TWI799051B - Automatic guided vehicle and method for forking pallet - Google Patents
Automatic guided vehicle and method for forking pallet Download PDFInfo
- Publication number
- TWI799051B TWI799051B TW111100044A TW111100044A TWI799051B TW I799051 B TWI799051 B TW I799051B TW 111100044 A TW111100044 A TW 111100044A TW 111100044 A TW111100044 A TW 111100044A TW I799051 B TWI799051 B TW I799051B
- Authority
- TW
- Taiwan
- Prior art keywords
- pallet
- processor
- bounding box
- distance
- depth
- Prior art date
Links
Images
Landscapes
- Warehouses Or Storage Devices (AREA)
- Forklifts And Lifting Vehicles (AREA)
Abstract
Description
本發明是有關於一種移動棧板的自動搬運車(automatic guided vehicle,AGV)和叉取棧板方法。 The invention relates to an automatic guided vehicle (AGV) for moving pallets and a method for forking pallets.
在智慧化工廠的趨勢下,採用自動棧板叉取技術可增加自動搬運車的自主營運模式,有效節省物流人員搬運貨物或上架貨物所需消耗的勞力和時間,進而加速物流產業或傳統產業的自動化。近年來AI機器學習技術已越趨發達,已有多種針對影像辨識的模型,其辨識率與辨識速度也有一定的基礎,並可不斷優化校正模型進行多方應用。 Under the trend of smart factories, the use of automatic pallet fork picking technology can increase the autonomous operation mode of automatic pallet trucks, effectively saving the labor and time required for logistics personnel to carry goods or put goods on shelves, and accelerate the development of logistics industry or traditional industries. automation. In recent years, AI machine learning technology has become more and more developed. There are many models for image recognition. The recognition rate and recognition speed also have a certain foundation, and the correction model can be continuously optimized for multiple applications.
目前現有之自動叉取棧板技術,多為由AGV定位方式行走至指定位置,並透過Touch Sensor與紅外線感測器判斷是否可叉取成功;另外也有透過3D視覺攝影機搭配計算模型辨識棧板,然而設備成本高昂,且擺放需要特定突出擺放方式才能辨識棧板進行叉取。為了使自動搬運車能自主地移動棧板,必須賦予自動搬運車辨識棧板的功能。然而,當物流倉庫環境狹小且環境擺設較為 雜亂時,傳統的機器視覺技術並無法準確地判斷出棧板的位置。此外,棧板的材質也會影響到物件辨識結果。 At present, most of the existing automatic fork-picking pallet technology is to walk to the designated position by the AGV positioning method, and judge whether the fork-picking is successful through the Touch Sensor and infrared sensor; in addition, there are also 3D vision cameras and computing models to identify pallets. However, the cost of equipment is high, and the placement requires a specific prominent placement method to identify pallets for fork picking. In order to enable the automatic pallet truck to move the pallet autonomously, the automatic pallet truck must be given the function of identifying the pallet. However, when the logistics warehouse environment is small and the environment decoration is relatively When it is messy, traditional machine vision technology cannot accurately determine the position of the pallet. In addition, the material of the pallet will also affect the object recognition result.
本發明提供一種用於移動棧板的自動搬運車和叉取棧板方法,可通過深度圖判斷棧板的位置。 The invention provides an automatic transport vehicle for moving a pallet and a method for forking the pallet, which can judge the position of the pallet through a depth map.
本發明的一種用於叉取棧板的自動搬運車,包含牙叉、主動輪、深度攝影機、儲存媒體以及處理器。深度攝影機擷取深度圖,其中深度圖包含棧板。儲存媒體儲存機器學習模型。處理器耦接牙叉、主動輪、深度攝影機以及儲存媒體,並且經配置以執行:自深度圖取得分別對應於多個深度的多個圖像;將多個圖像輸入至機器學習模型以產生棧板的三維定位資訊;以及根據三維定位資訊控制主動輪以及牙叉以移動棧板。 An automatic transport vehicle for forking pallets according to the present invention includes a tooth fork, a driving wheel, a depth camera, a storage medium and a processor. The depth camera captures a depth map, where the depth map includes pallets. The storage medium stores the machine learning model. The processor is coupled to the fork, the drive wheel, the depth camera and the storage medium, and is configured to perform: obtaining a plurality of images respectively corresponding to a plurality of depths from the depth map; inputting the plurality of images into a machine learning model to generate The three-dimensional positioning information of the pallet; and controlling the driving wheel and the tooth fork to move the pallet according to the three-dimensional positioning information.
在本發明的一實施例中,上述的多個圖像包含第一圖像,其中機器學習模型偵測第一圖像以產生對應於棧板的第一定界框以及第二定界框,其中處理器計算第一圖像的中心點與第一定界框之間的第一距離,並且計算中心點與第二定界框之間的第二距離,其中處理器響應於第一距離小於第二距離而從第一定界框和第二定界框中選出第一定界框,並且根據受選的第一定界框產生三維定位資訊。 In an embodiment of the present invention, the above-mentioned plurality of images includes a first image, wherein the machine learning model detects the first image to generate a first bounding box and a second bounding box corresponding to the pallet, wherein the processor calculates a first distance between the center point of the first image and the first bounding box, and calculates a second distance between the center point and the second bounding box, wherein the processor responds to the first distance being less than Select the first bounding frame from the first bounding frame and the second bounding frame according to the second distance, and generate 3D positioning information according to the selected first bounding frame.
在本發明的一實施例中,上述的機器學習模型偵測第一圖像以產生對應於第一定界框的第一可信度以及對應於第二定界 框的第二可信度,其中處理器響應於第一距離與第二距離相同而比較第一可信度與第二可信度,其中處理器響應於第一可信度大於第二可信度而從第一定界框和第二定界框中選出第一定界框,並且根據受選的第一定界框產生三維定位資訊。 In an embodiment of the present invention, the above machine learning model detects the first image to generate the first confidence level corresponding to the first bounding box and the second bounding box A second confidence level of block, wherein the processor compares the first confidence level to a second confidence level in response to the first distance being the same as the second distance, wherein the processor responds to the first confidence level being greater than the second confidence level The first bounding frame is selected from the first bounding frame and the second bounding frame, and three-dimensional positioning information is generated according to the selected first bounding frame.
在本發明的一實施例中,上述的多個圖像包含對應於第一深度的第一圖像,其中第一圖像包含像素,其中處理器深度圖取得像素的橫座標值、像素的縱座標值以及像素與深度攝影機之間的距離,其中處理器根據橫座標值、縱座標值以及距離判斷像素對應於第一深度。 In an embodiment of the present invention, the above-mentioned multiple images include a first image corresponding to a first depth, wherein the first image includes pixels, and the processor depth map obtains the abscissa value of the pixel, the vertical axis of the pixel The coordinate value and the distance between the pixel and the depth camera, wherein the processor judges that the pixel corresponds to the first depth according to the abscissa value, the ordinate value and the distance.
在本發明的一實施例中,上述的處理器根據橫座標值以及縱座標值計算座標原點與像素之間的第二距離,計算第二距離與距離的比值的反餘弦值,並且將距離與反餘弦值相乘以計算第一深度。 In an embodiment of the present invention, the above-mentioned processor calculates the second distance between the coordinate origin and the pixel according to the abscissa value and the ordinate value, calculates the arc cosine value of the ratio of the second distance to the distance, and calculates the distance Multiplied by the arccosine to calculate the first depth.
在本發明的一實施例中,上述的處理器響應於與棧板的叉口與深度攝影機的光軸之間的角度大於角度閾值而控制主動輪以縮小角度。 In an embodiment of the present invention, the processor controls the driving wheel to reduce the angle in response to the angle between the fork of the pallet and the optical axis of the depth camera being greater than an angle threshold.
在本發明的一實施例中,上述的自動搬運車更包含速度感測器。速度感測器耦接至處理器,其中速度感測器取得自動搬運車的線速度以及角速度,其中處理器根據線速度、角速度以及三維定位資訊控制主動輪。 In an embodiment of the present invention, the above-mentioned automatic transport vehicle further includes a speed sensor. The speed sensor is coupled to the processor, wherein the speed sensor obtains the linear velocity and angular velocity of the automatic transport vehicle, and the processor controls the driving wheel according to the linear velocity, angular velocity and three-dimensional positioning information.
在本發明的一實施例中,上述的自動搬運車更包含從動輪。主動輪的第一輪軸與從動輪的第二輪軸相距距離,其中處理器 根據距離控制主動輪。 In an embodiment of the present invention, the above-mentioned automatic transport vehicle further includes driven wheels. The distance between the first axle of the driving wheel and the second axle of the driven wheel, wherein the processor Control the driving wheel according to the distance.
在本發明的一實施例中,上述的多個深度中的鄰近深度彼此相距預設間距。 In an embodiment of the present invention, adjacent depths among the aforementioned plurality of depths are apart from each other by a preset distance.
在本發明的一實施例中,上述的處理器根據棧板的長度決定預設間距。 In an embodiment of the present invention, the above-mentioned processor determines the preset distance according to the length of the pallet.
在本發明的一實施例中,上述的深度攝影機包含下列的至少其中之一:RGBD鏡頭的攝影機、紅外線鏡頭的攝影機或多鏡頭的攝影機。 In an embodiment of the present invention, the above-mentioned depth camera includes at least one of the following: a camera with an RGBD lens, a camera with an infrared lens, or a camera with multiple lenses.
在本發明的一實施例中,上述的自動搬運車更包含收發器。收發器耦接處理器,其中處理器響應於通過收發器接收命令而控制主動輪以移動到指定地點,並且在指定地點擷取深度圖。 In an embodiment of the present invention, the above-mentioned automatic transport vehicle further includes a transceiver. The transceiver is coupled to the processor, wherein the processor controls the driving wheel to move to a specified location in response to receiving a command through the transceiver, and captures a depth map at the specified location.
在本發明的一實施例中,上述的機器學習模型為YOLO模型。 In an embodiment of the present invention, the above-mentioned machine learning model is a YOLO model.
本發明的一種叉取棧板的方法,適用於自動搬運車,其中方法包含:利用深度攝影機擷取深度圖,其中深度圖包含棧板;自深度圖取得分別對應於多個深度的多個圖像;將多個圖像輸入至機器學習模型以產生棧板的三維定位資訊;以及根據三維定位資訊控制自動搬運車的主動輪以及牙叉以移動棧板。 A method for forking pallets of the present invention is suitable for automatic transport vehicles, wherein the method includes: using a depth camera to capture a depth map, wherein the depth map includes pallets; obtaining multiple maps corresponding to multiple depths from the depth map image; input multiple images into the machine learning model to generate three-dimensional positioning information of the pallet; and control the driving wheel and the tooth fork of the automatic pallet truck to move the pallet according to the three-dimensional positioning information.
基於上述,本發明的自動搬運車可偵測棧板的三維定位資訊,並可根據三維定位資訊自動地移動棧板,從而為工廠節省大量的勞力成本和時間成本。本發明結合深度攝影機與AI機器學習,可讓物流業者透過較低設備建置成本,以及環境佈建需求低的狀 況下,有效的辨識出棧板位置與角度。本發明透過深度影像的分層處理與AI深度學習,可避免因環境變動或是因光線、不同的棧板材質變化等等,而造成無法辨識棧板的情況。 Based on the above, the automatic transport vehicle of the present invention can detect the three-dimensional positioning information of the pallet, and can automatically move the pallet according to the three-dimensional positioning information, thereby saving a lot of labor cost and time cost for the factory. The present invention combines the depth camera and AI machine learning, allowing the logistics industry to achieve low equipment construction costs and low environmental deployment requirements. Under certain circumstances, the position and angle of the pallet can be effectively identified. Through the layered processing of depth images and AI deep learning, the present invention can avoid the situation that pallets cannot be identified due to environmental changes or changes in light, different pallet materials, and the like.
100:自動搬運車 100:Automatic pallet truck
110:處理器 110: Processor
120:儲存媒體 120: storage media
121:機器學習模型 121:Machine Learning Models
130:收發器 130: Transceiver
140:深度攝影機 140: Depth camera
141:光軸 141: optical axis
150:牙叉 150: tooth fork
160:車輪 160: wheels
161:主動輪 161: driving wheel
162:從動輪 162: driven wheel
170:速度感測器 170: Speed sensor
200:棧板 200: Pallet
210:叉口 210: fork
211:中心軸 211: central axis
300、400、500:定界框 300, 400, 500: bounding box
310、410、O:中心點 310, 410, O: center point
61、62:輪軸 61, 62: axle
71、72:圖像 71, 72: Image
A1、A2、d、d2、d3、D:距離 A1, A2, d, d2, d3, D: distance
d1:深度 d1: depth
H:高度 H: height
L:長度 L: Length
m:預設間距 m: default spacing
P0:座標原點 P0: coordinate origin
P1:像素 P1: pixel
R:旋轉半徑 R: radius of rotation
W:寬度 W: width
x J 、x K 、z J 、z K :座標值 x J , x K , z J , z K : coordinate values
δ、δ J 、δ K :偏擺角 δ , δ J , δ K : yaw angle
θ、:角度 θ , :angle
S301、S302、S303、S304、S305、S306、S307、S308、S309、 S310、S311、S312、S313、S314、S315、S901、S902、S903、S904:步驟 S301, S302, S303, S304, S305, S306, S307, S308, S309, S310, S311, S312, S313, S314, S315, S901, S902, S903, S904: steps
圖1根據本發明的一實施例繪示一種用於叉取棧板的自動搬運車的示意圖。 FIG. 1 shows a schematic diagram of an automatic transport vehicle for forking pallets according to an embodiment of the present invention.
圖2根據本發明的一實施例繪示自動搬運車的車輪配置的示意圖。 FIG. 2 is a schematic diagram illustrating a wheel configuration of an automatic transport vehicle according to an embodiment of the present invention.
圖3根據本發明的一實施例繪示移動棧板的方法的流程圖。 FIG. 3 shows a flowchart of a method for moving a pallet according to an embodiment of the invention.
圖4根據本發明的一實施例繪示自動搬運車的旋轉半徑和偏擺角的示意圖。 FIG. 4 is a schematic diagram illustrating the rotation radius and yaw angle of the automatic transport vehicle according to an embodiment of the present invention.
圖5根據本發明的一實施例繪示自動搬運車和棧板的示意圖。 FIG. 5 shows a schematic diagram of an automatic transport vehicle and pallets according to an embodiment of the present invention.
圖6根據本發明的一實施例繪示判斷物件深度的示意圖。 FIG. 6 is a schematic diagram of determining the depth of an object according to an embodiment of the present invention.
圖7和8根據本發明的一實施例繪示對應於不同深度的圖像的示意圖。 7 and 8 are schematic diagrams illustrating images corresponding to different depths according to an embodiment of the present invention.
圖9根據本發明的一實施例繪示一種叉取棧板的方法的流程圖。 FIG. 9 shows a flowchart of a method for forking a pallet according to an embodiment of the present invention.
為了使本發明之內容可以被更容易明瞭,以下特舉實施 例作為本發明確實能夠據以實施的範例。另外,凡可能之處,在圖式及實施方式中使用相同標號的元件/構件/步驟,係代表相同或類似部件。 In order to make the content of the present invention more understandable, the following special examples are implemented Examples are given as examples of how the invention can actually be practiced. In addition, wherever possible, elements/components/steps using the same reference numerals in the drawings and embodiments represent the same or similar parts.
圖1根據本發明的一實施例繪示一種用於叉取棧板的自動搬運車100的示意圖。自動搬運車100可包含處理器110、儲存媒體120、收發器130、深度攝影機(depth camera)140、牙叉150以及車輪160。在一實施例中,自動搬運車100還可包含速度感測器170。自動搬運車100例如是叉車(forklift)或堆高機(fork truck)等。
FIG. 1 shows a schematic diagram of an
處理器110例如是中央處理單元(central processing unit,CPU),或是其他可程式化之一般用途或特殊用途的微控制單元(micro control unit,MCU)、微處理器(microprocessor)、數位信號處理器(digital signal processor,DSP)、可程式化控制器、特殊應用積體電路(application specific integrated circuit,ASIC)、圖形處理器(graphics processing unit,GPU)、影像訊號處理器(image signal processor,ISP)、影像處理單元(image processing unit,IPU)、算數邏輯單元(arithmetic logic unit,ALU)、複雜可程式邏輯裝置(complex programmable logic device,CPLD)、現場可程式化邏輯閘陣列(field programmable gate array,FPGA)或其他類似元件或上述元件的組合。處理器110可耦接至儲存媒體120、收發器130、深度攝影機140、牙叉150、車輪160以及速度感測器170,並且存取和執行儲存於儲存媒體120中的多個模組和各種應用程式。
The
儲存媒體120例如是任何型態的固定式或可移動式的隨機存取記憶體(random access memory,RAM)、唯讀記憶體(read-only memory,ROM)、快閃記憶體(flash memory)、硬碟(hard disk drive,HDD)、固態硬碟(solid state drive,SSD)或類似元件或上述元件的組合,而用於儲存可由處理器110執行的多個模組或各種應用程式。在本實施例中,儲存媒體120可儲存包含機器學習模型121等多個模組,其功能將於後續說明。
The
收發器130以無線或有線的方式傳送及接收訊號。收發器130還可以執行例如低噪聲放大、阻抗匹配、混頻、向上或向下頻率轉換、濾波、放大以及類似的操作。
The
深度攝影機140用以擷取物件的深度圖。深度攝影機140可包含RGBD鏡頭的攝影機、紅外線鏡頭的攝影機或多鏡頭的攝影機等,本發明不限於此。
The
牙叉150用以叉取棧板。當自動搬運車100欲移動棧板時,處理器110可控制牙叉150插入棧板的叉口(bay)中。處理器110可控制牙叉150垂直地移動以使棧板靠近或遠離地面。
速度感測器170可包含加速度計或陀螺儀等。速度感測器170用以感測自動搬運車100的線速度(linear velocity)與角速度(angular velocity),並將線速度和角速度回報給處理器110。
The
車輪160可包含主動輪(driving wheel)161及從動輪(driven wheel)162。圖2根據本發明的一實施例繪示自動搬運車的車輪配置的示意圖。在本實施例中,假設自動搬運車100行駛
的地面為笛卡兒座標系的XZ平面且Y軸與地面垂直。自動搬運車100可具有單一個設置在前方的主動輪161以及兩個設置在後方的從動輪162。主動輪161的輪軸61與從動輪的輪軸62相距距離D。處理器110可耦接至主動輪161並且控制主動輪的轉速以及偏擺角(yaw),藉以控制自動搬運車100移動速度和移動方向。本實施例叉車為三輪,其主動輪有一輪,直接控制叉車移動角度,其動力學與三輪車一樣;若為四輪時,其主動輪為兩輪,其動力學與一般汽車一樣。
The
圖3根據本發明的一實施例繪示移動棧板的方法的流程圖,其中所述方法可由如圖1所示的自動搬運車100實施。在步驟S301中,處理器110可通過收發器130接收命令,其中所述命令指示自動搬運車100移動到指定地點。舉例來說,若使用者欲搬運位於指定地點的棧板,使用者可操作終端裝置(例如:電腦或智慧型手機)發送對應於指定地點的命令給自動搬運車100。
FIG. 3 shows a flowchart of a method for moving pallets according to an embodiment of the present invention, wherein the method can be implemented by the
在步驟S302中,處理器110可根據命令控制主動輪161以將自動搬運車100移動到指定地點。處理器110可根據如公告號第I671610號的台灣專利所揭露的方法來控制自動搬運車100的移動。圖4根據本發明的一實施例繪示自動搬運車100的旋轉半徑R和偏擺角δ的示意圖。假設自動搬運車100的座標為(x J ,z J )且偏擺角為δ J ,則處理器110可根據方程式(1)、(2)、(3)、(4)和(5)來控制主動輪161的轉速以及偏擺角,藉以將自動搬運車100以偏擺角δ K 移動到座標(x K ,z K )。
In step S302 , the
回到圖3,在自動搬運車100移動到指定地點後,在步驟S303中,處理器110可通過深度攝影機140擷取深度圖(depth map),並且自深度圖取得分別對應於多個深度的多個圖像,其中深度圖可包含棧板。圖5根據本發明的一實施例繪示自動搬運車100和棧板200的示意圖。棧板200的長度為L,寬度為W且高度為H。棧板200可包含用以容納牙叉150的叉口210。深度攝影機140可擷取包含棧板200的深度圖。處理器110可根據預設間距m決定多個深度。多個深度中的鄰近深度可彼此相距預設間距
m。
Returning to FIG. 3, after the
舉例來說,假設深度攝影機140的光軸141與Z軸平行。處理器110可根據預設間距m從深度圖中取樣出對應於深度Z=0的圖像,對應於深度Z=m的圖像,對應於深度Z=2m的圖像以及對應於深度Z=3m的圖像等分別對應於不同深度的多個圖像。為了避免所有取樣出的圖像都未出現棧板200,處理器110可根據棧板200的尺寸來決定預設間距m。在一實施例中,處理器110可根據方程式(6)和(7)決定預設間距m,其中L為棧板200的長度,d為棧板200偏移的距離,α為係數(例如:α=3),並且θ為深度攝影機140的光軸141與叉口210的中心軸211之間的角度,其中叉口210的中心軸211可與棧板200的短邊(即:長度為W的邊)平行。
For example, assume that the
d=L.sinθ...(6) d = L . sin θ ... (6)
m=α.d...(7) m = α . d ...(7)
處理器110自深度圖中所擷取出的圖像上的每一個像素都對應於相同的深度。圖6根據本發明的一實施例繪示判斷物件深度的示意圖。以對應於棧板200的頂點的像素P1為例。假設深度攝影機140的光軸141與Z軸平行。若處理器110通過深度攝影機140拍攝棧板200的頂點,則深度攝影機140所產生的深度圖可包含對應於頂點之像素P1的橫座標值(即:X座標值)、像素P1的縱座標值(即:Y座標值)以及像素P1與深度攝影機140之間的距離d3等資訊,如圖6所示。處理器110可基於方程式
(8)和(9)而根據像素P1的橫座標值、像素P1的縱座標值以及距離d3判斷像素P1對應於深度d1。因此,若處理器110欲擷取對應於深度d1的圖像,則處理器110可從深度圖中擷取出像素P1以產生所述圖像。處理器110自深度圖中擷取出的圖像可與XY平面平行。
Each pixel on the image extracted by the
回到圖3,在取得分別對應於多個深度的多個圖像後,在步驟S304中,處理器110可將多個圖像輸入至機器學習模型121以產生對應於棧板200的至少一定界框,其中所述至少一定界框用以產生棧板200的三維定位資訊。機器學習模型121例如是包含YOLO模型的物件辨識(object detection)模型,但本發明不限於此。圖7和8根據本發明的一實施例繪示對應於不同深度的圖像的示意圖。假設處理器110自深度圖中擷取的多個圖像包含分別對應於不同深度的圖像71與圖像72,其中圖像71對應於深度Z=2m且圖像72對應於深度Z=3m。處理器110可將圖像71輸入至機器學習模型121以產生定界框300以及定界框400。此外,機器學習模型121還可產生對應於定界框300的可信度(confidence
score)以及對應於定界框400的可信度。另一方面,處理器110可將圖像72輸入至機器學習模型121以產生定界框500以及對應於定界框500的可信度。
Returning to FIG. 3 , after obtaining multiple images respectively corresponding to multiple depths, in step S304, the
回到圖3,在步驟S305中,處理器110可從多個圖像中選擇一個圖像。受選的圖像可包含棧板200,並可用以判斷棧板200的三維定位資訊。在一實施例中,處理器110可根據對應於圖像的定界框的可信度選擇圖像。具體來說,處理器110可從多個圖像中選出包含了對應於最大可信度的定界框的圖像以作為受選圖像。以圖7和圖8為例,假設圖像71中的定界框300的可信度大於定界框400的可信度,並且圖像71中的定界框300的可信度也大於圖像72中的定界框500的可信度。據此,處理器110可從圖像71和圖像72中選擇圖像71以作為受選圖像。
Returning to FIG. 3 , in step S305 , the
在步驟S306中,處理器110可判斷受選圖像是否包含多個定界框。若受選圖像包含多個定界框,則進入步驟S308。若受選圖像包含單一個定界框而不包含多個定界框,則進入步驟S307。以圖像71為例。假設圖像71為受選圖像,由於圖像71包含了定界框300和定界框400等兩個定界框,故處理器110可判斷受選圖像包含多個定界框。據此,處理器110可執行步驟S308。以圖像72為例。假設圖像72為受選圖像,由於圖像72包含一個定界框500,故處理器110可判斷受選圖像不包含多個定界框。據此,處理器110可執行步驟S307。
In step S306, the
在步驟S307中,處理器110可根據受選圖像中的定界框
產生棧板200的三維定位資訊,其中三維定位資訊可包含棧板200的橫軸座標值(即:X座標值)、縱座標值(即:Y座標值)以及深度(即:Z座標值)。以圖8的圖像72為例,假設圖像72為受選圖像。由於處理器110已知圖像72對應於深度Z=3m,故處理器110可判斷棧板200的深度為Z=3m。另一方面,處理器110可根據定界框500判斷棧板200的橫座標值與縱座標值。在取得棧板200的橫座標值、縱座標值以及深度後,處理器110可產生包含棧板200的橫座標值、縱座標值以及深度的三維定位資訊。
In step S307, the
在步驟S308中,處理器110可計算各個定界框(或定界框的中心點)與圖像的中心點之間的距離以產生多個距離,並且判斷所述多個距離是否相同。若所述多個距離都相同,則進入步驟S310。若所述多個距離不相同,則進入步驟S309。以圖像71為例,處理器110可計算定界框300的中心點310與圖像71的中心點O之間的距離A1以及定界框400的中心點410與圖像71的中心點O之間的距離A2。若距離A1與距離A2相同,則進入步驟S310。若距離A1與距離A2不同,則進入步驟S309。
In step S308, the
在步驟S309中,處理器110可從多個定界框中選出距離圖像的中心點最近的定界框以作為受選定界框,並可根據受選定界框產生棧板200的三維定位資訊。以圖像71為例,處理器110可響應於對應於定界框300的距離A1小於對應於定界框400的距離A2而從定界框300與定界框400中選出定界框300以作為受選定界框。據此,處理器110可根據定界框300產生棧板200的
三維定位資訊。
In step S309, the
在步驟S310中,處理器110可判斷分別對應於多個定界框的多個可信度是否相同。若多個可信度相同,則進入步驟S312。若多個可信度不相同,則進入步驟S311。以圖像71為例,若定界框300的可信度與定界框400的可信度相同,則進入步驟S312。若定界框300的可信度與定界框400的可信度不相同,則進入步驟S311。
In step S310, the
在步驟S311中,處理器110可從多個定界框中選出具有最大可信度的定界框以作為受選定界框,並可根據受選定界框產生棧板200的三維定位資訊。若圖像中的各個定界框與圖像的中心點之間的距離相同,代表處理器110並無法根據距離選擇較佳的定界框。因此,處理器110將選擇具有最大可信度的定界框以作為受選定界框。以圖像71為例,處理器110可響應於定界框300的可信度大於定界框400的可信度而從定界框300與定界框400中選出定界框300以作為受選定界框。據此,處理器110可根據定界框300產生棧板200的三維定位資訊。
In step S311 , the
在步驟S312中,處理器110可根據預設規則(或隨機地)從多個定界框中選出受選定界框,並且根據受選定界框產生棧板200的三維定位資訊。預設規則例如是「選擇具有最小橫座標值的定界框以作為受選定界框」。以圖像71為例,處理器110可響應於定界框300的橫座標值小於定界框400的橫座標值而從定界框300以及定界框400中選出定界框300以作為受選定界框。據此,
處理器110可根據定界框300產生棧板200的三維定位資訊。
In step S312 , the
為了降低辨識棧板200或將牙叉150插入叉口210的難易度,處理器110可根據叉口210的中心軸211與深度攝影機140的光軸141之間的角度θ判斷是否移動自動搬運車100。具體來說,在步驟S313中,處理器110可判斷叉口210的中心軸211與深度攝影機140的光軸141之間的角度θ是否大於角度閾值。若角度θ大於角度閾值,則進入步驟S314。若角度θ小於或等於角度閾值,則進入步驟S315。
In order to reduce the difficulty of identifying the
在步驟S314中,處理器110可控制主動輪161以移動自動搬運車100,藉以縮小角度θ,直到角度θ小於或等於角度閾值。接著,處理器110可重新執行圖3的流程以嘗試叉取棧板200。
In step S314 , the
在步驟S315中,處理器110可根據棧板200的三維定位資訊控制主動輪161以及牙叉150以移動棧板200。具體來說,處理器110可控制主動輪161移動自動搬運車100以將牙叉150插入叉口210中。接著,處理器110可控制牙叉150上升以舉起棧板200。
In step S315 , the
圖9根據本發明的一實施例繪示一種叉取棧板的方法的流程圖,其中所述方法可由如圖1所示的自動搬運車100實施。在步驟S901中,利用深度攝影機擷取深度圖,其中深度圖包含棧板。在步驟S902中,自深度圖取得分別對應於多個深度的多個圖像。在步驟S903中,將多個圖像輸入至機器學習模型以產生棧板的三維定位資訊。在步驟S904中,根據三維定位資訊控制自動搬
運車的主動輪以及牙叉以移動棧板。
FIG. 9 shows a flow chart of a method for forking pallets according to an embodiment of the present invention, wherein the method can be implemented by the
綜上所述,本發明的自動搬運車可根據命令自動地移動到指定地點,並且偵測指定地點是否存在棧板。若棧板的叉口與自動搬運車的牙叉之間的角度過大,自動搬運車可進行移動以縮小所述角度,以利牙叉叉取棧板。自動搬運車可通過影像分層演算法以從深度攝影機產生的深度圖中擷取出多個圖像,並且根據這些圖像判斷棧板的叉口位置,藉以增加自動搬運車對不同環境中的棧板或對不同材質的棧板的辨識準確度。自動搬運車可根據叉口位置控制車輪以及牙叉以自動地移動棧板。 To sum up, the automatic transport vehicle of the present invention can automatically move to a designated location according to commands, and detect whether there is a pallet at the designated location. If the angle between the fork of the pallet and the fork of the automatic pallet truck is too large, the automatic pallet truck can move to reduce the angle so that the pallet can be picked up by the forks of the pallet. The automatic pallet truck can extract multiple images from the depth map generated by the depth camera through the image layering algorithm, and judge the position of the fork of the pallet based on these images, so as to increase the automatic pallet truck's ability to stack in different environments board or the recognition accuracy of pallets of different materials. The automatic pallet truck can control the wheels and tooth forks according to the position of the fork to move the pallet automatically.
S901、S902、S903、S904:步驟 S901, S902, S903, S904: steps
Claims (14)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111100044A TWI799051B (en) | 2022-01-03 | 2022-01-03 | Automatic guided vehicle and method for forking pallet |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111100044A TWI799051B (en) | 2022-01-03 | 2022-01-03 | Automatic guided vehicle and method for forking pallet |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI799051B true TWI799051B (en) | 2023-04-11 |
TW202327977A TW202327977A (en) | 2023-07-16 |
Family
ID=86948765
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111100044A TWI799051B (en) | 2022-01-03 | 2022-01-03 | Automatic guided vehicle and method for forking pallet |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI799051B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111766881A (en) * | 2020-06-29 | 2020-10-13 | 云南电网有限责任公司大理供电局 | Multi-intelligent forklift combined operation control system |
US20210087033A1 (en) * | 2019-09-20 | 2021-03-25 | Hitachi, Ltd. | Machine learning method, forklift control method, and machine learning apparatus |
JP2021163299A (en) * | 2020-04-01 | 2021-10-11 | 三菱ロジスネクスト株式会社 | Image storage system and image storage program for cargo handling vehicle |
-
2022
- 2022-01-03 TW TW111100044A patent/TWI799051B/en active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210087033A1 (en) * | 2019-09-20 | 2021-03-25 | Hitachi, Ltd. | Machine learning method, forklift control method, and machine learning apparatus |
JP2021163299A (en) * | 2020-04-01 | 2021-10-11 | 三菱ロジスネクスト株式会社 | Image storage system and image storage program for cargo handling vehicle |
CN111766881A (en) * | 2020-06-29 | 2020-10-13 | 云南电网有限责任公司大理供电局 | Multi-intelligent forklift combined operation control system |
Also Published As
Publication number | Publication date |
---|---|
TW202327977A (en) | 2023-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9659217B2 (en) | Systems and methods for scale invariant 3D object detection leveraging processor architecture | |
KR101772367B1 (en) | Combination of stereo and structured-light processing | |
US9802317B1 (en) | Methods and systems for remote perception assistance to facilitate robotic object manipulation | |
US9630316B2 (en) | Real-time determination of object metrics for trajectory planning | |
US9630320B1 (en) | Detection and reconstruction of an environment to facilitate robotic interaction with the environment | |
Kelly et al. | Field and service applications-an infrastructure-free automated guided vehicle based on computer vision-an effort to make an industrial robot vehicle that can operate without supporting infrastructure | |
CN107610176A (en) | A kind of pallet Dynamic Recognition based on Kinect and localization method, system and medium | |
US10102629B1 (en) | Defining and/or applying a planar model for object detection and/or pose estimation | |
US20210190535A1 (en) | Information processing apparatus, information processing method, and medium | |
EP2677274B1 (en) | System and method for guiding a mobile device | |
Sokolov et al. | Analysis of ROS-based Visual and Lidar Odometry for a Teleoperated Crawler-type Robot in Indoor Environment. | |
WO2023173950A1 (en) | Obstacle detection method, mobile robot, and machine readable storage medium | |
CN113253737A (en) | Shelf detection method and device, electronic equipment and storage medium | |
CN116309719A (en) | Target tracking method, device, computer equipment and storage medium | |
CN115223039A (en) | Robot semi-autonomous control method and system for complex environment | |
TWI799051B (en) | Automatic guided vehicle and method for forking pallet | |
JP7192706B2 (en) | Position and orientation estimation device | |
CN116309882A (en) | Tray detection and positioning method and system for unmanned forklift application | |
CN116803631A (en) | Autonomous system and method performed by an autonomous system | |
US20230038578A1 (en) | Systems and Methods for Image Based Perception | |
CN115116048A (en) | Method and system for identifying and positioning pallet based on point cloud mass center | |
WO2024053150A1 (en) | Picking system | |
US20240017976A1 (en) | Advanced material handling vehicle | |
CN116778457B (en) | Automatic parking auxiliary control system and device for vehicle | |
US11966452B2 (en) | Systems and methods for image based perception |