332 results about "Visually guided" patented technology

A system and method for creating an integrated digital media management and reproduction device comprised of a database with key data values for a plurality of records, and a module with search controls that include sets of compound parallel attribute queries that can execute instructions for a data category, and concurrently retrieve and display records across a plurality of related categories—thereby revealing the associations between discrete records. The invention also has a plurality of software instantiated media players which, through instructions managed by a “master container” design, function as if they were dynamically aware of user actions and the quantifiable states of each other player object—and respond according to logic rules, visually guiding event workflow. The system has a memory module for storing query information, a processor configured to retrieve data, a display unit for retrieved data and a digital-to-analog converter for providing capability for connection to loudspeakers.

A method of visually guiding a pilot flying an aircraft using one or more conformal symbols whose position is dynamically updated throughout the guidance is provided herein. The method includes the following stages: determining a desired flight route of an aircraft, based on a user-selected maneuver; presenting to a pilot, on a display, at least one 3D visual symbol that is: (i) earth-space stabilized, and (ii) positioned along a future location along the desired route; computing an updated desired route based on repeatedly updated aircraft flight data that include at least one of: location, speed, and spatial angle, of the aircraft; and repeating the presenting of the at least one 3D visual symbol with its updated location along the updated desired route.

The present invention relates to an automatic guide method of intelligent industrial transportation vehicle and electric vehicle adopting said automatic guide method. The visual guide method of automatic guide vehicle controlled by computer is characterized by that the camera mounted on the automatic guide vehicle can be used for shooting the running path mark line on the pavement, station address code identifier and running state control identifier, and the computer connected with the camera can utilize image intellectualized identification to obtain the position deviation and direction deviation parameters of the vehicle body and running path mark line and station address and running state control information to give out correspondent control signal to wheel drive mechanism controller to implement automatic guide control of the automatic guide vehicle.

A robotic fruit picking system includes an autonomous robot that includes a positioning subsystem that enables autonomous positioning of the robot using a computer vision guidance system. The robot also includes at least one picking arm and at least one picking head, or other type of end effector, mounted on each picking arm to either cut a stem or branch for a specific fruit or bunch of fruits or pluck that fruit or bunch. A computer vision subsystem analyses images of the fruit to be picked or stored and a control subsystem is programmed with or learns picking strategies using machine learning techniques. A quality control (QC) subsystem monitors the quality of fruit and grades that fruit according to size and/or quality. The robot has a storage subsystem for storing fruit in containers for storage or transportation, or in punnets for retail.

The invention discloses a vehicle navigation method and a vehicle navigation apparatus. One concrete embodiment mode of the method comprises the following steps: a camera acquires traffic images; whether the vehicle's current driving lane is a navigation lane or not is judged, and the navigation lane is the vehicle's current driving lane defined in navigation information; lane objects with guiding locus objects to be displayed in a superposing manner are determined according to the judgment result, wherein the guiding locus objects are used for indicating a vehicle to drive in the current driving lane or to turn into the navigation lane; and the guiding locus objects are displayed on the determined lane object in a superposing manner. The method and the apparatus realizes superposing display of the guiding locus objects in the lane of the vehicle driving road according to the current position and the navigation route of the vehicle, so a driver is visually guided to drive the vehicle in the right lane, and the vehicle is accurately navigated.

A robotic fruit picking system includes an autonomous robot that includes a positioning subsystem that enables autonomous positioning of the robot using a computer vision guidance system. The robot also includes at least one picking arm and at least one picking head, or other type of end effector, mounted on each picking arm to either cut a stem or branch for a specific fruit or bunch of fruits or pluck that fruit or bunch. A computer vision subsystem analyses images of the fruit to be picked or stored and a control subsystem is programmed with or learns picking strategies using machine learning techniques. A quality control (QC) subsystem monitors the quality of fruit and grades that fruit according to size and/or quality. The robot has a storage subsystem for storing fruit in containers for storage or transportation, or in punnets for retail.

The invention provides a method and system for guiding mechanical hand grabbing through three-dimensional visual guidance. The whole system is fixed in space, the visual field does not change due to the movement of a mechanical arm, and a target object is not likely to be away from the observation visual field of a camera; by means of acquisition in an off calibration manner, a system model structure can be repeatedly calibrated, and therefore the work precision in long-time work tasks is guaranteed; and a robot can sense environments, by means of the 3D machine vision scanning and point cloudfeature recognition and analysis technology, the robot is guided to complete some recognition and grabbing tasks of disorderly objects, and people are liberated from high-repeatability dangerous labor.

The invention relates to a robot trajectory tracking control method based on visual guidance. The method comprises the following steps: establishing a robot visual servo control system; establishing abinocular vision unified measurement field; carrying out observing by using a binocular vision device to obtain a pose transformation relationship between an end effector coordinate system and a measurement coordinate system, and converting the pose transformation relationship to a robot base coordinate system through the binocular vision measurement field; carrying out smooth estimation on the observed pose of an end effector by utilizing a Kalman filter; calculating the pose error of the end effector; and designing a visual servo controller based on fuzzy PID, processing the pose error to obtain an expected pose at the next moment, and sending the expected pose to a robot system to control the end effector to move. The technical scheme is oriented to the field of flexible machining of aerospace large parts and the application requirements of robot high-precision machining equipment, the pose of the end effector is sensed in real time through a visual sensor, so that a closed-loop feedback system is formed, and the trajectory motion precision of a six-degree-of-freedom series robot is greatly improved.

The invention relates to a two-dimensional code guidance control method of an autonomous mobile robot, and belongs to the technical field of guidance control of mobile robots. The method comprises thesteps of: marking a guidance target position on a constructed map by using a plurality of two-dimensional code based on two-dimensional code vision and in combination with real-time positioning and composition of the mobile robot; moving, by the autonomous mobile robot, to a two-dimensional code area to complete rough positioning; and then, identifying, by the mobile robot, the two-dimensional code, calculating a three-dimensional coordinate point and pose coordinates of the point, adjusting the forward speed and direction of the mobile robot according to the identified posture of the two-dimensional code and a spatial position of the two-dimensional code relative to a camera, so that the robot moves to the guidance target position to complete target guidance. The two-dimensional code guidance control method provided by the invention has the advantages that a two-dimensional code label is used to cooperate with the camera to perform visual guidance, so that the posture characteristicsare obvious, the processing is fast, the hardware cost is low, and the guidance accuracy is high.

The multi-exercise trainer includes a portable workout board having a low-friction upper surface. The low-friction upper surface includes a set of indicia concentrically spaced from one another to provide visual guidance for performing exercises thereon. The multi-exercise trainer further includes a hand pad slidable and rotatable over the low-friction upper surface. The indicia designate defined distances on the low-friction upper surface so a user may selectively position and slide the hand pad thereon while simultaneously performing push-ups.

A system for guiding an automated guided vehicle (AGV) is provided. The system includes a guidance path, an AGV, an image capturing apparatus and an operation unit. The guidance path guides the AGV. The AGV moves on the guidance path and is guided by the guidance path. The AGV moves in a vision guidance region after departing from the guidance path. The image capturing apparatus captures a vision guidance region associated image. The vision guidance region associated image at least includes an image of the vision guidance region. The operation unit determines whether the AGV departs from the guidance path, and calculates position information of the AGV in the vision guidance region. When the AGV departs from the guidance path, the operation unit guides the AGV according to the vision guidance region associated image.

The invention provides a visual detection method for appearances which comprises the following steps: an optical guiding step: calculating the similarity of images to be compared by taking a referenceimage as a standard, so as to ensure the optical imaging consistency of the images acquired by the same batch of products on different machines; and in the visual guidance step, when small part products need to reach preset high precision, otherwise, indicating that a mechanical arm cannot conduct normal feeding; acquiring the deviation angle, the X position and the Y position of a product through a visual guidance algorithm before product feeding, and notifying the machines to conduct adjustment to ensure the product feeding precision. According to the invention, a deep learning and traditional image processing machine vision detection method is adopted, so that the requirement of similarity comparison in an image acquisition stage exists, and the invention is used for ensuring that consistent images are acquired, thereby ensuring accuracy of subsequent data for depth model detection and the accuracy of image detection.

The invention provides an FPC precision aligning machine, which comprises a working table. The working table is provided with a four-axis robot, a material loading plate, an alignment loading table and a first visual camera. The output end of the four-axis robot is connected with a rotating shaft. The rotating shaft is connected with a second visual camera and a grabbing mechanism. The first visual camera is arranged upwards. The alignment loading table is composed of a supporting seat and the supporting seat is provided with a loading plate. The loading plate is provided with two symmetrically arranged material loading levels. The lower part of the material loading levels is communicated with a first vacuum suction disc. Based on the visual guidance, the precise alignment is conducted. Therefore, the problems of low personnel efficiency and visual fatigue can be solved. Moreover, the high precision is achieved based on the visual guidance. When a soft FPC board is changed, a new product can be realized only through relearning the visual program. The utilization rate of equipment is improved, and the flexibility is high. The diversified demands of customers are well satisfied.

A method and system for visually guiding an aircraft in its landing approach to a runway having an approach area equipped with approach lights operable in off, low, medium, and high intensity states. The lights are communicated with a secondary side of a transformer, which has a primary side with low, medium, and high taps that correspond to the light states. Off, low, medium, and high lighting intensity requests correspond to the low, medium, and high states of the plurality of lights. AC power is switched between the transformer taps in response to a request for an increase in lighting intensity. Power is sequentially applied to the taps by supplying the power to the low tap for a first predetermined time interval before supplying the power to the medium tap.

MRI-guided robotics offers possibility for physicians to perform interventions remotely on confined anatomy. While the pathological and physiological changes could be visualized by high-contrast volumetric MRI scan during the procedure, robots promise improved navigation with added dexterity and precision. In cardiac catheterization, however, maneuvering a long catheter (1-2 meters) to the desired location and performing the therapy are still challenging. To meet this challenge, this invention presents an MRI-conditional catheter robotic system that integrates intra-op MRI, MR-based tracking units and enhanced visual guidance with catheter manipulation. This system differs fundamentally from existing master/slave catheter manipulation systems, of which the robotic manipulation is still challenging due to the very limited image guidance. This system provides a means of integrating intra-operative MR imaging and tracking to improve the performance of tele-operated robotic catheterization.

The invention discloses a robot visual calibrating method based on a perspective transformation model. The relation between a pixel coordinate system and a robot coordinate system is built according to a perspective transformation principle between plane coordinate systems; and four sets of pixel coordinates and robot coordinates are acquired by using four non-collinear marking points to calibrateand calculate coordinate conversion model parameters for visual guide robot positioning. The method can be used for calibrating fixed cameras or terminal cameras mounted on robots without consideringthe depth direction, and is low in cost, high in calibrating precision and suitable for visual positioning requirements of industrial scene robots.

A method to automate the process of teaching by allowing the robot to compare a live image of the work space along the desired path with a reference image of a similar workspace associated with a nominal path approximating the desired path, the robot teaches itself by comparing the reference image to the live image and generating the desired path at the desired location, hence eliminating human involvement in the process with most of its shortcomings. The present invention also overcomes the problem of site displacement or distortion by monitoring its progress along the path by sensors and modifying the path to conform to the desired path.

The invention relates to a mobile robot positioning method based on visual guidance laser repositioning, and the method comprises the following steps: carrying out the initialization positioning of the position of a robot according to a visual feature map, and mapping the position of the robot to a laser map; adopting an adaptive particle filtering method, and obtaining accurate positioning of therobot on a laser map according to a laser scanning matching result; judging whether the particle variance positioned in the positioning process of the self-adaptive particle filtering method exceedsa set threshold value or not: if so, performing visual repositioning by utilizing a visual feature map, outputting a positioning result of the robot, and re-initializing the current particle, namely,performing error recovery; if not, outputting a positioning result of the robot. Compared with the prior art, the method has the advantages that the robot can quickly recover accurate positioning by means of the repositioning function of the visual feature map during initialization or after being bound, so the stability and reliability of positioning are guaranteed.

The invention discloses a camera pose calibration method based on spatial point location information. For a robot vision system with an independently-installed camera, a sphere is placed at the tail end of a robot to serve as a calibration object, then the robot is operated to change the position and posture of the sphere to move to different point locations, images and point clouds of table tennis balls at the tail end of the robot are collected; the sphere center is fitted to serve as a spatial point, and meanwhile the corresponding position and posture of the robot are recorded; then a transformation relation between a camera coordinate system and a robot base coordinate system is calculated by searching an equation relation between specific point position changes; the points collectedunder a camera coordinate system are converted into points under a robot base coordinate system, and directly achieving target grabbing of the robot based on visual guidance. According to the invention, the sphere is used as a calibration object, the operation is simple, flexible and portable, the tedious calibration process is simplified, and compared with a method for conversion by means of a calibration plate or a calibration intermediate coordinate system, the method has higher precision, and does not introduce an intermediate transformation relationship and excessive error factors.

The invention provides a 3D visual guidance based unstacking method and system, and relates to the technical field of logistics and warehousing. The method comprises steps as follows: point cloud dataand image data of stacked materials are acquired on the basis of 3D vision; a target box body is recognized from the image data with an instance segmentation algorithm, and current position coordinates of the target box body are determined according to the point cloud data; information of a path from a manipulator to the target box body is planned according to the current position coordinates ofthe target box body and current position coordinates of the manipulator, the manipulator is enabled to grab the target box body from the stacked material according to the information of the path, andthe target box body is placed in the target position. Manual work is replaced to complete unstacking, working efficiency is high, the worker is tireless, working properties are relatively stable, andaccuracy rate of goods unstacking is high.

The invention relates to a user health condition comprehensive evaluation method and system. The system comprises a user information input module, a knowledge graph reasoning module and a result analysis module, and is used for collecting various types of information of genetic diseases, behavior characteristics, living environments and physiological states of users through the graphical user information input module and mapping the various types of information input by the users to specific user tags. After the labels are input into the knowledge graph reasoning module, the knowledge graph module performs reasoning by utilizing the user labels to obtain various high-risk diseases of the user, so that inspection items suitable for the corresponding diseases and suggestions and improvementmethods of bad behavior habits of the user are continued to be reasoned. In the result analysis module, the current health score of the user can be calculated according to the reasoning result, the user is more visually guided to judge the health condition of the user; meanwhile, comparison of the health conditions of the user before and after behavior feature improvement can be provided, and helpand power are provided for the user to improve the wrong habit of the user.