WO2023272985A1 - 智能堆垛机及托盘位置异常的识别方法、装置和设备 - Google Patents

智能堆垛机及托盘位置异常的识别方法、装置和设备 Download PDF

Info

Publication number
WO2023272985A1
WO2023272985A1 PCT/CN2021/121160 CN2021121160W WO2023272985A1 WO 2023272985 A1 WO2023272985 A1 WO 2023272985A1 CN 2021121160 W CN2021121160 W CN 2021121160W WO 2023272985 A1 WO2023272985 A1 WO 2023272985A1
Authority
WO
WIPO (PCT)
Prior art keywords
pallet
point cloud
cloud data
abnormal
offset
Prior art date
Application number
PCT/CN2021/121160
Other languages
English (en)
French (fr)
Inventor
徐光运
孙文侠
张贻弓
Original Assignee
兰剑智能科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 兰剑智能科技股份有限公司 filed Critical 兰剑智能科技股份有限公司
Publication of WO2023272985A1 publication Critical patent/WO2023272985A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
    • B65G43/08—Control devices operated by article or material being fed, conveyed or discharged
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G57/00—Stacking of articles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/06—Topological mapping of higher dimensional structures onto lower dimensional surfaces
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G2201/00—Indexing codes relating to handling devices, e.g. conveyors, characterised by the type of product or load being conveyed or handled
    • B65G2201/02—Articles
    • B65G2201/0235—Containers
    • B65G2201/0258—Trays, totes or bins
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
    • B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
    • B65G2203/04—Detection means
    • B65G2203/041—Camera
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds

Definitions

  • the invention relates to an intelligent stacker and an identification method, device and equipment for abnormal position of pallets, and belongs to the technical field of warehousing and logistics.
  • the current mainstream stacker positioning technology is to locate the stacker through encoders, laser ranging, etc., and move the stacker to the pick-up position at a specific coordinate position to pick up the goods.
  • the present invention develops a technology for detecting the position of the pallet, so as to avoid the occurrence of collision.
  • the present invention proposes an intelligent stacker and a method, device and equipment for identifying abnormal positions of pallets, which can avoid collisions.
  • an embodiment of the present invention provides a method for identifying abnormal pallet positions, including the following steps:
  • the status of the pallet includes: whether there is a pallet, pallet offset, hole collapse, pallet slider rotation, beam settlement, and beam tilt.
  • the processing of point cloud data includes:
  • the use of a 3D point cloud edge detection algorithm to determine the pallet state includes:
  • the pallet offset includes: pallet left offset and pallet right offset;
  • the hole collapse includes: left fork hole collapse and right fork hole collapse;
  • the beam settlement includes: the left beam settlement and the right beam settlement;
  • the inclination of the beam includes: inclination of the left beam and inclination of the right beam.
  • an embodiment of the present invention provides a device for detecting the position of a tray, including:
  • the point cloud data acquisition module is used to collect the point cloud data of the pallet
  • the point cloud data processing module is used to process the point cloud data
  • the pallet abnormality determination module is used to determine the status of the pallet by using the 3D point cloud edge detection algorithm.
  • the pallet status includes: presence or absence of the pallet, pallet offset, hole collapse, pallet slider rotation, beam settlement and beam tilt.
  • the point cloud data processing module includes:
  • the point cloud data correction module is used to correct the inclination of the collected point cloud data according to the calibration data
  • the image conversion module is used to convert the point cloud at the front end of the pallet into a 2D image
  • the pallet boundary positioning module is used to perform region edge detection on 2D images and locate the pallet boundary.
  • the pallet abnormality determination module is specifically used for:
  • the pallet offset includes: pallet left offset and pallet right offset;
  • the hole collapse includes: left fork hole collapse and right fork hole collapse;
  • the beam settlement includes: the left beam settlement and the right beam settlement;
  • the inclination of the beam includes: inclination of the left beam and inclination of the right beam.
  • an intelligent stacker provided by an embodiment of the present invention includes a stacker body, and also includes a 3D camera and an industrial computer.
  • the 3D camera takes pictures of the pallet and collects point cloud data of the pallet; the industrial computer
  • the machine is installed with a computer program, and the computer program executes the steps of the method for identifying an abnormal position of any pallet as described above when running.
  • the 3D camera is installed on the base and/or the side support of the stacker. Install the 3D camera on the base of the stacker or on the side bracket to meet the requirements of the 3D camera for collecting pallet data.
  • a computer device provided by an embodiment of the present invention is characterized in that it includes a processor, a memory, and a bus, and the memory stores machine-readable instructions executable by the processor.
  • the computer device runs When the processor communicates with the memory through a bus, the processor executes the machine-readable instructions, so as to execute the steps of the method for identifying an abnormality of any tray position as described above.
  • an embodiment of the present invention provides a storage medium, on which a computer program is stored, and when the computer program is run by a processor, the steps of the method for identifying an abnormal position of any tray described above are executed.
  • the present invention is based on the technology of visual detection of pallets, which uses visual detection of pallets before the stacker picks up the goods to detect whether its position, deformation, etc. are normal, and then picks up the goods after judging, so as to avoid the occurrence of collisions, and can also Abnormal pallets are corrected or alarmed.
  • the invention utilizes 3D vision technology to detect the position and abnormality of the pallet of goods to be picked up, avoiding the occurrence of collision of the stacker when the pallet is abnormally shifted, collapsed, etc., and increases the safety in the process of picking up the goods.
  • the invention uses 3D vision technology to detect the position and abnormality of the cargo pallet to be picked up during the stacker pick-up process, so as to avoid the occurrence of the stacker crashing when the pallet is abnormally shifted or collapsed.
  • Fig. 1 is a flow chart of a method for identifying abnormal pallet positions according to an exemplary embodiment
  • Fig. 2 is a schematic diagram showing an abnormal position of a pallet according to an exemplary embodiment
  • Fig. 3 is a flow chart of a kind of 3D point cloud edge detection algorithm shown according to an exemplary embodiment
  • Fig. 4 is a structural diagram of a device for detecting the position of a tray according to an exemplary embodiment
  • Fig. 5 is a schematic diagram showing the installation position of a 3D camera according to an exemplary embodiment
  • Fig. 6 is a schematic diagram showing the position of a 3D camera installed on a stacker according to an exemplary embodiment
  • Fig. 7 is a schematic diagram showing a dual-camera calibration pose transformation according to an exemplary embodiment
  • Fig. 8 is a structural diagram of a computer device according to an exemplary embodiment.
  • a method for identifying an abnormal pallet position includes the following steps:
  • the status of the pallet includes: whether there is a pallet, pallet offset, hole collapse, pallet slider rotation, beam settlement, and beam tilt.
  • the collection of point cloud data of the pallet includes:
  • the calibration board After the calibration board is placed on the standard position of the pallet, the calibration board is identified using the reliability image information, the reference pose of the camera is obtained, and the pose relationship between the image acquisition device and the pose of the standard pallet is obtained.
  • the processing of point cloud data includes:
  • the use of a 3D point cloud edge detection algorithm to determine the pallet state includes:
  • the pallet offset includes: pallet left offset and pallet right offset;
  • the hole collapse includes: left fork hole collapse and right fork hole collapse;
  • the beam settlement includes: the left beam settlement and the right beam settlement;
  • the inclination of the beam includes: inclination of the left beam and inclination of the right beam.
  • the present invention adopts a 3D point cloud edge detection algorithm.
  • the solution uses an industrial 3D camera to shoot the pallet to obtain the point cloud information of the pallet, correct the inclination of the point cloud according to the calibration data, and convert the point cloud of the front of the pallet into a 2D image, use the area edge search technology to locate the border of the pallet in the 2D image, and Compare the resulting value with the original template position data to obtain data such as the relative left and right translation of the pallet, up and down settlement, etc.
  • 2D image area edge search technology the idea is to arrange detection lines at equal intervals in the same direction in a certain ROI to detect edge gradient extremes, that is, to detect edge positions. Since the edges of pallets in this application are mostly straight lines, straight line fitting can be used to The detected points are fitted to a straight line to enhance the robustness of edge detection.
  • the area edge detection technology includes:
  • Line iterator which efficiently extracts the grayscale information at a specific line position of the image
  • the edge point detection algorithm uses the grayscale data on the straight line to detect the position of the maximum increase and decrease point, which is considered to be the edge position
  • Detection line layout algorithm after setting the detection range, and setting the detection line spacing or total amount, the detection lines are arranged at equal intervals in the same direction in the ROI
  • the present invention stably detects the physical edge of the tray through the 3D point cloud edge detection algorithm, judges the edge deformation, and determines the offset and deformation of the tray, and can obtain the presence or absence of the tray, the offset of the tray, the collapse of the hole, the rotation of the tray slider, and the beam Pallet status such as settlement and beam tilting.
  • a device for detecting the position of a pallet provided by an embodiment of the present invention includes:
  • the point cloud data acquisition module is used to collect the point cloud data of the pallet
  • the point cloud data processing module is used to process the point cloud data
  • the pallet abnormality determination module is used to determine the status of the pallet by using the 3D point cloud edge detection algorithm.
  • the pallet status includes: presence or absence of the pallet, pallet offset, hole collapse, pallet slider rotation, beam settlement and beam tilt.
  • the point cloud data processing module includes:
  • the point cloud data correction module is used to correct the inclination of the collected point cloud data according to the calibration data
  • the image conversion module is used to convert the point cloud at the front end of the pallet into a 2D image
  • the pallet boundary positioning module is used to perform region edge detection on 2D images and locate the pallet boundary.
  • the pallet abnormality determination module is specifically used for:
  • the pallet offset includes: pallet left offset and pallet right offset;
  • the hole collapse includes: left fork hole collapse and right fork hole collapse;
  • the beam settlement includes: the left beam settlement and the right beam settlement;
  • the inclination of the beam includes: inclination of the left beam and inclination of the right beam.
  • an intelligent stacker provided by an embodiment of the present invention includes a stacker body, and also includes a 3D camera and an industrial computer.
  • the 3D camera takes pictures of the pallet and collects point cloud data of the pallet; the industrial computer
  • the machine is installed with a computer program, and the computer program executes the steps of the method for identifying an abnormal position of any pallet as described above when running.
  • the 3D camera is installed on the base and/or the side support of the stacker. As shown in Figure 5 and Figure 6, the 3D camera is installed on the base of the stacker or on the side bracket to meet the requirements of the 3D camera for collecting pallet data.
  • the present invention uses a 3D camera to take pictures, and the number and installation position of the cameras are selected according to the type of stacker. For single-side pallets of a single-deep stacker, two cameras are used to take pictures; for single-side shooting of a double-deep stacker , as shown in Fig. 5 and Fig. 6, two cameras (proximity cameras) are selected for the near stretch tray to take pictures, and one camera (far stretch camera) is used for the far stretch tray to take pictures.
  • the camera is installed on the cargo platform, and the industrial computer and switch are installed in the electrical cabinet of the cargo platform, and they all move together with the cargo platform.
  • the installation of the camera on the stacker has large position restrictions and field of view restrictions.
  • the camera cannot face the pallet directly, and can only shoot part of the pallet tilted, and the imaging distance is relatively short.
  • the plan chooses to use a camera on both sides of the stacker to shoot in the middle, and shoots a pile and a hole of the pallet respectively;
  • the gap between the forks mounts the camera to shoot horizontally forward.
  • the installation position and camera angle of view are shown in Figure 5 and Figure 6.
  • the present invention adopts the calibration method of multiple Tof 3D cameras. After placing the calibration plate at the standard position of the pallet, the calibration plate is identified by using the Tof 3D camera confidence image information to obtain the reference pose of the camera, and then obtain two 3D cameras and a stacker. Pose relations for standard pallet poses. The pose transformation between multiple Tof3D cameras and stackers (standard pick-up pallets) is obtained through this calibration technology. After installing the camera, calibrate the position of the camera and the stacker, and provide calibration data for the subsequent point cloud information processing.
  • camA H camB camA H cal * cal H cal' *( camB H cal' ) -1 , and then obtain the pose transformation between two Tof3D cameras and pallets.
  • the stacker moves to the target pick-up location, and the main control PLC of the stacker uses TCP communication to trigger the work of the industrial computer
  • the industrial computer calls the camera to take pictures, and calls the 3D point cloud edge detection algorithm to detect the current pallet offset, hole collapse, beam settlement and other core detection quantities
  • the industrial computer system compares the core detection volume of the current pallet with the core detection volume of the standard pallet stored in advance, and compares the deviation with the set threshold to determine the logic of picking up, correcting, and alarming
  • the industrial computer returns the processing results to the main control PLC of the stacker, and the stacker performs corresponding operations according to the visual results.
  • the specific detection items and detection methods in the process of detecting the pallet position include:
  • the present invention uses an algorithm to detect the result of the edge of the pallet to determine whether there is a pallet in the position.
  • Pallet offset Due to the mechanical error of the stacker and the sliding of the pallet, the pallet is not on the standard pick-up position, and there may be a left-right offset.
  • the invention uses vision to detect the positions of the sliders on both sides of the tray to determine the overall position of the tray.
  • Pallet collapse Collision during pallet handling and long-term placement of heavy goods on the pallet may cause the pallet to collapse.
  • the invention uses vision to detect the position of the edge of the tray hole to calculate the collapse height and judge whether it collapses.
  • Beam settlement and beam inclination The installation height of the beams in each cargo space is inconsistent, resulting in a height difference between the loading platform and the beams; and the beams may be tilted left and right, resulting in inconsistent heights of the beams, causing problems in loading and unloading.
  • the present invention uses vision to detect the height of the crossbeam under the left and right holes, and judges whether the heights of the two places are consistent.
  • Pallet slider rotation During the pallet handling process, some collisions may cause the slider to rotate and shift, and it may hit the rotated and shifted bad slider when the stacker picks up the goods normally.
  • the patent analyzes the point cloud of the slider area on the basis of positioning the tray, and uses the point cloud analysis to determine the angle of the slider and combine it with the detection of the edge of the slider to determine whether the slider rotates.
  • Fig. 8 is a structural diagram of a computer device according to an exemplary embodiment.
  • a computer device provided by an embodiment of the present invention includes a processor, a memory, and a bus.
  • the memory stores machine-readable instructions executable by the processor.
  • the processor communicates with the memory through a bus, and the processor executes the machine-readable instructions, so as to perform the steps of the above-mentioned method for identifying an abnormality of any tray position during execution.
  • the above-mentioned memory and processor can be general-purpose memory and processor, which are not specifically limited here.
  • the processor runs the computer program stored in the memory, the above-mentioned method for calculating the installation position deviation of the AGV forklift laser scanner can be executed.
  • FIG. 8 does not constitute a limitation on the computer equipment, and may include more or less components than those shown in the illustration, or combine some components, or split some components. components, or different component arrangements.
  • the computer device may further include a touch screen for displaying a graphical user interface (for example, an application startup interface) and receiving user operations on the graphical user interface (for example, application startup operations).
  • a specific touch screen may include a display panel and a touch panel.
  • the display panel can be configured in the form of LCD (Liquid Crystal Display, Liquid Crystal Display), OLED (Organic Light-Emitting Diode, Organic Light-Emitting Diode), and the like.
  • the touch panel can collect the user's contact or non-contact operations on or near it, and generate preset operation instructions, for example, the user uses any suitable operations near the control panel.
  • the touch panel may include two parts: a touch detection device and a touch controller.
  • the touch detection device detects the user's touch orientation and posture, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, and converts it into The processed information is then sent to the processor, and can receive and execute commands from the processor.
  • various types of touch panels such as resistive, capacitive, infrared, and surface acoustic waves can be used to implement the touch panel, and any technology developed in the future can also be used to implement the touch panel.
  • the touch panel can cover the display panel, and the user can operate on or near the touch panel covered on the display panel according to the graphical user interface displayed on the display panel.
  • the touch panel After the touch panel detects the operation on or near it , to the processor to determine the user input, and the processor then provides a corresponding visual output on the display panel in response to the user input.
  • the touch panel and the display panel can be implemented as two independent components or integrated.
  • an embodiment of the present invention also provides a storage medium, on which a computer program is stored, and when the computer program is run by the processor, the steps of the method for identifying an abnormal position of any tray described above are executed. .
  • the device for launching the application program provided in the embodiment of the present application may be specific hardware on the device or software or firmware installed on the device.
  • the implementation principles and technical effects of the device provided by the embodiment of the present application are the same as those of the aforementioned method embodiment.
  • the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the above-mentioned method embodiments, and will not be repeated here.
  • the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • the disclosed devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of modules is only a logical function division.
  • multiple modules or components can be combined or integrated. to another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces, and the indirect coupling or communication connection of devices or modules may be in electrical, mechanical or other forms.
  • a module described as a separate component may or may not be physically separated, and a component shown as a module may or may not be a physical module, that is, it may be located in one place, or may be distributed to multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional module in the embodiments provided in this application may be integrated into one processing module, each module may exist separately physically, or two or more modules may be integrated into one module.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions
  • the device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mechanical Engineering (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

本发明公开了一种智能堆垛机及托盘位置异常的识别方法、装置和设备，方法包括以下步骤：采集托盘的点云数据；对点云数据进行处理，获取托盘位置；判定托盘是否出现异常，所述托盘出现异常的情况包括：托盘偏移、孔洞塌陷和横梁沉降。本发明利用3D视觉技术对将取的货物托盘进行位置和异常检测，避免了托盘发生偏移、坍塌等异常时堆垛机撞货的发生，增加了取货过程中的安全性。

Description

智能堆垛机及托盘位置异常的识别方法、装置和设备 技术领域
本发明涉及一种智能堆垛机及托盘位置异常的识别方法、装置和设备，属于仓储物流技术领域。
背景技术
目前主流的堆垛机定位技术，是通过编码器、激光测距等对堆垛机进行定位，将堆垛机移动到特定坐标位置的取货位，进行取货。
但是，堆垛机取货过程中，并无对托盘的检测，只是到达目标位置后直接伸叉取货。而托盘上货物质量、堆垛机摆放误差等因素，容易导致货架上的托盘出现偏移和形变、坍塌，堆垛机取货时进行“盲取”容易发生“撞货”的危险，这会对用户产生不可估计的损失。
为了避免这种撞货的风险，本发明研发了一种检测托盘位置的技术，以此来避免撞货的发生。
因此，需要一种在减低成本的基础上提高效率的检测托盘位置的方法。
发明内容
为了解决上述问题，本发明提出了一种智能堆垛机及托盘位置异常的识别方法、装置和设备，能够避免撞货的发生。
本发明解决其技术问题采取的技术方案是：
第一方面，本发明实施例提供的一种托盘位置异常的识别方法，包括以下步骤：
采集托盘的点云数据；
对点云数据进行处理；
利用3D点云边缘检测算法判定托盘状态，所述托盘状态包括：有无托盘、托盘偏移、孔洞塌陷、托盘滑块旋转、横梁沉降以及横梁倾斜。
作为本实施例一种可能的实现方式，所述对点云数据进行处理，包括：
依据标定数据矫正采集点云数据的倾斜；
将托盘前端点云转换为2D图像；
利用3D点云边缘检测算法对2D图像进行区域边缘检测，定位托盘的边界。
作为本实施例一种可能的实现方式，所述利用3D点云边缘检测算法判定托盘状态，包括：
在2D图像中利用区域边缘查找技术定位托盘边界，将结果数值与托盘原始模板的数据进行对比，获取两者的位置偏差，将位置偏差量大于设定阈值则判定托盘出现异常，否则为无异常。
作为本实施例一种可能的实现方式，
所述托盘偏移包括：托盘左偏移和托盘右偏移；
所述孔洞塌陷包括：左叉孔洞塌陷和右叉孔洞塌陷；
所述横梁沉降包括：左侧横梁沉降和右侧横梁沉降；
所述横梁倾斜包括：左侧横梁倾斜和右侧横梁倾斜。
第二方面，本发明实施例提供的一种检测托盘位置的装置，包括：
点云数据采集模块，用于采集托盘的点云数据；
点云数据处理模块，用于对点云数据进行处理；
托盘异常判定模块，用于利用3D点云边缘检测算法判定托盘状态，所述托盘状态包括：有无托盘、托盘偏移、孔洞塌陷、托盘滑块旋转、横梁沉降以及横梁倾斜。
作为本实施例一种可能的实现方式，所述点云数据处理模块包括：
点云数据矫正模块，用于依据标定数据矫正采集点云数据的倾斜；
图像转换模块，用于将托盘前端点云转换为2D图像；
托盘边界定位模块，用于对2D图像进行区域边缘检测，定位托盘的边界。
作为本实施例一种可能的实现方式，所述托盘异常判定模块，具体用于：
在2D图像中利用区域边缘查找技术定位托盘边界，将结果数值与托盘原始模板的数据进行对比，获取两者的位置偏差，将位置偏差量大于设定阈值则判定托盘出现异常，否则为无异常。
作为本实施例一种可能的实现方式，
所述托盘偏移包括：托盘左偏移和托盘右偏移；
所述孔洞塌陷包括：左叉孔洞塌陷和右叉孔洞塌陷；
所述横梁沉降包括：左侧横梁沉降和右侧横梁沉降；
所述横梁倾斜包括：左侧横梁倾斜和右侧横梁倾斜。
第三方面，本发明实施例提供的一种智能堆垛机，包括堆垛机本体，还包括3D相机和工控机，所述3D相机对托盘进行拍照，采集托盘的点云数据；所述工控机安装有计算机程序，该计算机程序在运行时执行如上述任意托盘位置异常的识别方法的步骤。
作为本实施例一种可能的实现方式，所述的3D相机安装在堆垛机的底座和/或侧边支架上。将3D相机安装在堆垛机的底座上或者侧边支架上，满足3D相机采集托盘数据的要求。
作为本实施例一种可能的实现方式，在执行如上述任意托盘位置异常的识别方法的步骤之前，在托盘的标准位置放置标定板后，利用信度图像信息识别标定板，获取相机参考位姿，并获取图像采集装置与标准托盘位姿的位姿关系，作为标定数据。
第四方面，本发明实施例提供的一种计算机设备，其特征是，包括处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，当所述计算机设备运行时，所述处理器与所述存储器之间通过总线通信，所述处理器执行所述机器可读指令，以执行时执行如上述任意托盘位置异常的识别方法的步骤。
第五方面，本发明实施例提供的一种存储介质，该存储介质上存储有计算 机程序，该计算机程序被处理器运行时执行如上述任意托盘位置异常的识别方法的步骤。
本发明实施例的技术方案可以具有的有益效果如下：
本发明依据视觉检测托盘的技术，既在堆垛机取货前利用视觉检测托盘，检测其位置、形变等是否正常，判断之后再进行取货，以此来避免撞货的发生，还可以对异常托盘进行纠偏或报警操作。
本发明利用3D视觉技术对将取的货物托盘进行位置和异常检测，避免了托盘发生偏移、坍塌等异常时堆垛机撞货的发生，增加了取货过程中的安全性。
本发明在堆垛机取货过程中，利用3D视觉技术对将取的货物托盘进行位置和异常检测，避免了托盘发生偏移、坍塌等异常时堆垛机撞货的发生。
附图说明：
图1是根据一示例性实施例示出的一种托盘位置异常的识别方法的流程图；
图2是根据一示例性实施例示出的一种托盘位置异常示意图；
图3是根据一示例性实施例示出的一种3D点云边缘检测算法的流程图；
图4是根据一示例性实施例示出的一种检测托盘位置的装置的结构图；
图5是根据一示例性实施例示出的一种3D相机的安装位置示意图；
图6是根据一示例性实施例示出的一种3D相机安装在堆垛机上位置示意图；
图7是根据一示例性实施例示出的一种双相机标定位姿变换示意图；
图8是根据一示例性实施例示出的一种计算机设备的结构图。
具体实施方式
下面结合附图与实施例对本发明做进一步说明：
为能清楚说明本方案的技术特点，下面通过具体实施方式，并结合其附图， 对本发明进行详细阐述。下文的公开提供了许多不同的实施例或例子用来实现本发明的不同结构。为了简化本发明的公开，下文中对特定例子的部件和设置进行描述。此外，本发明可以在不同例子中重复参考数字和/或字母。这种重复是为了简化和清楚的目的，其本身不指示所讨论各种实施例和/或设置之间的关系。应当注意，在附图中所图示的部件不一定按比例绘制。本发明省略了对公知组件和处理技术及工艺的描述以避免不必要地限制本发明。
如图1所示，本发明实施例提供的一种托盘位置异常的识别方法，包括以下步骤：
采集托盘的点云数据；
对点云数据进行处理；
利用3D点云边缘检测算法判定托盘状态，所述托盘状态包括：有无托盘、托盘偏移、孔洞塌陷、托盘滑块旋转、横梁沉降以及横梁倾斜。
作为本实施例一种可能的实现方式，所述采集托盘的点云数据，包括：
在托盘的标准位置放置标定板后，利用信度图像信息识别标定板，获取相机参考位姿，并获取图像采集装置与标准托盘位姿的位姿关系。
作为本实施例一种可能的实现方式，所述对点云数据进行处理，包括：
依据标定数据矫正采集点云数据的倾斜；
将托盘前端点云转换为2D图像；
利用3D点云边缘检测算法对2D图像进行区域边缘检测，定位托盘的边界。
作为本实施例一种可能的实现方式，所述利用3D点云边缘检测算法判定托盘状态，包括：
在2D图像中利用区域边缘查找技术定位托盘边界，将结果数值与托盘原始模板的数据进行对比，获取两者的位置偏差，将位置偏差量大于设定阈值则判定托盘出现异常，否则为无异常。
作为本实施例一种可能的实现方式，如图2所示，
所述托盘偏移包括：托盘左偏移和托盘右偏移；
所述孔洞塌陷包括：左叉孔洞塌陷和右叉孔洞塌陷；
所述横梁沉降包括：左侧横梁沉降和右侧横梁沉降；
所述横梁倾斜包括：左侧横梁倾斜和右侧横梁倾斜。
如图3所示，本发明采用了3D点云边缘检测算法。方案采用工业3D相机拍摄托盘获取托盘的点云信息后，依据标定数据矫正点云的倾斜，并将托盘前端点云转换为2D图像，在2D图像中利用区域边缘查找技术定位托盘的边界，并将结果数值与原始模板位置数据进行对比，获取托盘相对左右平移、上下沉降等数据。
2D图像区域边缘查找技术，其思想是在一定的ROI内同方向等间距布置检测线检测边缘梯度极值，即检测边缘位置，由于本应用中托盘边缘多为直线，之后可利用直线拟合将检测到的点拟合为直线，以增强边缘检测的鲁棒性。
该区域边缘检测技术包含：
线迭代器，将图像某一特定直线位置上的灰度信息高效提取出来
检测边缘点算法，利用直线上的灰度数据，检测最大增幅与降幅点位置，认为是边缘位置
检测线布局算法，设置检测范围后，并设置检测线间距或总量，在ROI内同方向等间距布置检测线
直线拟合，获取同方向等间距布置检测线检测边缘梯度极值，即检测边缘位置，利用这些位置拟合出直线，即可认为是实际的直线边缘位置。
本发明通过3D点云边缘检测算法稳定检测托盘的物理边缘，判断边缘形变量，确定托盘的偏移及形变量，即可获得有无托盘、托盘偏移、孔洞塌陷、托盘滑块旋转、横梁沉降以及横梁倾斜等托盘状态。
如图4所示，本发明实施例提供的一种检测托盘位置的装置，包括：
点云数据采集模块，用于采集托盘的点云数据；
点云数据处理模块，用于对点云数据进行处理；
托盘异常判定模块，用于利用3D点云边缘检测算法判定托盘状态，所述托盘状态包括：有无托盘、托盘偏移、孔洞塌陷、托盘滑块旋转、横梁沉降以及横梁倾斜。
作为本实施例一种可能的实现方式，所述点云数据处理模块包括：
点云数据矫正模块，用于依据标定数据矫正采集点云数据的倾斜；
图像转换模块，用于将托盘前端点云转换为2D图像；
托盘边界定位模块，用于对2D图像进行区域边缘检测，定位托盘的边界。
作为本实施例一种可能的实现方式，所述托盘异常判定模块，具体用于：
在2D图像中利用区域边缘查找技术定位托盘边界，将结果数值与托盘原始模板的数据进行对比，获取两者的位置偏差，将位置偏差量大于设定阈值则判定托盘出现异常，否则为无异常。
作为本实施例一种可能的实现方式，
所述托盘偏移包括：托盘左偏移和托盘右偏移；
所述孔洞塌陷包括：左叉孔洞塌陷和右叉孔洞塌陷；
所述横梁沉降包括：左侧横梁沉降和右侧横梁沉降；
所述横梁倾斜包括：左侧横梁倾斜和右侧横梁倾斜。
第三方面，本发明实施例提供的一种智能堆垛机，包括堆垛机本体，还包括3D相机和工控机，所述3D相机对托盘进行拍照，采集托盘的点云数据；所述工控机安装有计算机程序，该计算机程序在运行时执行如上述任意托盘位置异常的识别方法的步骤。
作为本实施例一种可能的实现方式，所述的3D相机安装在堆垛机的底座和/或侧边支架上。如图5和图6所示，将3D相机安装在堆垛机的底座上或者侧边支架上，满足3D相机采集托盘数据的要求。
作为本实施例一种可能的实现方式，在执行如上述任意托盘位置异常的识别方法的步骤之前，在托盘的标准位置放置标定板后，利用信度图像信息识别 标定板，获取相机参考位姿，并获取图像采集装置与标准托盘位姿的位姿关系，作为标定数据。
本发明利用3D相机进行拍摄，相机的数量及安装位置依据堆垛机的类型进行选配，对于单深堆垛机单侧托盘，选用两个相机进行拍照；对于双深堆垛机单侧拍摄，如图5和图6所示，近伸托盘选用两个相机(近伸相机)进行拍照，远伸托盘选用一个相机(远伸相机)进行拍摄。相机安装于载货台上，工控机及交换机安装在载货台电气柜中，均随载货台一起移动。
由于堆垛机空间紧凑，相机在堆垛机上的安装有较大的位置限制及视场限制，相机无法正视拍摄托盘，仅仅能倾斜拍摄部分托盘，且成像距离较近。对于近深取货位托盘拍摄，方案选择在堆垛机两侧各用一个相机倾斜向中间拍摄，分别拍摄托盘的一个桩和孔洞；对于远伸托盘取货位托盘拍照，方案选择在两货叉之间的空隙安装相机水平向前拍摄。安装位置及相机视角如图5和图6所示。
本发明采用多个Tof 3D相机标定的方法，在托盘的标准位置放置标定板后，利用Tof 3D相机置信度图像信息识别标定板，获取相机参考位姿，进而获取2个3D相机、堆垛机标准托盘位姿的位姿关系。通过该标定技术获取多个Tof3D相机、堆垛机(标准取货位托盘)之间的位姿变换。用于安装相机后，对相机位置与堆垛机进行标定，为后面点云信息处理提供标定数据。
由于近伸两相机无共同视野,考虑标定精度，手动(依靠装置自动)移动标定板，使得标定板分别在两相机下可以拍摄。手动移动标定板时，沿着标定板坐标系的一个轴方向移动固定距离，这样两次标定板位姿间变换阵 calH cal’仅有一个平移量。
例如，如图7所示，标定相机后， camAH cal和 camBH cal’均可由标定计算外参得到，则相机B在相机A下的位姿有： camAH camB＝ camAH cal* calH cal’*( camBH cal’) -1，进而获取两个Tof3D相机、托盘之间的位姿变换。
利用所述堆垛机进行检测托盘位置的过程如下：
1、堆垛机移动到目标取货货位，堆垛机主控PLC利用TCP通讯触发工控机 工作
2、工控机调用相机拍照，调用3D点云边缘检测算法检测当前托盘的偏移、孔洞塌陷、横梁沉降等核心检测量
3、工控机统将当前托盘的核心检测量与预先存储的标准托盘核心检测量进行对比，并将偏差与设定阈值进行比较，决定取货、纠偏、报警逻辑
4、工控机将处理结果返回堆垛机主控PLC,堆垛机依据视觉结果执行相应操作。
在检测托盘位置的过程中具体的检测项及检测方法包括：
(1)有无托盘：由于人工操作等原因，堆垛机货架有些货位无托盘，堆垛机存在空取现象。本发明利用算法检测托盘边缘的结果，判定该货位是否有托盘。
(2)托盘偏移：由于堆垛机放货时的机械误差、托盘滑动等，照成托盘不在标准取货位上，可能存在左右偏移。本发明利用视觉检测托盘的两侧滑块位置，判定托盘整体的位置。
(3)托盘坍塌：托盘搬运过程中的碰撞，较重货物在托盘上的长时间放置，可能导致托盘发生坍塌。本发明利用视觉检测托盘孔洞边缘位置计算坍塌高度，判断是否坍塌。
(4)横梁沉降与横梁倾斜：每个货位横梁安装高度不一致，造成载货台与横梁有高度差；且横梁可能存在左右倾斜，造成横梁左右高度不一致，取放货造成问题。本发明利用视觉检测左右两孔洞下的横梁高度，判断两处高度是否一致。
(5)托盘滑块旋转：在托盘搬运过程中，一些碰撞可能导致滑块发生旋转、偏移，在堆垛机正常取货时可能撞到已旋转、偏移的坏滑块。专利在定位托盘的基础上分析滑块区域点云，利用点云分析确定滑块角度并与检测滑块边缘相结合的方式，判定滑块是否旋转。
图8是根据一示例性实施例示出的一种计算机设备的结构图。如图8所示， 本发明实施例提供的一种计算机设备，包括处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，当所述计算机设备运行时，所述处理器与所述存储器之间通过总线通信，所述处理器执行所述机器可读指令，以执行时执行如上述任意托盘位置异常的识别方法的步骤。
具体地，上述存储器和处理器能够为通用的存储器和处理器，这里不做具体限定，当处理器运行存储器存储的计算机程序时，能够执行上述计算AGV叉车激光扫描仪安装位置偏差的方法。
本领域技术人员可以理解，图8中示出的计算机设备的结构并不构成对计算机设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。
在一些实施例中，该计算机设备还可以包括触摸屏可用于显示图形用户界面(例如，应用程序的启动界面)和接收用户针对图形用户界面的操作(例如，针对应用程序的启动操作)。具体的触摸屏可包括显示面板和触控面板。其中显示面板可以采用LCD(Liquid Crystal Display，液晶显示器)、OLED(Organic Light-Emitting Diode,有机发光二极管)等形式来配置。触控面板可收集用户在其上或附近的接触或者非接触操作，并生成预先设定的操作指令，例如，用户使用手指、触笔等任何适合的物体或附件在触控面板上或在触控面板附近的操作。另外，触控面板可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测用户的触摸方位、姿势，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成处理器能够处理的信息，再送给处理器，并能接收处理器发来的命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板，也可以采用未来发展的任何技术实现触控面板。进一步的，触控面板可覆盖显示面板，用户可以根据显示面板显示的图形用户界面，在显示面板上覆盖的触控面板上或者附近进行操作，触控面板检测到在其上或附近的操作后，传送给处理器以确定用户输入，随后处理器响应于用户输入在显示面板上提供相 应的视觉输出。另外，触控面板与显示面板可以作为两个独立的部件来实现也可以集成而来实现。
对应于上述应用程序的启动方法，本发明实施例还提供了一种存储介质，该存储介质上存储有计算机程序，该计算机程序被处理器运行时执行如上述任意托盘位置异常的识别方法的步骤。
本申请实施例所提供的应用程序的启动装置可以为设备上的特定硬件或者安装于设备上的软件或固件等。本申请实施例所提供的装置，其实现原理及产生的技术效果和前述方法实施例相同，为简要描述，装置实施例部分未提及之处，可参考前述方法实施例中相应内容。所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，前述描述的系统、装置和单元的具体工作过程，均可以参考上述方法实施例中的对应过程，在此不再赘述。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
在本申请所提供的实施例中，应该理解到，所揭露装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个模块或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或模块的间接耦合或通信连接，可以是电性，机械或其它的形式。
作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可 以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外，在本申请提供的实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以两个或两个以上模块集成在一个模块中。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
最后应当说明的是：以上实施例仅用以说明本发明的技术方案而非对其限制，尽管参照上述实施例对本发明进行了详细的说明，所属领域的普通技术人员应当理解：依然可以对本发明的具体实施方式进行修改或者等同替换，而未脱离本发明精神和范围的任何修改或者等同替换，其均应涵盖在本发明的权利要求保护范围之内。

Claims (13)

  1. 一种托盘位置异常的识别方法，其特征是，包括以下步骤：
    采集托盘的点云数据；
    对点云数据进行处理；
    利用3D点云边缘检测算法判定托盘状态，所述托盘状态包括：有无托盘、托盘偏移、孔洞塌陷、托盘滑块旋转、横梁沉降以及横梁倾斜。
  2. 根据权利要求1所述的托盘位置异常的识别方法，其特征是，所述对点云数据进行处理，包括：
    依据标定数据矫正采集点云数据的倾斜；
    将托盘前端点云转换为2D图像；
    利用3D点云边缘检测算法对2D图像进行区域边缘检测，定位托盘的边界。
  3. 根据权利要求2所述的托盘位置异常的识别方法，其特征是，所述利用3D点云边缘检测算法判定托盘状态，包括：
    在2D图像中利用区域边缘查找技术定位托盘边界，将结果数值与托盘原始模板的数据进行对比，获取两者的位置偏差，将位置偏差量大于设定阈值则判定托盘出现异常，否则为无异常。
  4. 根据权利要求1-3任意一项所述的托盘位置异常的识别方法，其特征是，
    所述托盘偏移包括：托盘左偏移和托盘右偏移；
    所述孔洞塌陷包括：左叉孔洞塌陷和右叉孔洞塌陷；
    所述横梁沉降包括：左侧横梁沉降和右侧横梁沉降；
    所述横梁倾斜包括：左侧横梁倾斜和右侧横梁倾斜。
  5. 一种检测托盘位置的装置，其特征是，包括：
    点云数据采集模块，用于采集托盘的点云数据；
    点云数据处理模块，用于对点云数据进行处理；
    托盘异常判定模块，用于利用3D点云边缘检测算法判定托盘状态，所述托盘状态包括：有无托盘、托盘偏移、孔洞塌陷、托盘滑块旋转、横梁沉降以 及横梁倾斜。
  6. 根据权利要求5所述的检测托盘位置的装置，其特征是，所述点云数据处理模块包括：
    点云数据矫正模块，用于依据标定数据矫正采集点云数据的倾斜；
    图像转换模块，用于将托盘前端点云转换为2D图像；
    托盘边界定位模块，用于对2D图像进行区域边缘检测，定位托盘的边界。
  7. 根据权利要求6所述的检测托盘位置的装置，其特征是，所述托盘异常判定模块，具体用于：
    在2D图像中利用区域边缘查找技术定位托盘边界，将结果数值与托盘原始模板的数据进行对比，获取两者的位置偏差，将位置偏差量大于设定阈值则判定托盘出现异常，否则为无异常。
  8. 根据权利要求5-7任意一项所述的检测托盘位置的装置，其特征是，
    所述托盘偏移包括：托盘左偏移和托盘右偏移；
    所述孔洞塌陷包括：左叉孔洞塌陷和右叉孔洞塌陷；
    所述横梁沉降包括：左侧横梁沉降和右侧横梁沉降；
    所述横梁倾斜包括：左侧横梁倾斜和右侧横梁倾斜。
  9. 一种智能堆垛机，包括堆垛机本体，其特征是，还包括3D相机和工控机，所述3D相机对托盘进行拍照，采集托盘的点云数据；所述工控机安装有计算机程序，该计算机程序在运行时执行如权利要求1-4任一所述的托盘位置异常的识别方法的步骤。
  10. 根据权利要求9所述的智能堆垛机，其特征是，所述的3D相机安装在堆垛机的底座和/或侧边支架上。
  11. 根据权利要求10所述的智能堆垛机，其特征是，在执行如权利要求1-4任一所述的托盘位置异常的识别方法的步骤之前，在托盘的标准位置放置标定板后，利用信度图像信息识别标定板，获取相机参考位姿，并获取图像采集装置与标准托盘位姿的位姿关系，作为标定数据。
  12. 一种计算机设备，其特征是，包括处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，当所述计算机设备运行时，所述处理器与所述存储器之间通过总线通信，所述处理器执行所述机器可读指令，以执行时执行如权利要求1-4任一所述的托盘位置异常的识别方法的步骤。
  13. 一种存储介质，其特征是，该存储介质上存储有计算机程序，该计算机程序被处理器运行时执行如权利要求1-4任一所述的托盘位置异常的识别方法的步骤。
PCT/CN2021/121160 2021-06-30 2021-09-28 智能堆垛机及托盘位置异常的识别方法、装置和设备 WO2023272985A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110742463.5 2021-06-30
CN202110742463.5A CN113435524A (zh) 2021-06-30 2021-06-30 智能堆垛机及托盘位置异常的识别方法、装置和设备

Publications (1)

Publication Number Publication Date
WO2023272985A1 true WO2023272985A1 (zh) 2023-01-05

Family

ID=77758405

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/121160 WO2023272985A1 (zh) 2021-06-30 2021-09-28 智能堆垛机及托盘位置异常的识别方法、装置和设备

Country Status (2)

Country Link
CN (1) CN113435524A (zh)
WO (1) WO2023272985A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116309550A (zh) * 2023-05-11 2023-06-23 聊城市飓风工业设计有限公司 基于图像处理的集成电路贴片异常识别方法
CN117649564A (zh) * 2024-01-29 2024-03-05 成都飞机工业（集团）有限责任公司 一种飞机舱位装配偏差识别装置及量化评估方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113435524A (zh) * 2021-06-30 2021-09-24 兰剑智能科技股份有限公司 智能堆垛机及托盘位置异常的识别方法、装置和设备
CN114972505B (zh) * 2022-04-29 2023-05-12 弥费科技(上海)股份有限公司 一种位置识别系统
CN114955342B (zh) * 2022-06-02 2024-07-02 浙江中烟工业有限责任公司 一种高架库呆滞托盘查找方法及系统
CN115546202B (zh) * 2022-11-23 2023-03-03 青岛中德智能技术研究院 一种用于无人叉车的托盘检测与定位方法
CN116040261B (zh) * 2022-12-23 2023-09-19 青岛宝佳智能装备股份有限公司 一种专用托盘翻转机
CN117381804B (zh) * 2023-12-13 2024-04-02 珠海格力智能装备有限公司 智能搬运机器人的物料放置部件自动摆正方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107507167A (zh) * 2017-07-25 2017-12-22 上海交通大学 一种基于点云平面轮廓匹配的货物托盘检测方法及系统
CN110058591A (zh) * 2019-04-24 2019-07-26 合肥柯金自动化科技股份有限公司 一种基于激光雷达与深度摄像机混合导航的agv系统
CN110781794A (zh) * 2019-10-21 2020-02-11 兰剑智能科技股份有限公司 一种智能识别的方法及系统
CN110950277A (zh) * 2019-12-16 2020-04-03 浙江迈睿机器人有限公司 用于agv叉车的托盘姿态识别系统及其方法
CN112070759A (zh) * 2020-09-16 2020-12-11 浙江光珀智能科技有限公司 一种叉车托盘检测与定位方法及系统
CN112614183A (zh) * 2020-12-25 2021-04-06 深圳市镭神智能系统有限公司 托盘位姿检测方法、装置、设备和存储介质
CN113435524A (zh) * 2021-06-30 2021-09-24 兰剑智能科技股份有限公司 智能堆垛机及托盘位置异常的识别方法、装置和设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107102009A (zh) * 2017-05-04 2017-08-29 武汉理工大学 一种基于机器视觉的筒纱管质量检测的方法
CN108876771B (zh) * 2018-06-04 2022-05-20 广东工业大学 一种咬边焊接缺陷的检测方法
CN110097574A (zh) * 2019-04-24 2019-08-06 南京邮电大学 一种已知刚体的实时位姿估计方法
CN112001972A (zh) * 2020-09-25 2020-11-27 劢微机器人科技(深圳)有限公司 托盘位姿定位方法、装置、设备及存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107507167A (zh) * 2017-07-25 2017-12-22 上海交通大学 一种基于点云平面轮廓匹配的货物托盘检测方法及系统
CN110058591A (zh) * 2019-04-24 2019-07-26 合肥柯金自动化科技股份有限公司 一种基于激光雷达与深度摄像机混合导航的agv系统
CN110781794A (zh) * 2019-10-21 2020-02-11 兰剑智能科技股份有限公司 一种智能识别的方法及系统
CN110950277A (zh) * 2019-12-16 2020-04-03 浙江迈睿机器人有限公司 用于agv叉车的托盘姿态识别系统及其方法
CN112070759A (zh) * 2020-09-16 2020-12-11 浙江光珀智能科技有限公司 一种叉车托盘检测与定位方法及系统
CN112614183A (zh) * 2020-12-25 2021-04-06 深圳市镭神智能系统有限公司 托盘位姿检测方法、装置、设备和存储介质
CN113435524A (zh) * 2021-06-30 2021-09-24 兰剑智能科技股份有限公司 智能堆垛机及托盘位置异常的识别方法、装置和设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116309550A (zh) * 2023-05-11 2023-06-23 聊城市飓风工业设计有限公司 基于图像处理的集成电路贴片异常识别方法
CN116309550B (zh) * 2023-05-11 2023-08-04 聊城市飓风工业设计有限公司 基于图像处理的集成电路贴片异常识别方法
CN117649564A (zh) * 2024-01-29 2024-03-05 成都飞机工业（集团）有限责任公司 一种飞机舱位装配偏差识别装置及量化评估方法
CN117649564B (zh) * 2024-01-29 2024-05-14 成都飞机工业（集团）有限责任公司 一种飞机舱位装配偏差识别装置及量化评估方法

Also Published As

Publication number Publication date
CN113435524A (zh) 2021-09-24

Similar Documents

Publication Publication Date Title
WO2023272985A1 (zh) 智能堆垛机及托盘位置异常的识别方法、装置和设备
US9828223B2 (en) Fork-lift truck and method for operating a fork-lift truck
CN108885792B (zh) 使用物理长度单位进行的货板检测
US9025827B2 (en) Controlling truck forks based on identifying and tracking multiple objects in an image scene
JP7206421B2 (ja) スマートフォークリフト及び容器位置姿勢ずれの検出方法
WO2022105695A1 (zh) 货物取放方法、装置、仓储机器人和仓储系统
KR101095579B1 (ko) 모노 비전 기반의 팔레트 위치 및 자세 측정 방법
US20230286750A1 (en) Method and device for storing goods, robot, warehousing system and storage medium
US20100097349A1 (en) Method and apparatus for detecting touch point
US11604281B2 (en) Position and posture estimation apparatus of a forklift pallet
US20240067450A1 (en) Adjustment method, apparatus, and device for material handling apparatus
WO2020039817A1 (ja) フォークリフト用荷役作業支援装置
JPWO2019163378A5 (zh)
WO2023005854A1 (zh) 机器人控制方法、装置、机器人、存储介质及程序产品
US20200103916A1 (en) Automatic guided vehicle, agv control system, and agv control method
CN112630786A (zh) 基于2d激光的agv缓存区盘点方法、装置及设备
JP2019217570A (ja) 情報処理装置、情報処理装置を備える荷降しシステム、及び情報処理プログラム
US11386573B2 (en) Article recognition apparatus
JP2019124573A (ja) 自車位置推定装置、自車位置推定方法、および自車位置推定プログラム
CN113002399A (zh) 货架搬运方法及其装置、机器可读介质和系统
WO2024053150A1 (ja) ピッキングシステム
US20230139296A1 (en) Initial setting method of unmanned forklift, palette for adjustment, and adjustment system of unmanned forklift
US20240054730A1 (en) Phased Capture Assessment and Feedback for Mobile Dimensioning
CN117644510A (zh) 机器人作业方法、装置、设备以及存储介质
EP3742384A1 (en) Information processing apparatus, article identification apparatus, and article identification system

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21947913

Country of ref document: EP

Kind code of ref document: A1