71results about How to "Improve crawl success rate" patented technology

The invention discloses a robot under-actuated hand autonomous grasping method based on stereoscopic vision, and relates to a robot autonomous grasping method. The problems that a grasping point can not be calculated through an existing robot grasping method until a three-dimensional model of an object is obtained in advance and the existing robot grasping method can only recognize a simple object and can not obtain a corresponding grasping point for a complicated object are solved. The method includes the steps of obtaining RGB-D point cloud of the object and the environment through a Kinect sensor and conducting filtering on the point cloud for a to-be-grasped object and the environment of the object; extracting normal vector included angle characteristics, coplanar characteristics, distance characteristics, grasping stability characteristics, collision detecting characteristics and corresponding constraint equations for the RGB-D point cloud; establishing a grasping planning scheme on the basis of Gaussian process classification; driving an under-actuated hand for grasping according to the grasping scheme, then judging whether the under-actuated hand has already grasped the object or not according to current detection till the under-actuated hand grasps the object, and releasing the object after completing the grasping task. The method is suitable for the field of robot grasping.

The invention relates to a robot disordered grasping device and method based on double cameras. The device comprises a worktable, a material taking box, a suction disc, a robot, a bracket, a machine vision system and a material discharging box. The material taking box and the material discharging box are arranged on the worktable at interval; the robot is arranged on the worktable and is located between the material taking box and the material discharging box; the suction disc is arranged at a tail end executing device of the robot; the bracket is arranged at one end, close to the material taking box, of the worktable; the machine vision system is arranged on the bracket; a target object is arranged in the material taking box; the robot is used for controlling the suction disc to grasp the target object in the material taking box in an disordered manner through the machine vision system and putting the target object into the material discharging box. According to the robot disordered grasping device and method based on the double cameras, the machine vision system can be used for acquiring three-dimensional posture information of a disordered stacked object to be grasped so as to realize disordered grasping and ordered placement processes of the robot; the robot disordered grasping device and method have the advantages of compact structure, high grasping success rate, high placement precision, low cost, convenience for operation and the like, and automation and intellectualization of a grasping process can be realized.

The invention discloses a material carrying and moving composite robot. The robot comprises the following modules of a visual grabbing module, a Mecanum wheel-based moving control module, a laser navigation module and a laser and sonar obstacle avoidance module, wherein the visual grabbing module is used for grabbing information data of a target material, processing the information data, comparingthe information data with key characteristic information of the target material, and carrying out visual grabbing on the target material during the material carrying and moving process; the Mecanum wheel-based moving control module is used for controlling walking poses of the composite robot; the laser navigation module is used for conducting navigation and optimal path planning according to a global map and a local map, and conducting rough positioning of the position of a target station; and the laser and sonar obstacle avoidance module integrates a laser obstacle avoidance algorithm and asonar obstacle avoidance algorithm, and is used for obstacle avoidance during walking. The robot has the beneficial effects of being high in target material grabbing success rate, accurate in positioning and capable of automatically walking.

A tissue culture seedling transplanting gripper with a scratching function belongs to the field of facility agriculture automation seedling transplanting equipment, and comprises a cylinder connecting frame, a steel needle frame, a wedge bench, guide tubes, steel needles, a gripper seat, springs, a cylinder, a cylinder push rod, and movable shafts; the cylinder is mounted above the cylinder connecting frame; the gripper seat is mounted below the cylinder connecting frame; the steel needle frame and the wedge bench are fixed at the front end of the cylinder push rod; a projection is disposed at the inner side of the parallel guide tube, and the projection is provided with a hole; each of the four guide tubes is mounted on the gripper seat by the movable shaft which passes through the hole on the projection, and can rotate around the movable shaft; the four guide tubes are uniformly distributed at the periphery of the outside of the gripper seat, and are mounted parallel to the cylinderaxis. the spring is mounted at the lower part of a group of two guide tubes facing each other, and the two ends of the spring are respectively fixed on the two guide tubes; one end of one steel needle is fixed on the steel needle frame, and the other end is inserted into the guide tube. The invention is applicable to transplanting between different aperture disks, has a compact structure, and is convenient for installation and maintenance.

The invention provides a TFT array substrate board and an alignment method thereof. The TFT array substrate board comprises a display area and a non-display area surrounding the display area, whereinthe non-display area is provided with alignment marks and a transparent conducting layer which is arranged on the alignment marks and is in contact with the alignment marks; when alignment equipment scans the area where the alignment marks are located through electronic scanning, the different bound electron capacity of the alignment marks and the transparent conducting layer are used to enable the alignment marks to show black in the alignment equipment, the transparent conducting layer is in grey color in the alignment equipment, and obvious grey-scale comparison is formed, the grabbing success rate of alignment marks is improved, and the false grabbing rate of alignment equipment is reduced

The invention discloses a mechanical arm grabbing planning method and system combined with self-supervised learning, and the method comprises the steps: generating a plurality of grabbing postures through the complete point cloud of an object, obtaining a pair of contact points between the grabbing postures and the complete point cloud of the object, comparing the included angles between the normal vectors, pointing to the interior of the object, of the pair of contact points and the unit vectors, serving the tangent value of the large included angle as the quality coefficient of the grabbing posture, and generating a category label for the grabbing posture; serving the multiple grabbing postures with the category labels as training data, training the classification neural network to be converged, and obtaining a grabbing quality classification model; and generating a plurality of candidate grabbing postures through the complete point cloud of the object to be grabbed, scording and classifying the candidate grabbing postures through the grabbing quality classification model, and serving the candidate grabbing posture with the highest score and the category of the candidate grabbing posture as the optimal grabbing plan of the mechanical arm. The self-supervised learning mode is introduced to construct the training data, robust grabbing of unknown objects in the multi-target stacking scene is achieved, and the grabbing success rate of the mechanical arm is increased.

The invention discloses a sweet pepper recognition and picking sequence determination method based on multi-view three-dimensional reconstruction. Firstly, point cloud data of a target fruit is obtained through multi-view three-dimensional reconstruction in combination with a plurality of views, so that point cloud noise can be effectively reduced, and the influence of leaf shielding can be reduced; recognizing the obtained RGBD point cloud information through an HSV recognition algorithm, and filtering out non-red sweet pepper fruit point cloud; solving the number of point clouds of the sweet pepper fruits and the number of point clouds in each point cloud of the sweet pepper fruits through Euclidean clustering; and finally, the recognized fruit point cloud clusters, namely the sweet pepper fruit point cloud, are processed, the size of each fruit point cloud cluster, the grabbing difficulty degree and the distance from the optimal grabbing point in each fruit point cloud cluster to the tail end of the mechanical arm are obtained, and the optimal grabbing sequence of the fruits is obtained through a multi-target optimization algorithm. According to the method, information in multiple aspects is combined to determine how the picking robot grabs the recognized fruits, the picking sequence of the fruits is determined, the grabbing success rate of the picking robot can be increased. Meanwhile, energy consumption of the mechanical arm is reduced, the picking success rate is increased, and the fruit damage rate is reduced.

The embodiment of the invention provides a vehicle-mounted manipulator one-key grabbing and putting-back control method, device and system, and belongs to the technical field of manipulator control. The method comprises the following steps that an obstacle virtual wall is established, and a grabbing path and a putting-back path of a manipulator are constructed based on the obstacle virtual wall; in the grabbing stage, in response to a first instruction sent by a user side, the manipulator is controlled to move above a target object, and after it is detected that the execution tail end of the manipulator is in contact with the target object, a first gripper and a second gripper at the execution tail end are controlled to grab the target object with preset first output pressure, and the manipulator is moved to a first target position according to the grabbing path; and the first gripper and the second gripper are controlled to release the target object. According to the technical scheme,the grabbing path and the putting-back path of the manipulator are determined based on establishing the obstacle virtual wall, so that the operation safety is effectively guaranteed.

The invention discloses a pushing and grabbing collaborative sorting network based on double viewing angles and a sorting method and system thereof. The trained pushing and grabbing collaborative sorting network comprises a pushing full convolutional network and a grabbing full convolutional network, and the network is applied to robot pushing and grabbing collaborative sorting. The sorting methodcomprises the following steps of correspondingly acquiring point cloud graphs of an object scene to be sorted from two viewing angles, rotating a top view of the point cloud graphs, correspondingly inputting a plurality of rotating images into the pushing full convolutional network and the grabbing full convolutional network to obtain two thermodynamic graphs with Q values output by the networks,and selecting the thermodynamic diagram with the larger Q value as a final thermodynamic diagram; and according to the pixel point corresponding to the maximum Q value in the thermodynamic diagram and the rotation angle of the rotation image corresponding to the thermodynamic diagram, controlling the robot to execute the sorting action of the network corresponding to the thermodynamic diagram, and then completing sorting. According to the sorting method, double viewing angles are combined with deep Q learning, so that the grabbing success rate is high and the generalization ability is high inthe face of a disordered stacking scene.

Example methods and devices for processing a page are described. One or more pages of a designated website are acquired. The one or more pages are clustered to obtain one or more classes in accordance with page features of the pages. At least one class is selected as a list page set according to a page linking relationship between the one or more classes. It is not necessary to require an operator to manually involve in the process of establishing the list page set. The present techniques have simple operations and high accuracy rate, thereby improving an efficiency and reliability of establishing a list page library.

The invention relates to the field of pot seedling transplantation. The technical scheme is that a small-space parallel inclined entering shrinking type vegetable pot seedling transplantation tail endexecutor is characterized by comprising a supporting seat, a cylinder, a claw needle fixed plate, a guide plate, a separation plate, a plurality of claw needles, a plurality of circular rings and a retraction block, wherein the cylinder is vertically mounted on the supporting seat; the claw needle fixed plate is fixed at the tail end of a pushing rod of the cylinder; the guide plate and the separation plate are fixed on the supporting seat at an interval and the middle parts of the guide plate and the separation plate are set as through holes; one end of each claw needle is fixed on the clawneedle fixed plate, while the other end sequentially passes through the guide plate and the separator downwards to grab pot needles; the plurality of circular rings are movably positioned on the separation plate along a horizontal direction and correspondingly sleeve the claw needles; the retraction block is arranged in a suspended mode at the center of the through hole of the separation plate andis fixedly connected with each circular ring by a steel wire rope; the guide plate is provided with a plurality of guide holes convenient for each claw needle to pass through; and the separation plate is provided with a plurality of chutes convenient for each claw needle to pass through. The end executor has the characteristics of small structure, small volume, high stability and applicability tosmall-space pot seedling transplantation.

The invention discloses a control system and a control method for the autonomous grasp of an unmanned aerial vehicle(UAV), and relates to a UAV system and a control method thereof. The system providedby the invention comprises a ground monitoring system, a UAV control system and an autonomous grasp system; wherein the ground monitoring system which comprises a mobile computer, a wireless communication unit and a data transmission unit is used for transmitting data information and monitoring the running state of the UAV; the UAV control system which comprises a UAV flying control unit, a UAV flying dynamic unit and a UAV hovering height holding unit is used for providing driving force to the UAV and controlling the flying state of the UAV; and the autonomous grasp system which comprises abinocular vision unit, an image processing unit, an autonomous grasp control unit and a grasp action unit is mainly used for obtaining object information and realizing autonomous grasp. By utilizing the advantage in binocular vision, the UAV takes the initiative to find a target and independently develops algorithms, thereby realizing the integration of the flying system and the grasp system and achieving good effects in stable UAV flying and precise autonomous grasp.

The embodiment of the invention provides a method and apparatus for capturing information of user interface UI elements, and a storage medium. The method for capturing information of user interface UIelements may includes detecting a user operation acting on the UI and obtaining a position parameter affected by the user operation; determining a target element for the user operation according to the position parameter; obtaining a type of the target element; according to the type of the target element, a corresponding element grabbing tool is called to grab the information of the target element.

The invention belongs to the field of robot finger control, and discloses a control method and system for fingers of a dexterous hand of a robot. The method comprises the following steps of obtainingcategory information of a to-be-grabbed object, and determining a theoretical motor drive current for each finger to grab the to-be-grabbed object in a pre-established control model for a driving motor stroke and current for each finger of the dexterous hand to grab each category of object; driving each finger of the dexterous hand to grab the to-be-grabbed object by adopting the theoretical motordrive current, and acquiring an actual motor drive current for each finger to grab the to-be-grabbed object in real time; and when the actual motor drive current for any finger to grab the to-be-grabbed object exceeds the theoretical motor drive current of the corresponding finger, enabling the driving motor to stop working, and completing the grabbing action of the to-be-grabbed object. According to the control method, finger pressure detection is converted into motor current detection for driving the finger to move, so that the precision and convenience of pressure measurement are improved,and the precision of finger feedback control is improved; and the control system is simple in structure.

The invention belongs to the field of computer vision and intelligent robots, and particularly relates to a robot target grabbing detection method based on a scale-invariant network. The objective ofthe invention is to make up for the defects of an existing grabbing detection algorithm in target scale change adaptability and grabbing state diversity representation. A complex multi-scale network structure and a multi-observation-angle sample are not needed; a scale transformation factor can be adaptively estimated; target consistence output is provide;, according to the object grabbing detection method, the scale transformation factor can be adjusted in a self-adaptive mode according to the size of the object to be grabbed and the actual distance between the object to be grabbed and the camera, consistent output of the target object is obtained, and therefore robustness of a grabbing detection result under different scales is guaranteed.

The invention provides a mechanical arm and a wafer grabbing device. The mechanical arm comprises a mechanical arm body which comprises a main body part and two fork arm parts, and the main body partis provided with a first fixing part. The tail end of each fork arm part is provided with a second supporting part and a second fixing part, and a height difference exists between the second fixing part and the second supporting part, so that the second fixing part and the first fixing part are enabled to fix the wafer; and the upper surface of the second supporting part inclines towards one sidesurface in the height extension direction of the second fixing part, so that the wafer gradually moves to the top of the second supporting part along the upper surface inclining towards one side surface, and the movement path of the wafer is prevented from deviating. Moreover, the second fixing part and the second supporting part have a certain height difference, so that the second fixing part caneffectively block the wafer and fix the wafer with the first fixing part, the wafer is prevented from moving out of the fork arm part in the moving process, and the grabbing success rate of the waferis increased.

The invention belongs to the field of robot control, in particular to a method for acquiring grasping points of a robot steadily grasping an object based on monocular vision, aiming at solving the problem of low grasping success rate of a robot to an unknown object in an unstructured environment. The invention comprises the following steps: obtaining the color image of the object and the environment based on the monocular vision sensor, and extracting the plane edge contour of the object; Based on the planar edge contours of four-fingered parallel manipulator and object, constructing the environment constraint domain of robot grasping system, and obtaining the lowest point of environment attraction domain, and then a plurality of candidate grasping points. Inputting the candidate grabbingpoints of each group into a grabbing point quality evaluation network to obtain the grabbing point quality of each group of candidate grabbing points; Selecting the output of the grab point corresponding to the maximum quality of the grab point. The invention improves the rapidity, accuracy and reliability of the grasping point identification, and improves the grasping success rate of the robot tothe unknown object in the unstructured environment.

The invention discloses a wire clamping device of a hot-line work robot and an operation method thereof.The wire clamping device comprises a fixed claw assembly and a movable claw assembly; the fixed claw assembly comprises a wire clamping support and a lower rolling shaft; the movable claw assembly comprises an upper rolling shaft, a wire clamping swing rod and a connecting rod; the lower rolling shaft is connected to the wire clamping support; the upper rolling shaft is connected to one end of the wire clamping swing rod; the middle of the wire clamping swing rod is hinged to the wire clamping support; the other end of the wire clamping swing rod is hinged to the connecting rod; and the connecting rod drives the wire clamping swing rod to rotate to achieve opening and closing control between the upper rolling shaft and the lower rolling shaft, and then wire clamping operation is achieved. The wire clamping device tool has high adaptability and compatibility to a robot, and a large opening can be achieved while the light design requirement of the robot is met, so that the grabbing success rate is greatly increased; and resistance brought by branch wires when the robot moves is greatly reduced through the rolling wire stroking design, the operation efficiency is effectively improved, and the risk of manual operation is avoided.

The invention relates to the field of mechanical assembly, in particular to a quick high-precision filter cartridge packaging system. The quick high-precision filter cartridge packaging system comprises a barrel feeding device, a barrel cover pushing device and a barrel cover packaging device, wherein a barrel body and a barrel cover are sequentially conveyed out through the barrel feeding deviceand the barrel cover pushing device correspondingly, then the barrel body is packaged by the barrel cover under drive of the barrel cover packaging device, automatic taking and packaging are achieved,and the automatic degree is high; and a grabbing module fixedly grabs the barrel cover from inside to outside, compared with a grabbing manner of a vacuum chuck, the grabbing success rate is high, the concentricity is high, and the percentage of defective products generated during assembly is low.

The invention discloses an unmanned aerial vehicle grabbing device, including a fixing bracket, wherein positioning holes are formed at the positions close to four corners of the inner wall of the bottom end of the fixing bracket; positioning rods are inserted into the inner walls of the four positioning holes; a transverse plate arranged horizontally is fixed on the out walls of the top ends of the four positioning rods by bolts; the positions, close to the bottom end of the transverse plate, of the four positioning rods, are each sleeved with a first spring member; the bottom ends of the four positioning rods are fixed with the same mounting bracket by bolts; the outer walls on both sides of the bottom end of the mounting bracket are welded with support brackets, and clamping mechanismsare arranged at the bottom ends of the outer walls on opposite sides of the two support brackets; and the clamping mechanisms comprise semi-circular rings. The unmanned aerial vehicle grabbing deviceis convenient for grasping the goods, is conducive to improving the grasping success rate, is compact in structure, quick in response, is convenient for grasping and putting the goods, is conducive tolifting the shock absorption performance of the device, is conducive to protecting the goods and enriches the functions of the device.