation planes; respectively projecting the three-dimensional point cloud data on the basic observation planes to obtain three plane projection functions; respectively generating, according to the three-dimensional point cloud data, three depth value functions corresponding to the plane projection functions; digitally processing three plane projection graphs and three depth graphs respectively, and converting same to two-dimensional images of a specified format; and compressing, storing and displaying the two-dimensional images of the specified format.

The invention provides a target positioning method based on a RGBD, and the main steps comprise hardware environment arrangement and device initialization; the RGBD sensor is adopted to acquire depth data and color image of a mobile robot in current frame, a depth image is segmented based on the depth data to obtain a target region in the depth image, the target image is set as SearchRect_depth and is mapped to the color image, and the corresponding color image part is recorded as SearchRectROI; in the color image SearchRectROI, a CAMSHIFT method is utilized to calculate a position (x, y) of a target in the color image; the depth data is combined to calculate world coordinates (xw, yw, zw) of the current target; the world coordinates (xw, yw, zw) of the current target is transmitted to the mobile robot through a communication system, and the robot can control its self motion. According to the invention, the method has advantage of fast calculation speed, accurate positioning, strong adaptability for environment change and good expandability for different targets.

The invention belongs to the technical field of automatic welding, and provides an intelligent three-dimensional weld joint autonomous tracking method which comprises the following steps: S1, camera calibration: a camera shoots and acquires image information of calibration plates at different spatial positions, establishes a corresponding equation set according to the shot image information, and obtains an internal parameter matrix and an external parameter matrix through analysis; s2, line laser plane calibration; s3, hand-eye calibration; s4, determination of a welding seam starting point and a welding seam ending point; and s5, welding seam track planning. According to the intelligent three-dimensional autonomous welding seam tracing method, any type of weld grooves is identified by utilizing an image algorithm; a linear laser triangulation method and a vision and robot calibration algorithm are adopted to autonomously plan a motion path, so that autonomous tracking of a welding line in any three-dimensional space is realized, three-dimensional orientation information of a welding line groove is obtained, and tracking of a right-angle or acute-angle inflection point is realized in a self-adaptive pre-swing manner.

The invention, which relates to the field of metering equipment employing an optical method as a feature, provides a machine vision positioning method for automatic screw assembling. The method comprises steps of inputting and recording data, obtaining an image, carrying out image pretreatment, carrying out Hough transform treatment, calibrating a camera, and calculating a position. According to the method, a circle in an image is searched by using the Hough transform method and the center of the circle is used as a positioning point, so that defects of high selection requirement and low precision for feature point selection according to the existing visual positioning method can be overcome; and a defect of an assembling failure caused by inaccurate product position fixation by a clamp during the automatic screw assembling process in the prior art can be overcome.

The invention discloses a welding seam tracking system and a welding seam tracking method. The welding seam tracking system comprises a vision sensing device, a bracket, a welding gun, a movement mechanism, a computer and a baffle, wherein the vision sensing device comprises a spot laser, a line laser and an area-array camera; the area-array camera collects images and transmits the collected images to the computer; the computer gives a command to control the movement mechanism to move in three-dimensional directions, so that during the welding process, the height of the welding gun can be automatically adjusted by monitoring the altitude changes of the workpiece surface. According to the welding seam tracking system and the welding seam tracking method, the welding seam height recognition tracking method and the welding gun adjusting method which are integrated based on the dot and line lasers is firstly adopted, the tracking method has a better adaptability to various working conditions, the limitation of the tracking method in the prior art is overcome, the response speed of the method is high, the altitude changes of the workpiece surface can be accurately identified, the accuracy is high, and the welding seam tracking can be completed high efficiently.

Provided is a process that includes training a computer-vision object recognition model with a training data set including images depicting objects, each image being labeled with an object identifier of the corresponding object; obtaining a new image; determining a similarity between the new image and an image from the training data set with the trained computer-vision object recognition model; and causing the object identifier of the object to be stored in association with the new image, visual features extracted from the new image, or both.

The invention relates to a visual-servo-based screw hole locating and screw locking-removing method. A screw hole is located and a screw is locked and removed through a visual-servo-based screw hole locating and screw locking-removing device. The position information and pose information of the target screw hole or screw are obtained through a visual measuring module of the visual-servo-based screw hole locating and screw locking-removing device. Screw hole locating and screw locking and removing are controlled to be performed through a control performing module of the visual-servo-based screwhole locating and screw locking-removing device. Through the visual-servo-based screw hole locating and screw locking-removing method, locating precision of the screw can be improved to a large extent. A mechanical arm is used as a moving carrier, the work range is increased, and locking and removing work of the screw can also be conducted in an environment to which a worker cannot go conveniently. A point-to-surface screw or screw hole locating method is provided.

The presence range for workpieces (the internal edge of a container's opening) is defined with a visual sensor attached to a robot and the range is divided into a specified number of sectional regions. A robot position suitable for sensing each of the sectional regions is determined, and sensing is performed at the position so that workpieces in the container are picked up.

The invention provides an automatic tracking method of a double-foot robot. The method includes: a vision sensor arranged on the double-foot robot sends navigation path image information under the feet of the robot to a processor; the processor processes the received navigation path image information, obtains a relative position relation between a current attitude of the robot and a navigation path, and sends the relation to a controller, wherein the relative position relation includes an angle deviation and a position deviation; and the controller controls the robot to adjust the walking pathto realize automatic tracking according to the received angle deviation and the position deviation. According to the method, the navigation path image information acquired by the robot is sent through the vision sensor; graying, mean filtering, the Canny edge detection algorithm and extraction of path edge coordinates are performed on the image to obtain path information, and the accuracy of thepath information is improved through interval scanning; in path recognition, a slope matching method is proposed for a cross path to select an optimal forward path; and therefore, good timeliness andanti-interference capability are achieved.

The invention provides a robot charging docking system based on pattern recognition. The system comprises a robot and a charging post. The charging post is provided with a charging recognition pattern. The robot is provided with a camera and a central control device. The central control device is used to process an image photographed by the camera to recognize the charging recognition pattern, determine the distance and angle between the robot and the charging post according to the charging recognition pattern, and controls the robot to move toward the charging post. The robot charging docking system provided by the invention allows the large robot to automatically charge with high degree of autonomy and reliability. The invention further provides a robot charging docking method based on pattern recognition.