TW201914782A - Holding position and posture instruction apparatus, holding position and posture instruction method, and robot system - Google Patents
Holding position and posture instruction apparatus, holding position and posture instruction method, and robot system Download PDFInfo
- Publication number
- TW201914782A TW201914782A TW107103224A TW107103224A TW201914782A TW 201914782 A TW201914782 A TW 201914782A TW 107103224 A TW107103224 A TW 107103224A TW 107103224 A TW107103224 A TW 107103224A TW 201914782 A TW201914782 A TW 201914782A
- Authority
- TW
- Taiwan
- Prior art keywords
- posture
- holding
- holding position
- manipulator
- input
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 38
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 230000036544 posture Effects 0.000 claims description 374
- 230000005484 gravity Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 24
- 238000012545 processing Methods 0.000 description 16
- 238000013459 approach Methods 0.000 description 10
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 5
- 238000009434 installation Methods 0.000 description 4
- 210000000707 wrist Anatomy 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000007429 general method Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1612—Programme controls characterised by the hand, wrist, grip control
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/39—Robotics, robotics to robotics hand
- G05B2219/39543—Recognize object and plan hand shapes in grasping movements
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/40—Robotics, robotics mapping to robotics vision
- G05B2219/40395—Compose movement with primitive movement segments from database
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
Description
本發明係關於把持零件之產業用機器人的把持位置姿勢教導裝置、把持位置姿勢教導方法及機器人系統。 The present invention relates to a holding position and posture teaching device, a holding position and posture teaching method, and a robot system of an industrial robot that holds parts.
以往,已知具備有把持零件並使之以預定的姿勢排列於預定的位置之機械手之產業用機器人。為了使如此的機器人執行預定的動作,要預先教導把持動作,惟,由於此教導作業花很多時間,所以有教導作業自動化、縮短時間之需求。就作業自動化、縮短時間之方法而言,已開發出一種根據預先登錄於機器人之零件的形狀資料、及機械手對於各零件的把持位置及把持姿勢(以下,統稱為把持位置姿勢)的資料,來使機器人執行把持動作之技術。 Conventionally, industrial robots equipped with a manipulator that grips parts and arranges them in predetermined positions at predetermined positions are known. In order for such a robot to perform a predetermined action, it is necessary to teach the holding action in advance. However, since this teaching operation takes a lot of time, there is a need to teach the operation automation and shorten the time. In terms of methods for automating operations and shortening time, a data has been developed based on the shape data of parts previously registered in the robot, and the holding position and holding posture (hereinafter, collectively referred to as holding position posture) of each part of the robot for each part. To enable the robot to perform a holding action.
專利文獻1中,具備登錄有複數個零件的形狀資料、及機械手對於各零件的把持位置姿勢之資料庫,從資料庫搜尋與把持對象的零件類似形狀的零件的形 狀資料,並使機器人執行對於類似形狀的零件之把持位置姿勢。專利文獻2中,具備登錄有複數個基本形狀模型、及機械手對於各基本形狀模型的把持位置姿勢之資料庫,將把持對象的零件與基本形狀模型對照而決定機械手的把持位置姿勢。此處所謂的基本形狀係例如圓柱、四角柱、圓筒等之三維的幾何元素的模型。 Patent Document 1 includes a database in which shape data of a plurality of parts is registered, and a gripping position and posture of each part of the manipulator for each part, and searches the database for shape data of parts having a shape similar to the part to be gripped, and causes the robot to execute The holding position and posture of similar shaped parts. Patent Literature 2 includes a database in which a plurality of basic shape models and the grip positions and postures of the manipulator for each basic shape model are registered, and the parts to be grasped are compared with the basic shape models to determine the grip position and posture of the robot. The basic shape referred to here is a model of three-dimensional geometric elements such as a cylinder, a square column, a cylinder, and the like.
(專利文獻1)日本特開2008-15683號公報 (Patent Document 1) Japanese Unexamined Patent Publication No. 2008-15683
(專利文獻2)WO 2009/113339號公報 (Patent Document 2) WO 2009/113339
然而,在零件以雜亂堆疊的散亂堆積狀態投入生產之情況,難以預先將因應於零件可能呈現的各姿勢之機械手的把持位置姿勢都登錄在資料庫,在把持位置姿勢未登錄在資料庫中之情況,會有機器人無法進行把持動作之問題。例如,具有預定為供機器人抓取的抓取部之零件以傾斜狀態投入生產,該抓取部接觸於平面之情況,就無法以資料庫中登錄的把持該抓取部之把持位置姿勢執行把持動作。 However, when the parts are put into production in a disorderly stacked state, it is difficult to register the holding position and posture of the manipulator corresponding to each posture that the part may assume in the database, and the holding position and posture are not registered in the database. In the case of the above, there will be a problem that the robot cannot perform the holding operation. For example, if a part with a gripping part that is scheduled to be gripped by a robot is put into production at an inclined state, and the gripping part is in contact with a flat surface, the gripping position and posture of the gripping part registered in the database cannot be performed. action.
本發明係為了解決上述課題而完成者,其目的在於提供針對投入的零件可能呈現的各姿勢來產生可適用的機械手的把持位置姿勢之把持位置姿勢教導裝置。 此外,其目的在於提供把持位置姿勢教導方法。進一步地提供採用了把持位置姿勢教導裝置之機器人系統。 The present invention has been completed to solve the above-mentioned problems, and an object of the present invention is to provide a gripping position and posture teaching device for generating a gripping position and posture of an applicable manipulator for each posture that the input component may assume. In addition, the purpose is to provide a method for teaching the holding position and posture. Further, a robot system adopting a holding position and posture teaching device is provided.
本發明之把持位置姿勢教導裝置係具備:從表示零件的形狀之零件形狀資料,算出零件的投入姿勢之零件投入姿勢算出部;根據表示機械手的形狀之機械手資料,選定相對於投入姿勢之機械手的把持姿勢之把持姿勢選定部;將匯整了以把持姿勢來把持零件之機械手的把持部與零件之供機械手把持的被把持部分別一致之位置而得出的區域,抽出作為把持位置區域之把持位置區域抽出部;以及在把持位置區域內選定以機械手把持零件之把持位置,且針對每個投入姿勢輸出至少一個把持姿勢中的把持位置,作為機械手的把持位置姿勢之把持位置姿勢輸出部。 The holding position and posture teaching device of the present invention includes: a part input posture calculation unit that calculates the input posture of the part from the part shape data indicating the shape of the part; and selects the position relative to the input posture based on the data of the manipulator indicating the shape of the manipulator The selected part of the holding posture of the holding posture of the manipulator; the area obtained by arranging the positions where the holding part of the manipulator holding the part in the holding posture and the held part of the part for holding by the manipulator respectively coincide will be extracted as The holding position area extraction portion of the holding position area; and selecting the holding position of the part held by the robot in the holding position area, and outputting the holding position in at least one holding position for each input posture as the holding position posture of the robot Holding position and posture output unit.
本發明之把持位置姿勢教導方法係包括:從表示零件的形狀之零件形狀資料,算出零件的投入姿勢之零件投入姿勢算出步驟;根據表示機械手的形狀之機械手資料,選定相對於投入姿勢之機械手的把持姿勢之把持姿勢選定步驟;將匯整了以把持姿勢來把持零件之機械手的把持部與零件之供機械手把持的被把持部分別一致之位置而得出的區域,抽出作為把持位置區域之把持位置區域抽出步驟;以及在把持位置區域內選定以機械手把持零件之把持位置,且針對每個投入姿勢輸出至少一個把持姿勢中的把持位置,作為機械手的把持位置姿勢之把持位置姿 勢輸出步驟。 The teaching method of the holding position and posture of the present invention includes: a step of calculating a part input posture for calculating the input posture of the part from the part shape data indicating the shape of the part; and selecting the position relative to the input posture based on the data of the robot hand indicating the shape of the manipulator Steps for selecting the holding posture of the holding posture of the manipulator; the area obtained from the positions where the holding part of the manipulator that holds the part in the holding posture and the held part of the part that is held by the manipulator for holding the manipulator will be taken as Steps for extracting the holding position area of the holding position area; and selecting the holding position of the part held by the robot in the holding position area, and outputting the holding position in at least one holding position for each input posture as the holding position posture of the robot Steps to output the holding position and posture.
本發明之機器人系統係具備:根據零件形狀資料及機械手資料產生機械手的把持位置姿勢之把持位置姿勢教導裝置;認識有關於投入的零件的位置及姿勢的資訊之感測器;以及根據來自感測器之資訊及把持位置姿勢教導裝置所產生的把持位置姿勢來把持零件之機器人。 The robot system of the present invention is provided with: a holding position and posture teaching device for generating a holding position and posture of a manipulator based on part shape data and manipulator data; a sensor that recognizes information about the position and posture of the input part; The information of the sensor and the holding position and posture generated by the holding position and posture teaching device are robots that hold parts.
根據本發明,可針對零件可能呈現的各姿勢產生可適用的把持位置姿勢,即使把持位置姿勢未登錄在資料庫之情況,也可教導機器人把持位置姿勢。 According to the present invention, an applicable holding position posture can be generated for each posture that the part may assume. Even if the holding position posture is not registered in the database, the robot can be taught the holding position posture.
10‧‧‧零件 10‧‧‧Parts
10a至10d‧‧‧側面(被把持部) 10a to 10d‧‧‧Side (holding part)
20‧‧‧機械手 20‧‧‧manipulator
20a、20b‧‧‧側面(把持部) 20a, 20b‧‧‧Side (holding part)
21‧‧‧指部 21‧‧‧ Finger
22‧‧‧手腕部 22‧‧‧Wrist
23‧‧‧缺口部 23‧‧‧Notch
24‧‧‧吸取部 24‧‧‧Suction Department
31‧‧‧記憶部 31‧‧‧ Memory Department
32‧‧‧處理部 32‧‧‧ Processing Department
50‧‧‧感測器 50‧‧‧Sensor
100‧‧‧機器人系統 100‧‧‧Robot system
110‧‧‧零件投入台 110‧‧‧Parts input station
120‧‧‧暫置台 120‧‧‧ temporary station
130‧‧‧改換姿勢治具 130‧‧‧Change posture fixture
140‧‧‧排列台 140‧‧‧Arrangement table
150‧‧‧三維視覺感測器 150‧‧‧3D visual sensor
160‧‧‧二維視覺感測器 160‧‧‧Two-dimensional visual sensor
200‧‧‧機器人 200‧‧‧Robot
201‧‧‧本體 201‧‧‧Body
202‧‧‧控制部 202‧‧‧Control Department
300‧‧‧把持位置姿勢教導裝置 300‧‧‧ Holding position and posture teaching device
301‧‧‧零件形狀資料 301‧‧‧Part shape data
302‧‧‧機械手資料 302‧‧‧manipulator information
303‧‧‧把持位置姿勢資料 303‧‧‧ Holding position information
304‧‧‧把持姿勢資料 304‧‧‧ holding posture information
310‧‧‧零件投入姿勢算出部 310‧‧‧Part input posture calculation unit
311‧‧‧資料庫檢索部 311‧‧‧Database Search Department
320‧‧‧把持姿勢選定部 320‧‧‧Control posture selection
321‧‧‧把持姿勢輸入部 321‧‧‧Control posture input unit
330‧‧‧把持位置區域抽出部 330‧‧‧ Extraction section of holding position area
340‧‧‧把持位置姿勢輸出部 340‧‧‧Control position posture output unit
341‧‧‧把持位置姿勢調整部 341‧‧‧ Holding position and posture adjustment section
第1圖係具備本發明的實施形態1之把持位置姿勢教導裝置之機器人系統的概略構成圖。 FIG. 1 is a schematic configuration diagram of a robot system equipped with a grip position and posture teaching device according to Embodiment 1 of the present invention.
第2圖係本發明的實施形態1之把持位置姿勢教導裝置的概略構成圖。 Fig. 2 is a schematic configuration diagram of a grip position and posture teaching device according to Embodiment 1 of the present invention.
第3圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 3 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第4圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 4 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第5圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 5 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第6圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 6 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第7圖係顯示本發明的實施形態1之機械手與零件的一例之示意圖。 FIG. 7 is a schematic diagram showing an example of a robot and parts according to Embodiment 1 of the present invention.
第8圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 8 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第9圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 9 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第10圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 10 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第11圖係顯示本發明的實施形態1之把持位置姿勢教導裝置的處理程序的一例之流程圖。 FIG. 11 is a flowchart showing an example of the processing procedure of the grip position and posture teaching device according to Embodiment 1 of the present invention.
第12圖係顯示本發明的實施形態1之把持位置姿勢教導裝置的處理程序的一例之示意圖。 Fig. 12 is a schematic diagram showing an example of the processing procedure of the grip position and posture teaching device according to the first embodiment of the present invention.
第13圖係顯示本發明的實施形態1之機械手的一例之示意圖。 Fig. 13 is a schematic diagram showing an example of a manipulator according to Embodiment 1 of the present invention.
第14圖係顯示本發明的實施形態1之零件的把持位置姿勢的一例之示意圖。 Fig. 14 is a schematic diagram showing an example of the holding position and posture of the component according to the first embodiment of the present invention.
第15圖係顯示採用本發明的實施形態2之把持位置姿勢教導裝置之機器人系統的一例之示意圖。 Fig. 15 is a schematic diagram showing an example of a robot system using a grip position and posture teaching device according to Embodiment 2 of the present invention.
第16圖係本發明的實施形態3之把持位置姿勢教導裝置的概略構成圖。 Fig. 16 is a schematic configuration diagram of a grip position and posture teaching device according to Embodiment 3 of the present invention.
第17圖係本發明的實施形態4之把持位置姿勢教導裝置的概略構成圖。 Fig. 17 is a schematic configuration diagram of a grip position and posture teaching device according to Embodiment 4 of the present invention.
第18圖係本發明的實施形態5之把持位置姿勢教導裝置的概略構成圖。 Fig. 18 is a schematic configuration diagram of a grip position and posture teaching device according to Embodiment 5 of the present invention.
第19圖係顯示本發明的實施形態之吸取式機械手的一例之示意圖。 Fig. 19 is a schematic diagram showing an example of a suction robot according to an embodiment of the present invention.
以下,利用圖式,具體說明本發明的實施形態之把持位置姿勢教導裝置、把持位置姿勢教導方法、及具備有把持位置姿勢教導裝置之機器人系統。 Hereinafter, the drawings will be used to specifically describe a grip position and posture teaching device, a grip position and posture teaching method, and a robot system equipped with a grip position and posture teaching device according to an embodiment of the present invention.
第1圖係具備本發明的實施形態1之把持位置姿勢教導裝置之機器人系統的概略構成圖。如第1圖所示,機器人系統100係包含機器人200、把持位置姿勢教導裝置300、及感測器50而構成,並連接成可相通訊。機器人系統100係以把持位置姿勢教導裝置300所產生的把持位置姿勢使機器人200動作。 FIG. 1 is a schematic configuration diagram of a robot system equipped with a grip position and posture teaching device according to Embodiment 1 of the present invention. As shown in FIG. 1, the robot system 100 includes a robot 200, a holding position and posture teaching device 300, and a sensor 50, and is connected to communicate with each other. The robot system 100 operates the robot 200 in the grasping position and posture generated by the grasping position and posture teaching device 300.
機器人200係例如為垂直多關節型機器人,具有機器人本體201、及機器人控制部202。機器人本體201係具備任意形狀的機械手20,該機械手20係具有把持零件10(未圖示)的把持面。機械手20係具備有例如可開閉的指部21,且朝向本體201之驅動旋轉的手腕部22的旋轉軸方向而安裝。機器人控制部202係具備記述有機器人200的動作之控制程式,根據從感測器50、把持位置姿勢教導裝置300等取得的資訊而進行機器人200的驅動的控制。 The robot 200 is, for example, a vertical articulated robot, and has a robot body 201 and a robot control unit 202. The robot body 201 includes a manipulator 20 having an arbitrary shape, and the manipulator 20 has a grip surface for gripping a component 10 (not shown). The manipulator 20 is provided with, for example, a finger 21 that can be opened and closed, and is mounted in the direction of the rotation axis of the wrist 22 that is driven to rotate by the body 201. The robot control unit 202 is provided with a control program in which the operation of the robot 200 is described, and controls the driving of the robot 200 based on information obtained from the sensor 50, the grip position and posture teaching device 300, and the like.
感測器50係計測欲把持的零件10的二維 影像、三維資料等,認識零件10的位置及姿勢。零件10的認識結果係在感測器50或機器人控制部202中變換為表現機器人200的位置姿勢之座標系的資料。根據把持位置姿勢教導裝置300所產生的機器手20的把持位置姿勢及來自感測器50之認識結果,算出感測器50所認識的零件10的位置姿勢。 The sensor 50 measures two-dimensional images, three-dimensional data, etc. of the part 10 to be grasped, and recognizes the position and posture of the part 10. The recognition result of the part 10 is converted into data of a coordinate system representing the position and posture of the robot 200 in the sensor 50 or the robot control unit 202. The position and posture of the component 10 recognized by the sensor 50 are calculated based on the grasped position and posture of the robot hand 20 generated by the holding position and posture teaching device 300 and the recognition result from the sensor 50.
接著,針對教導機器人200把持位置姿勢之把持位置姿勢教導裝置300的構成進行說明。把持位置姿勢教導裝置300係例如具備有記憶部31、處理部32等之演算處理裝置。把持位置姿勢教導裝置300除了上述部件之外,更佳為還設有具備顯示零件10及機械手20之3D顯示畫面、輸入按鈕等之使用者圖像介面(Graphical User Interface;GUI)。 Next, the configuration of the holding position and posture teaching device 300 that teaches the robot 200 to hold the position and posture will be described. The holding position and posture teaching device 300 is an arithmetic processing device including, for example, a memory unit 31 and a processing unit 32. In addition to the above-mentioned components, the holding position and posture teaching device 300 is further preferably provided with a graphical user interface (GUI) including a 3D display screen of the display part 10 and the manipulator 20, an input button, and the like.
記憶部31中儲存有例如零件形狀資料301、機械手資料302、及產生把持位置姿勢之程式等。處理部32係根據記憶部31中儲存的零件形狀資料301及機械手資料302來進行程式的演算處理。零件形狀資料301係有關於零件10之三維形狀資料。另外,機械手資料302係有關於機械手20之三維形狀資料。機械手資料302中,除了三維形狀資料之外,較佳為還包含有:可與零件10接觸之機械手20的把持面;指部21的動作方向;及機械手20之對於機器人200的安裝部起指向機械手20的前端之方向(以下,簡稱為安裝方向)等之有關於機械手20之附加資訊。 The memory section 31 stores, for example, part shape data 301, manipulator data 302, and a program that generates a holding position and posture. The processing unit 32 performs program calculation processing based on the part shape data 301 and the robot data 302 stored in the memory unit 31. The part shape information 301 is the three-dimensional shape information about the part 10. In addition, the manipulator data 302 is data about the three-dimensional shape of the manipulator 20. In addition to the three-dimensional shape data, the manipulator data 302 preferably includes: the gripping surface of the manipulator 20 that can contact the part 10; the movement direction of the finger 21; and the installation of the manipulator 20 to the robot 200 The part points to the direction of the front end of the manipulator 20 (hereinafter, simply referred to as the installation direction), etc., which has additional information about the manipulator 20.
以下記載的把持位置姿勢教導裝置300的說明中,若沒有特別的記載,零件10及機械手20皆表示以三維形狀資料規定之虛擬空間上的零件模型及機械手模型。另外,把持位置姿勢係指虛擬的空間上之機械手20相對於零件10之相對的位置及姿勢。位置可用任意的三維座標系加以表現,姿勢可用例如繞著各軸的旋轉量之參數加以表現。 In the description of the holding position and posture teaching device 300 described below, if there is no special description, both the part 10 and the manipulator 20 represent a part model and a manipulator model on a virtual space defined by three-dimensional shape data. In addition, the holding position and posture refer to the relative position and posture of the robot 20 relative to the component 10 in the virtual space. The position can be expressed by an arbitrary three-dimensional coordinate system, and the posture can be expressed by parameters such as the amount of rotation around each axis.
接著,針對執行把持位置姿勢教導裝置300的機能之構成進行說明。第2圖係顯示把持位置姿勢教導裝置300之概略構成圖。 Next, a description will be given of the functional configuration of the device 300 for performing the grip position and posture teaching. FIG. 2 is a schematic configuration diagram showing the holding position and posture teaching device 300.
零件投入姿勢算出部310係取得記憶部31中儲存的零件形狀資料301,將投入機器人系統100之零件10的姿勢分類,並分別算出所分類出的投入姿勢。投入姿勢的分類及算出方法,係依零件10以散亂堆積的狀態投入生產之情況、及零件10以姿勢雖不整齊但未重疊在平面上的形態投入生產之情況,採用不同的方法。 The part input posture calculation unit 310 obtains the part shape data 301 stored in the memory unit 31, classifies the posture of the part 10 input into the robot system 100, and calculates the classified input postures respectively. The classification and calculation method of the input posture adopt different methods according to the case where the part 10 is put into production in a state of being scattered and stacked, and the case where the part 10 is put into production in a form where the posture is not regular but does not overlap on the plane.
零件10以散亂堆積的狀態投入生產之情況,例如,相對於機械手20接近零件10之方向,以相反方向作為零件10的方向而進行投入姿勢的分類。例如,如第3圖所示,將固定於零件10之直角座標系P的座標軸設為(Px,Py,Pz),將機器人系統100的直角座標系W的座標軸設為(Wx,Wy,Wz)。此時,在機械手20的接近方向為Wz的負方向之情況下,固定於零件10之直角座標系P而表示Wz的正方向之向量A係零件10的方向。如此,在以 散亂堆積的狀態投入生產之情況,係根據相對於接近方向之零件10的方向而進行投入姿勢之分類。 When the parts 10 are put into production in a state of being scattered and stacked, for example, with respect to the direction in which the robot 20 approaches the parts 10, the input posture is classified with the opposite direction as the direction of the parts 10. For example, as shown in FIG. 3, the coordinate axis of the rectangular coordinate system P fixed to the part 10 is set to (Px, Py, Pz), and the coordinate axis of the rectangular coordinate system W of the robot system 100 is set to (Wx, Wy, Wz ). At this time, when the approaching direction of the robot 20 is the negative direction of Wz, it is fixed to the rectangular coordinate system P of the component 10 and represents the direction of the component 10 by the vector A of the positive direction of Wz. In this way, when it is put into production in a state of being scattered and stacked, the putting posture is classified according to the direction of the part 10 relative to the approaching direction.
零件10以姿勢不整齊但未重疊在平面上之形態投入生產之情況,係根據零件10的穩定姿勢來進行零件10的投入姿勢的分類。此處所謂的穩定姿勢,係指零件10在平面上穩定靜止之姿勢。針對在兩種情況分類出的每個投入姿勢,分別算出零件10的姿勢。 When the part 10 is put into production in a form where the posture is not regular but does not overlap on the plane, the input posture of the part 10 is classified according to the stable posture of the part 10. The so-called stable posture here refers to a posture where the part 10 is stable and stationary on a plane. For each input posture classified in the two cases, the posture of the part 10 is calculated separately.
把持姿勢選定部320係取得記憶部31中儲存的機械手資料302,針對零件投入姿勢算出部310所算出的每個投入姿勢,選定機械手20的把持姿勢。 The holding posture selection unit 320 acquires the robot data 302 stored in the memory unit 31, and selects the holding posture of the robot 20 for each input posture calculated by the part input posture calculation unit 310.
在此,所選的把持姿勢必須考慮實際把持零件10之際之機器人200的機械上的限制。例如,如第4圖所示,在此假定設置於比零件10要靠Wx的負方向之機器人200(未圖示)從向量B之方向來把持投入直角座標系W的機器人系統100之零件10之情況。如第5圖所示,若零件10從第4圖的狀態繞Wz軸旋轉後,要採用與第4圖相同之相對於零件10的把持位置之機械手20的把持姿勢,就必須使機械手20的安裝部朝Wx的正方向大幅移動,由於機器人200搆不到零件10而無法執行把持動作。如第6圖所示,若採用零件10旋轉之軸方向Wz與機械手資料302規定之機械手20的安裝方向(向量B)所夾的角度小之把持姿勢,則即使零件10旋轉,機器人200也可藉由使手腕部22旋轉,不大幅改變機械手20的位置而執行把持動作。在此,機械手20接近零件10之方向,通常係零 件10旋轉之軸方向Wz。對此,把持姿勢選定部320中,係選定機械手20接近零件10之方向與表示機械手20的安裝部到前端的方向之安裝方向的夾角在預定的角度以內之機械手20的姿勢,作為把持姿勢。 Here, the selected holding posture must consider the mechanical limitations of the robot 200 when the part 10 is actually held. For example, as shown in FIG. 4, it is assumed here that the robot 200 (not shown) disposed in the negative direction of Wx relative to the part 10 holds the part 10 of the robot system 100 thrown into the rectangular coordinate system W from the direction of the vector B Situation. As shown in FIG. 5, if the part 10 rotates around the Wz axis from the state of FIG. 4, in order to adopt the same holding posture of the manipulator 20 with respect to the holding position of the part 10 as in FIG. 4, the manipulator must be The mounting portion of 20 moves greatly in the positive direction of Wx, and the robot 200 cannot perform the gripping operation because it cannot construct the part 10. As shown in FIG. 6, if the gripping posture between the axis direction Wz of rotation of the part 10 and the mounting direction (vector B) of the manipulator 20 specified by the manipulator data 302 is small, even if the part 10 rotates, the robot 200 It is also possible to perform the gripping operation without significantly changing the position of the robot 20 by rotating the wrist 22. Here, the direction in which the robot 20 approaches the part 10 is usually the axis direction Wz in which the part 10 rotates. In this regard, the holding posture selection part 320 selects the posture of the manipulator 20 whose angle between the direction in which the robot 20 approaches the part 10 and the mounting direction indicating the direction from the mounting part of the manipulator 20 to the front end is within a predetermined angle, as Hold posture.
把持位置區域抽出部330係針對把持姿勢選定部320所選定的每個把持姿勢,將匯整了屬於相同把持種別之位置的區域抽出作為把持位置區域。此處所謂的相同把持種別係定義為相對於零件10的投入姿勢之機械手20的把持姿勢相同,且相對於機械手20的把持部之零件10的被把持部一致之情況。例如,如第7圖所示,使用具有指部21之機械手20來把持零件10之情況,機械手20的把持部係指部21的內側的側面20a、20b,零件10的被把持部係零件10的各側面10a~10d。此時,就第8及9圖而言,相對於零件10的投入姿勢之把持姿勢相同,且相對於機械手20的把持部20a、20b之零件10的被把持部10a、10b也分別一致,所以為相同把持種別。另一方面,第10圖雖與第8圖為相同把持姿勢,但相對於機械手20的把持部20a、20b之零件10的被把持部卻是10c、10d,與第8圖不一致,所以為不同的把持種別。 The grip position area extraction unit 330 extracts the area where the positions belonging to the same grip type are collected as the grip position area for each grip position selected by the grip position selection unit 320. Here, the same gripping type is defined as a case where the gripping posture of the manipulator 20 with respect to the throwing posture of the part 10 is the same, and the gripped part of the part 10 with respect to the gripping part of the manipulator 20 coincides. For example, as shown in FIG. 7, when a robot 20 having a finger 21 is used to hold a part 10, the grip of the robot 20 is the inner side surface 20 a, 20 b of the finger 21, and the gripped part of the part 10 is The side surfaces 10a to 10d of the component 10. At this time, as shown in FIGS. 8 and 9, the holding posture with respect to the input posture of the part 10 is the same, and the grasped parts 10 a and 10 b of the part 10 with respect to the holding parts 20 a and 20 b of the manipulator 20 also agree, So for the same type of control. On the other hand, although FIG. 10 has the same holding posture as FIG. 8, the gripped parts of the part 10 with respect to the gripping parts 20a, 20b of the manipulator 20 are 10c, 10d, which is inconsistent with FIG. 8, so Different control types.
把持位置姿勢輸出部340係決定把持位置區域抽出部330所抽出的把持位置區域中的把持位置,並針對零件10的每個投入姿勢,輸出作為把持位置姿勢。 The grip position and posture output unit 340 determines the grip position in the grip position area extracted by the grip position area extraction unit 330 and outputs it as the grip position posture for each input posture of the component 10.
藉由上述的構成,本實施形態之把持位置姿勢教導裝置300可根據零件形狀資料301及機械手資料 302,針對零件10的每個投入姿勢,產生至少一個把持位置姿勢。 With the above configuration, the holding position and posture teaching device 300 of the present embodiment can generate at least one holding position and posture for each input posture of the part 10 based on the part shape data 301 and the manipulator data 302.
接著,參照第11圖,說明利用上述構成執行機能之處理程序的一例。第11圖係顯示處理程序的一例之步驟S1至S4之流程圖。 Next, referring to FIG. 11, an example of a processing program that uses the above-described configuration to execute the function will be described. FIG. 11 is a flowchart showing steps S1 to S4 of an example of the processing procedure.
步驟S1中,零件投入姿勢算出部310中取得零件形狀資料301,並進行零件10的投入姿勢之分類及算出。投入姿勢的分類及算出方法係依零件10以散亂堆積的狀態投入之情況、及零件10以姿勢雖不整齊但未重疊在平面上之形態投入之情況,採用不同的方法。 In step S1, the part input posture calculation unit 310 obtains the part shape data 301, and classifies and calculates the input posture of the part 10. The classification and calculation method of the input posture are different methods according to the case where the part 10 is input in a state of being scattered and stacked, and the case where the part 10 is input in a form where the posture is not regular but does not overlap on the plane.
零件10以散亂堆積的狀態投入時,例如,有以極座標空間來表現而進行投入姿勢分類之方法。如第3圖所示,機械手20的接近方向為Wz的負方向時,將固定於零件10之直角座標系P之與接近方向相反方向之向量A設為零件10的方向。此時,以固定於零件10之極座標空間來表現向量A,以其角度成分(θ,φ)的範圍來進行分類。例如,若以30°單位來進行θ及φ的分類,則可區分為12×12共144種之種類。認識零件10的姿勢,以極座標空間表現該零件10的姿勢中之向量A的方向,判斷落在預先分類的144種之中的哪個範圍,而算出作為零件10的投入姿勢。 When the parts 10 are put in a state of being scattered and stacked, for example, there is a method of expressing in a polar coordinate space and classifying the put posture. As shown in FIG. 3, when the approaching direction of the robot 20 is the negative direction of Wz, the vector A of the direction opposite to the approaching direction of the rectangular coordinate system P fixed to the part 10 is set as the direction of the part 10. At this time, the vector A is expressed in the polar coordinate space fixed to the part 10, and the classification is performed in the range of its angular components (θ, φ). For example, if θ and φ are classified in units of 30 °, it can be divided into 144 types of 12 × 12. Recognizing the posture of the part 10, expressing the direction of the vector A in the posture of the part 10 in polar coordinate space, judging which range among the 144 kinds classified in advance, and calculating the input posture as the part 10.
零件10以姿勢雖不整齊但未重疊在平面上之形態投入時,零件10係就每個穩定姿勢來分類。就穩定姿勢的算出方法而言,例如首先,零件投入姿勢算出部310 取得零件10的零件形狀資料301,並算出包圍零件10之最小體積的凸多面體。然後,將零件10的重心投影在置放零件10的平面上,判斷投影的點是否位於凸多面體的表面內,而將位於表面內者作為零件10的穩定姿勢而算出。此時之機械手20的接近方向係例如為零件10的置放平面的法線方向。穩定姿勢的算出方法不限於此,只要可算出零件10在平面上為穩定靜止的姿勢,則不限制方法。如此,步驟S1中,算出至少一個零件10的投入姿勢。 When the part 10 is put in a form where the posture is not regular but does not overlap on the plane, the part 10 is classified for each stable posture. As for the method for calculating the stable posture, for example, first, the part input posture calculation unit 310 obtains the part shape data 301 of the part 10 and calculates the convex polyhedron surrounding the minimum volume of the part 10. Then, the center of gravity of the part 10 is projected on the plane on which the part 10 is placed, it is determined whether the projected point is located in the surface of the convex polyhedron, and the person located in the surface is calculated as the stable posture of the part 10. The approaching direction of the robot 20 at this time is, for example, the normal direction of the placement plane of the component 10. The calculation method of the stable posture is not limited to this, and the method is not limited as long as it can calculate the posture that the part 10 is stable and stationary on the plane. In this way, in step S1, the insertion posture of at least one component 10 is calculated.
其次,步驟S2中,把持姿勢選定部320取得機械手資料302,並選定步驟S1中導出的每個投入姿勢的機械手20的把持姿勢。利用第12圖來說明把持姿勢的選定方法的一例。如第12圖所示,首先在機械手20的接近方向為Wz軸之機器人系統100的直角座標系W(Wx,Wy,Wz),及機械手20的安裝方向為Qz軸之固定於機械手20的座標系Q(Qx,Qy,Qz)的基礎上,使Wz軸與Qz軸一致。然後,將機械手20的把持面的法線(向量V)與零件10的各面的法線(向量W)所夾的角度在容許角度以內之零件10的面,抽出作為被把持面。再以使抽出的零件10的被把持面與機械手20的把持面平行相向之方式,使機械手20的把持面的法線與零件10的被把持面的法線配合,將此時之機械手20的姿勢選定作為相對於零件10的投入姿勢之把持姿勢。利用如此的選定方法,把持姿勢選定部320可選定已考慮了實際把持零件10之際的機器人200的機械上的限制之把持姿勢。此時,在零件10以散亂堆積的 狀態投入之情況,較佳為以對於任意的投入姿勢皆可導出容許角度以內的把持姿勢之方式,適切地設定容許角度或用以分類投入姿勢之單位角度的大小,或是兩方都做適切的設定。 Next, in step S2, the grip posture selection unit 320 obtains the robot data 302, and selects the grip posture of the robot 20 for each input posture derived in step S1. An example of the selection method of the holding posture will be described using FIG. 12. As shown in FIG. 12, first, the rectangular coordinate system W (Wx, Wy, Wz) of the robot system 100 in which the approach direction of the manipulator 20 is the Wz axis, and the installation direction of the manipulator 20 is the Qz axis are fixed to the manipulator The coordinate system of 20 is based on Q (Qx, Qy, Qz), so that the Wz axis coincides with the Qz axis. Then, the surface of the part 10 whose angle between the normal of the gripping surface of the robot 20 (vector V) and the normal of each surface of the component 10 (vector W) is within the allowable angle is extracted as the gripped surface. Then, in such a way that the gripped surface of the extracted part 10 is parallel to the gripped surface of the robot 20, the normal of the gripped surface of the robot 20 and the normal of the gripped surface of the component 10 are matched, and the mechanical The posture of the hand 20 is selected as the holding posture with respect to the input posture of the part 10. With such a selection method, the holding posture selection unit 320 can select a holding posture that has considered the mechanical limitations of the robot 200 when actually holding the component 10. At this time, when the component 10 is thrown in a state of being scattered and stacked, it is preferable to appropriately set the allowable angle or the unit for classifying the throwing posture in such a manner that the grasping posture within the allowable angle can be derived for any throwing posture The size of the angle, or both sides can be appropriately set.
在此,機械手20的安裝方向例如可由機械手資料302加以指定。另外,機械手20的把持面也可由機械手資料302加以指定,且能夠以指部21的開閉方向的面作為把持面。另外,機械手20的把持面的法線與零件10的被把持面的法線所夾角度的容許角度,可由機械手資料302或其他的輸入資料等加以指定,亦可設定為例如5°之固定值。 Here, the installation direction of the manipulator 20 can be specified by the manipulator data 302, for example. In addition, the grip surface of the robot 20 can also be specified by the robot data 302, and the surface of the finger 21 in the opening and closing direction can be used as the grip surface. In addition, the allowable angle between the normal of the gripping surface of the robot 20 and the normal of the gripped surface of the part 10 can be specified by the robot data 302 or other input data, etc., and can also be set to, for example, 5 ° Fixed value.
並且,在機械手20的把持面有複數個之情況時,係就機械手20的各個把持面抽出零件10的被把持面。在零件10的被把持面未被抽出之情況時,則是選定例如在第12圖中機械手20的接近方向之Wz軸與機械手20的安裝方向之Qz軸相重合之情況的機械手20的姿勢之中的一個作為把持姿勢。此時,把持姿勢係機械手20的繞Qz軸之旋轉方向的位置並未確定,但此旋轉方向可為機器人系統100的座標系W的Wx軸或Wy軸,與機械手20的三維形狀資料所規定的座標系Q的Qx軸或Qy軸方向一致之方向。此外,亦可使用適當的座標軸、基準等來決定。如此,步驟S2中,針對零件10的每個投入姿勢,選定至少一個把持姿勢。 In addition, when there are a plurality of gripping surfaces of the manipulator 20, the gripped surface of the component 10 is extracted from each gripping surface of the manipulator 20. When the gripped surface of the part 10 is not drawn out, for example, the manipulator 20 in which the Wz axis of the approaching direction of the manipulator 20 coincides with the Qz axis of the mounting direction of the manipulator 20 in FIG. 12 is selected. One of the postures is the holding posture. At this time, the position of the holding posture of the rotation direction of the manipulator 20 around the Qz axis is not determined, but this rotation direction may be the Wx axis or Wy axis of the coordinate system W of the robot system 100, and the three-dimensional shape data of the manipulator 20 The specified coordinates are the directions in which the directions of the Qx axis and the Qy axis of Q coincide. In addition, it can also be determined using an appropriate coordinate axis, reference, or the like. In this manner, in step S2, at least one holding posture is selected for each input posture of the component 10.
其次,步驟S3中,把持位置區域抽出部330 將匯整了把持姿勢選定部320所選定的把持姿勢中之機械手20的把持部與零件10的被把持部分別一致之位置,亦即相同把持種別之位置而得出的區域,抽出作為把持位置區域。就把持位置區域的抽出方法而言,例如,模擬開閉機械手20的指部21來把持零件10的動作之方法。在此,把持的模擬可採用各種已知的方法。舉例來說,首先以預定的把持姿勢,一邊變更機械手20相對於零件10的相對位置一邊使指部21開閉,來找出可把持零件10之範圍,然後,在可把持的範圍內使零件10與機械手20的面相接觸的情況時,將相同把持種別的位置匯整成為一個把持位置區域而予以抽出。 Next, in step S3, the grasping position area extraction unit 330 aggregates the positions where the grasping part of the robot 20 and the grasped part of the component 10 in the grasping posture selected by the grasping posture selecting unit 320 respectively coincide, that is, the same grasp The area derived from the different positions is extracted as the holding position area. The method of extracting the grip position area is, for example, a method of simulating the operation of gripping the part 10 by opening and closing the finger 21 of the robot 20. Here, various known methods can be used for the simulation of holding. For example, first, in a predetermined holding posture, the finger 21 is opened and closed while changing the relative position of the robot 20 relative to the part 10 to find out the range in which the part 10 can be held, and then, within the range in which the part can be held 10 When the surface of the manipulator 20 is in contact, the positions of the same grip type are aggregated into a grip position area and extracted.
相同把持種別之把持位置區域,除此之外,還可根據零件形狀資料301,從邊界條件算出把持種別變更之位置。如此,步驟S3中,針對零件10的每個投入姿勢,抽出至少一個把持位置區域。 In addition to the holding position area of the same holding type, the position of the holding type change can be calculated from the boundary conditions based on the part shape data 301. In this manner, in step S3, at least one grip position area is extracted for each input posture of the component 10.
其次,步驟S4中,把持位置姿勢輸出部340從步驟S3中抽出的把持位置區域當中選定把持位置。就把持位置的選定方法而言,例如,首先從把持位置區域抽出部330所抽出的複數個把持位置區域,算出各個區域的範圍,針對每個投入姿勢,選定一個範圍最廣的把持位置區域。然後,算出所選定的把持位置區域的重心作為把持位置。將所算出的把持位置輸出作為零件10的每個投入姿勢之把持位置姿勢。 Next, in step S4, the grip position posture output unit 340 selects the grip position from the grip position area extracted in step S3. Regarding the method of selecting the holding position, for example, first, a plurality of holding position areas extracted from the holding position area extraction unit 330 are calculated, and the range of each area is calculated, and the widest holding position area is selected for each input posture. Then, the center of gravity of the selected holding position area is calculated as the holding position. The calculated holding position is output as the holding position posture for each input posture of the component 10.
把持位置姿勢係例如以零件10與機械手20 的相對位置及姿勢的資料,輸出至編輯機器人控制部202的控制程式之工具。另外,亦可利用GUI的顯示部等視覺化而對使用者輸出,或組合以上兩者。另外,還可記憶表示作為基準之零件10的位置與在把持零件10的時點之機器人200的位置姿勢之間的關係之資料。此處表示作為基準之零件10的位置與機器人200的位置姿勢之間的關係之資料,可利用從感測器50等取得之作為基準之零件10的位置的資料,亦可設置輸入部等,由使用者適當地輸入,亦可輸入由機器人系統100的模擬而得到的資料。另外,亦可從編輯機器人控制部202的控制程式之工具輸入,或以上各者的組合。 The grasping position and posture is, for example, a tool for editing the control program of the robot control unit 202 with data on the relative position and posture of the part 10 and the robot 20. In addition, the display portion of the GUI or the like may be used to visualize the output to the user, or a combination of the two. In addition, data indicating the relationship between the position of the part 10 as a reference and the position and posture of the robot 200 at the time when the part 10 is held can also be memorized. Here, the data showing the relationship between the position of the reference part 10 and the position and posture of the robot 200 can be obtained from the sensor 50 or the like as the reference position of the part 10, or an input unit can be provided. The user can appropriately input the data obtained by the simulation of the robot system 100. In addition, it may be input from a tool that edits the control program of the robot control unit 202, or a combination of the above.
如上所述,藉由執行步驟S1至S4之處理,可根據零件形狀資料301及機械手資料302,針對零件10的每個投入姿勢輸出至少一個把持位置姿勢。 As described above, by performing the processes of steps S1 to S4, at least one holding position posture can be output for each input posture of the part 10 based on the part shape data 301 and the manipulator data 302.
又,在此為了簡化說明而限定各機能的處理來進行說明,但本發明之處理不限於此。 In addition, in order to simplify the description, the processing of each function is limited and described, but the processing of the present invention is not limited to this.
例如,把持位置姿勢輸出部340雖說明為選定範圍最廣的把持位置區域,但亦可選定零件10與機械手20的接觸面的數目最多的區域作為把持位置區域。如第13圖所示,指部21有缺口部23之機械手20、具有複數個指部之機械手20等的情況下,以接觸面的數目多者為較佳。此係因為在把持著零件10而移動之情況較不易掉落的緣故,及藉由利用複數個接觸面對零件10施力,容易使把持後的零件10的位置姿勢穩定的緣故。 For example, although the grip position posture output unit 340 is described as the grip position area with the widest selection range, the area with the largest number of contact surfaces between the component 10 and the robot 20 may be selected as the grip position area. As shown in FIG. 13, in the case where the finger 21 has the notch portion 23 of the manipulator 20, the manipulator 20 having a plurality of fingers, and the like, it is preferable that the number of contact surfaces is large. This is because it is less likely to fall when moving while holding the part 10, and by applying force to the part 10 by using a plurality of contacts, it is easy to stabilize the position and posture of the part 10 after holding.
又,把持位置姿勢輸出部340雖顯示了以把持位置姿勢的重心作為把持位置之例,但亦可選定接近零件10的重心之把持位置區域內的位置作為把持位置。此外,還可藉由判斷把持零件10之際的穩定性來選定把持位置。就此穩定性的判斷方法而言,例如,能夠以選定的把持姿勢及把持位置區域來把持零件10且算出對零件10施加外力的情況之零件10的位移,然後選出位移小的位置作為把持位置。由於採用如此的把持位置的選定方法,機械手20可穩定地把持零件10。 In addition, although the grip position and posture output unit 340 shows an example in which the center of gravity of the grip position and posture is used as the grip position, a position within the grip position area close to the center of gravity of the component 10 may be selected as the grip position. In addition, the holding position can also be selected by judging the stability when holding the part 10. As for this method of determining stability, for example, it is possible to hold the component 10 in the selected holding posture and holding position area and calculate the displacement of the component 10 when an external force is applied to the component 10, and then select a position with a small displacement as the holding position. With such a method of selecting the holding position, the robot 20 can stably hold the part 10.
再者,把持位置姿勢輸出部340雖顯示了針對零件10的每個投入姿勢分別輸出一個把持位置姿勢之例,但亦可輸出複數個。例如,針對把持位置區域抽出部330所導出的複數個把持位置區域,分別導出把持位置,並全部輸出作為把持位置姿勢。 In addition, although the holding position and posture output unit 340 shows an example in which one holding position and posture is output for each input posture of the component 10, a plurality of output positions may be output. For example, for a plurality of grasping position areas derived by the grasping position area extraction unit 330, the grasping positions are respectively derived, and all are output as the grasping position posture.
另外,亦可不全部輸出作為把持位置姿勢,而是根據優先度而選定一部分。例如,針對把持位置姿勢進行評價,並輸出評價順位高的三個之方法、輸出得到一定以上的評價的把持位置姿勢之方法、或組合此等之方法。就評價方法而言,可為零件10與機械手20的接觸面的數目、把持位置區域的廣度、零件10的重心到把持位置的距離等之個別的評價基準,或此等的組合。 In addition, not all outputs may be output as the holding position and posture, but a part may be selected according to the priority. For example, a method of evaluating the holding position and posture and outputting three methods of evaluating the high order, a method of outputting a holding position and posture that has obtained a certain evaluation or more, or a combination of these methods. The evaluation method may be individual evaluation criteria such as the number of contact surfaces of the component 10 and the manipulator 20, the width of the holding position area, the distance from the center of gravity of the component 10 to the holding position, or a combination of these.
另外,就從把持位置姿勢輸出部340所輸出的複數個把持位置姿勢選定一個使機器人200動作的把持位置姿勢之方法而言,有在把持位置姿勢教導裝置300 設置顯示部,將所有的把持位置姿勢輸出至顯示部,讓使用者選擇之方法,以可在機器人控制部202的控制程式內選擇之方式來輸出之方法。 In addition, in the method of selecting one holding position posture for operating the robot 200 from the plurality of holding position postures output by the holding position posture output unit 340, there is a display unit provided in the holding position posture teaching device 300, and all holding positions The posture is output to the display section for the user to select the method to output in a manner that can be selected within the control program of the robot control section 202.
再者,亦可依據零件10投入的位置而變更機械手20的接近方向。例如,零件10投入於具有壁部的箱狀物中之情況,接近方向以考慮機械手20的尺寸等而設定成不會與壁部發生干涉為較佳。例如,如第14圖所示,經感測器50認識的零件10位於箱壁附近之情況,係使機械手20的接近方向傾斜向與箱壁相反的方向。在此情況,零件投入姿勢算出部310中,對應於與接近方向相反方向之向量A來進行零件10的投入姿勢之分類。靠近複數個壁部之情況時,係使接近方向傾斜向與各壁部皆相反的方向。又,在零件10靠近壁部而位於壁際之情況時,亦可將接近方向設定於更狹小的範圍來算出把持位置姿勢。 Furthermore, the approach direction of the robot 20 may be changed according to the position where the component 10 is put in. For example, when the component 10 is thrown into a box having a wall portion, the approach direction is preferably set so as not to interfere with the wall portion in consideration of the size of the manipulator 20 and the like. For example, as shown in FIG. 14, when the part 10 recognized by the sensor 50 is located near the box wall, the approach direction of the robot 20 is inclined in the opposite direction to the box wall. In this case, the part input posture calculation unit 310 classifies the input posture of the component 10 corresponding to the vector A in the direction opposite to the approach direction. When approaching a plurality of wall portions, the approach direction is inclined in the opposite direction to each wall portion. In addition, when the component 10 is close to the wall portion and located at the wall, the approach direction can be set to a narrower range to calculate the grip position and posture.
如上所述,根據本發明之把持位置姿勢教導裝置300,由於具備:將零件10的投入姿勢予以分類及算出之零件投入姿勢算出部310;選定每個投入姿勢的機械手20的把持姿勢之把持姿勢選定部320;針對每個把持姿勢,抽出相同把持種別的把持位置區域之把持位置區域抽出部330;以及從把持位置區域內選定把持位置,且將所選定的把持姿勢之把持位置輸出作為機械手20的把持位置姿勢之把持位置姿勢輸出部340,因此,可針對每個投入姿勢產生至少一個機械手20的把持位置姿勢。 As described above, according to the holding position and posture teaching device 300 of the present invention, it includes: a part input posture calculation unit 310 that classifies and calculates the input posture of the component 10; and holds the holding posture of the robot 20 that selects each input posture Posture selection unit 320; for each holding posture, extract the holding position area extraction section 330 of the same holding position area; and select the holding position from the holding position area, and output the selected holding position holding position as a machine The holding position and posture output unit 340 of the holding position and posture of the hand 20 can generate at least one holding position and posture of the manipulator 20 for each input posture.
以下,參照第15圖來說明實施本發明之實施形態2的機器人系統。第15圖係顯示本發明的實施形態2之使散亂堆積的零件排列整齊之機器人系統的一例之示意圖。第15圖中,與第1及2圖相同的符號係表示相同或相當的部分。本實施形態之機器人系統係將實施形態1之把持位置姿勢教導裝置應用於使散亂堆積的零件排列整齊之系統者。 Hereinafter, a robot system embodying Embodiment 2 of the present invention will be described with reference to FIG. 15. FIG. 15 is a schematic diagram showing an example of a robot system for arranging and arranging scattered parts in Embodiment 2 of the present invention. In Fig. 15, the same symbols as in Figs. 1 and 2 denote the same or corresponding parts. The robot system of the present embodiment is a system that applies the holding position and posture teaching device of the first embodiment to align the scattered and stacked parts.
如第15圖所示,機器人系統100具備:三維視覺感測器(vision sensor)150、二維視覺感測器160、機器人200、及把持位置姿勢教導裝置300。把持位置姿勢教導裝置300係在機器人200進行把持動作之前,預先以實施形態1中揭示的方法產生零件10的把持位置姿勢,並教導給機器人200。 As shown in FIG. 15, the robot system 100 includes a three-dimensional vision sensor 150, a two-dimensional vision sensor 160, a robot 200, and a holding position and posture teaching device 300. The holding position and posture teaching device 300 generates the holding position and posture of the component 10 in advance by the method disclosed in Embodiment 1 before the robot 200 performs the holding action, and teaches the robot 200 to the holding position and posture.
零件10係以散亂堆積的狀態投入零件投入台110。就將零件10投入零件投入台110之方法而言,除了將零件10依序投入固定於零件投入台110的托盤上之方法外,還有概括更換裝滿有零件10的托盤之方法,以及組合此等之方法。 The parts 10 are put into the parts putting table 110 in a state of being scattered and stacked. As for the method of putting the component 10 into the component loading table 110, in addition to the method of sequentially placing the component 10 on the tray fixed to the component loading table 110, there is also a general method of replacing the tray filled with the component 10, and the combination These methods.
三維視覺感測器150係用來認識散亂堆積在零件投入台110上之零件10的位置之感測器。利用三維視覺感測器150的認識結果,從零件投入台110取出一個零件10,直接排列至排列台140,但若無法直接排列的情況時,以讓零件10彼此不相接觸之方式,置放至暫置台 120。 The three-dimensional visual sensor 150 is a sensor for recognizing the position of the part 10 scattered on the part putting table 110. Using the recognition result of the three-dimensional visual sensor 150, a part 10 is taken out from the part loading table 110 and arranged directly to the arrangement table 140, but if it cannot be arranged directly, the parts 10 are placed in such a way that they do not touch each other To temporary table 120.
此處所謂的無法直接排列之情況,係指零件10的認識結果的精度低而無法進行為了要排列整齊的正確的把持之情況。例如,零件10的特徵點被擋住,所認識的零件10的位置姿勢產生疑義之情況,或者,所選擇的把持位置姿勢為不穩定的方法,以機械手20把持之際零件10會動之情況。此外,還有零件10的位置姿勢未被認識,而是認識可把持的空間來進行把持之情況。所謂的可把持的空間,若為夾抓型的機械手20,則為機械手20的指部21可伸入且要把持的零件10在指部21之間之空間,若為吸取型的機械手20,則為物體的一定面積以上的平面。另外,還有由於把持位置姿勢的關係,因機械手20及機器人200與周圍的設備干涉之情況、機器人200的機械上的限制等,而無法實現位置姿勢之情況。 The so-called inability to arrange directly here refers to a situation in which the accuracy of the recognition result of the component 10 is low, and it is impossible to perform accurate holding in order to arrange neatly. For example, the feature point of the part 10 is blocked, the position and posture of the recognized part 10 is doubtful, or the selected holding position and posture is unstable, and the part 10 will move when the robot 20 holds it . In addition, there is a case where the position and posture of the component 10 are not recognized, but the graspable space is recognized. The so-called grippable space, if it is a gripping robot 20, is the space where the fingers 21 of the robot 20 can extend and the part 10 to be gripped is between the fingers 21, if it is a suction-type machine The hand 20 is a plane above a certain area of the object. In addition, there are cases where the position and posture cannot be realized due to the relationship between the gripping position and posture, the interference of the robot 20 and the robot 200 with the surrounding equipment, the mechanical limitations of the robot 200, and the like.
在如上述的情況,判斷為無法直接移動到排列台140,而將零件10以穩定的姿勢置放在暫置台120。二維視覺感測器160係高精度地認識置放在暫置台120上之零件10的位置姿勢。機器人200係使用由把持位置姿勢教導裝置300所產生的把持位置姿勢來把持零件10。機器人200係以零件10以預先決定的最終姿勢整齊排列在排列台140上之方式來執行動作。 In the case as described above, it is determined that the arrangement table 140 cannot be moved directly, and the component 10 is placed on the temporary table 120 in a stable posture. The two-dimensional visual sensor 160 recognizes the position and posture of the part 10 placed on the temporary table 120 with high accuracy. The robot 200 grips the component 10 using the grip position and posture generated by the grip position and posture teaching device 300. The robot 200 executes the operation in such a manner that the parts 10 are neatly arranged on the arrangement table 140 in a predetermined final posture.
在無法以把持位置姿勢教導裝置300所教導的把持位置姿勢使零件10移動到排列台140之情況時,機器人200利用改換姿勢治具130使零件10改換姿勢之 後,以成為最終姿勢之方式移動到排列台140。所謂的無法移動之情況,係指機械手20、機器人200等與周圍的設備干涉之情況、機器人200無法實現位置姿勢之情況等。不只是改換姿勢治具130,亦可將零件10放在暫置台120上來再次改換姿勢。 When it is impossible to move the part 10 to the alignment table 140 in the holding position and posture taught by the holding position and posture teaching device 300, the robot 200 uses the posture change jig 130 to change the posture of the part 10, and then moves to the final posture排 台 140。 Arrange the table 140. The so-called immovable situation refers to a situation where the robot 20, the robot 200, etc. interfere with surrounding equipment, a situation where the robot 200 cannot realize the position and posture, and the like. Not only changing the posture jig 130, but also placing the part 10 on the temporary table 120 to change the posture again.
根據上述之構成,機器人系統100可用把持位置姿勢教導裝置300所產生的把持位置姿勢來把持散亂堆積的零件10,並整齊排列成預定的位置姿勢。 According to the above configuration, the robot system 100 can hold the scattered parts 10 by the holding position and posture generated by the holding position and posture teaching device 300 and arrange them in a predetermined position and posture.
又,本實施形態中,雖說明了將把持位置姿勢教導裝置300應用於有散亂堆積的零件10投入之系統之例,但亦可應用於除此之外的系統,例如零件10以姿勢雖不整齊但未重疊之方式投入之系統、零件10的姿勢為整齊排列地投入之系統等。 Furthermore, in the present embodiment, although the example in which the holding position and posture teaching device 300 is applied to a system in which the parts 10 are scattered and stacked is described, it can also be applied to other systems. The system put in a non-tidy but non-overlapping manner, the posture of the parts 10 is the system put in a neat arrangement, etc.
以下,參照第16圖來說明實施本發明之實施形態3的把持位置姿勢教導裝置。第16圖係本發明之把持位置姿勢教導裝置300的概略構成圖。第16圖中,與第1及2圖相同的符號係表示相同或相當的部分。本實施形態除了追加把持位置姿勢資料303及資料庫檢索部311之外,係與實施形態1一樣。 The grip position and posture teaching device embodying Embodiment 3 of the present invention will be described below with reference to FIG. 16. FIG. 16 is a schematic configuration diagram of the holding position and posture teaching device 300 of the present invention. In Fig. 16, the same symbols as in Figs. 1 and 2 denote the same or corresponding parts. This embodiment is the same as Embodiment 1 except that the holding position and posture data 303 and the database search unit 311 are added.
本實施形態中,構成為將記述有機械手20相對於主要的零件10之相對位置及姿勢之把持位置姿勢資料303儲存於記憶部31中,且具備有可檢索記憶部31 的資料庫之資料庫檢索部311。 In this embodiment, the holding position and posture data 303 describing the relative position and posture of the manipulator 20 relative to the main part 10 is stored in the memory section 31, and the database with the searchable memory section 31 is provided. Library search unit 311.
資料庫檢索部311係取得零件投入姿勢算出部310算出的零件10的投入姿勢的資料。並且,檢索儲存有主要的零件10的把持位置姿勢資料303之資料庫。在抽出經判斷為可用於算出的零件10的投入姿勢之把持位置姿勢資料303之情況時,判定投入姿勢之機械手200的接近方向與把持位置姿勢資料303之機械手200的安裝方向所夾的角度是否在容許角度以內。若判定為把持位置姿勢資料303的把持位置姿勢在容許角度以內時,把持位置姿勢輸出部340就其輸出作為把持位置姿勢。 The database search unit 311 acquires data on the input posture of the component 10 calculated by the component input posture calculation unit 310. Then, a database storing the holding position and posture data 303 of the main part 10 is searched. When extracting the grasping position and posture data 303 of the throwing posture of the part 10 determined to be usable for calculation, it is determined that the approaching direction of the throwing position of the robot 200 and the mounting direction of the grasping position and posture data 303 of the robot 200 Whether the angle is within the allowable angle. If it is determined that the grip position and posture of the grip position and posture data 303 is within the allowable angle, the grip position and posture output unit 340 outputs the output as the grip position and posture.
即使是如此的構成中,也與實施形態1一樣地,可針對零件10的每個投入姿勢產生至少一個把持位置姿勢。而且,本實施形態中,由於將把持位置姿勢資料303儲存在記憶部31中,且具備檢索記憶部31的資料庫之資料庫檢索部311,因此,在資料庫中登錄有可適用於零件10之把持位置姿勢資料303之情況時,可將其把持位置姿勢資料303輸出作為零件10的把持位置姿勢。 Even in such a configuration, as in the first embodiment, at least one grip position posture can be generated for each input posture of the component 10. Furthermore, in the present embodiment, since the holding position and posture data 303 is stored in the memory unit 31, and the database search unit 311 is provided with a database for searching the memory unit 31, the applicable part 10 is registered in the database In the case of the holding position and posture data 303, the holding position and posture data 303 can be output as the holding position and posture of the component 10.
就處理程序而言,以零件投入姿勢算出部310算出投入姿勢(步驟S1),以資料庫檢索部311檢索包含把持位置姿勢資料303之資料庫(步驟S2)。若抽出可適用的把持位置姿勢資料303時,省略把持姿勢選定部320、把持位置區域抽出部330及把持位置姿勢輸出部340的處理,以把持位置姿勢輸出部340輸出(步驟S3)。若未抽出可適用的把持位置姿勢資料303,則進行與實施形態1一 樣之處理。 As for the processing program, the part input posture calculation unit 310 calculates the input posture (step S1), and the database search unit 311 searches the database including the grip position posture data 303 (step S2). When the applicable grip position and posture data 303 is extracted, the processes of the grip position selection unit 320, the grip position area extraction unit 330, and the grip position and posture output unit 340 are omitted, and the grip position and posture output unit 340 outputs (step S3). If the applicable holding position and posture data 303 is not extracted, the same processing as in the first embodiment is performed.
藉由執行以上的處理程序,可與實施形態1一樣地根據零件形狀資料301及機械手資料302,針對零件10的每個投入姿勢產生一個把持位置姿勢。而且,在登錄有可適用於零件10之把持位置姿勢資料303之情況時,可省略把持姿勢選定部320、把持位置區域抽出部330及把持位置姿勢輸出部340的處理,而從把持位置姿勢輸出部340輸出其把持位置姿勢資料303。 By executing the above processing procedure, a holding position posture can be generated for each input posture of the part 10 based on the part shape data 301 and the manipulator data 302 as in the first embodiment. In addition, when the grip position and posture data 303 applicable to the part 10 is registered, the processing of the grip position selection unit 320, the grip position area extraction unit 330, and the grip position and posture output unit 340 can be omitted and output from the grip position and posture The unit 340 outputs its grip position posture data 303.
以下,參照第17圖來說明實施本發明之實施形態4的把持位置姿勢教導裝置。第17圖係本實施形態的概略構成圖。第17圖中,與第1及2圖相同的符號係表示相同或相當的部分。把持位置姿勢教導裝置300除了追加把持姿勢資料304及把持姿勢輸入部321之外,係與實施形態1一樣。 Hereinafter, a grip position and posture teaching device embodying Embodiment 4 of the present invention will be described with reference to FIG. 17. Fig. 17 is a schematic configuration diagram of the present embodiment. In Fig. 17, the same reference numerals as those in Figs. 1 and 2 denote the same or corresponding parts. The holding position and posture teaching device 300 is the same as the first embodiment except that the holding posture data 304 and the holding posture input unit 321 are added.
本實施形態係如第17圖所示,構成為具備供輸入把持姿勢資料304之把持姿勢輸入部321。 As shown in FIG. 17, this embodiment is configured to include a holding posture input unit 321 for inputting holding posture data 304.
把持姿勢資料304係記述有機械手20對於零件10的把持姿勢之資料。把持姿勢資料304的資料形式可與把持姿勢選定部320所輸出的姿勢相同,亦可為獨自的形式。在獨自的形式之情況,由把持姿勢輸入部321變更為與把持姿勢選定部320相同的資料形式。 The holding posture data 304 is data describing the holding posture of the robot 20 with respect to the part 10. The data format of the grip posture data 304 may be the same as the posture output by the grip posture selection unit 320, or may be a unique format. In the case of a unique format, the grip posture input unit 321 is changed to the same data format as the grip posture selection unit 320.
把持姿勢輸入部321可讀取把持姿勢資料 304,亦可由使用者利用GUI進行輸入。GUI係具備例如零件10及機械手20的3D顯示畫面及進行把持姿勢的輸入之輸入按鈕等。 The holding posture input unit 321 can read the holding posture data 304, or the user can input it using the GUI. The GUI includes, for example, a 3D display screen of the component 10 and the robot 20, and an input button for inputting a holding posture.
即使是如此的構成中,與實施形態1一樣地,可針對零件10的每個投入姿勢產生至少一個把持位置姿勢。而且,根據本實施形態,由於具備把持姿勢輸入部321,因此使用者可從所經手的零件10及機械手20的特徵來直接指定把持姿勢。 Even in such a configuration, as in the first embodiment, at least one holding position posture can be generated for each input posture of the component 10. Further, according to the present embodiment, since the holding posture input unit 321 is provided, the user can directly specify the holding posture from the characteristics of the parts 10 and the robot 20 that the user handles.
就處理程序而言,以零件投入姿勢算出部310算出投入姿勢(步驟S1),針對每個投入姿勢,以把持姿勢輸入部321輸入把持姿勢資料304(步驟S2)。若已輸入有把持姿勢資料304時,則略過把持姿勢選定部320,由把持位置區域抽出部330及把持位置姿勢輸出部340以實施形態1中記載的方法進行處理,由把持位置姿勢輸出部輸出(步驟S3)。若未輸入有把持姿勢資料304,則進行與實施形態1一樣之處理。 Regarding the processing program, the part input posture calculation unit 310 calculates the input posture (step S1), and for each input posture, the grip posture input unit 321 inputs the grip posture data 304 (step S2). If the holding posture data 304 has been input, the holding posture selection unit 320 is skipped, and the holding position area extraction unit 330 and the holding position and posture output unit 340 are processed by the method described in Embodiment 1, and the holding position and posture output unit Output (step S3). If the holding posture data 304 is not input, the same processing as in the first embodiment is performed.
藉由執行以上的處理程序,可與實施形態1一樣地根據零件形狀資料301及機械手資料302,針對零件10的每個投入姿勢產生一個把持位置姿勢。而且,在在把持姿勢輸入部321已輸入有把持姿勢資料304之情況,可省略把持姿勢選定部320的處理,而產生把持位置姿勢。 By executing the above processing procedure, a holding position posture can be generated for each input posture of the part 10 based on the part shape data 301 and the manipulator data 302 as in the first embodiment. In addition, when the grip posture data 304 has been input to the grip posture input unit 321, the process of the grip posture selection unit 320 may be omitted, and the grip position posture may be generated.
以下,參照第18圖來說明實施本發明之實施形態5 的把持位置姿勢教導裝置。第18圖係本實施形態的概略構成圖。第18圖中,與第1及2圖相同的符號係表示相同或相當的部分。本實施形態除了追加把持位置姿勢調整部341之外,係與實施形態1一樣。 The grip position and posture teaching device embodying Embodiment 5 of the present invention will be described below with reference to FIG. 18. Fig. 18 is a schematic configuration diagram of this embodiment. In Fig. 18, the same reference numerals as those in Figs. 1 and 2 denote the same or corresponding parts. This embodiment is the same as Embodiment 1 except that the grip position and posture adjustment unit 341 is added.
本實施形態係如第18圖所示,構成為具備調整把持位置姿勢之把持位置姿勢調整部341。把持位置姿勢調整部341係對使用者提示把持位置姿勢,而且,使用者可根據提示的資訊來調整把持位置姿勢。 As shown in FIG. 18, this embodiment is configured to include a grip position and posture adjustment unit 341 that adjusts the grip position and posture. The holding position and posture adjustment unit 341 presents the user with the holding position and posture, and the user can adjust the holding position and posture based on the information presented.
就提示及調整把持位置姿勢之方法而言,可利用GUI。GUI係具備例如零件10及機械手20的3D顯示畫面及進行機械手20的位置姿勢的變更及把持位置姿勢的輸入之輸入按鈕等。把持位置姿勢調整部341中,亦可對使用者提示特定的把持位置區域,且只可在其範圍內調整位置。 As for the method of prompting and adjusting the holding position and posture, the GUI can be used. The GUI includes, for example, a 3D display screen of the parts 10 and the robot 20, and input buttons for changing the position and posture of the robot 20 and inputting the holding position and posture. In the grip position and posture adjustment unit 341, a specific grip position area may be presented to the user, and the position may be adjusted only within the range.
即使是如此的構成中,與實施形態1一樣地,可針對零件10的每個投入姿勢產生至少一個把持位置姿勢。而且,根據本實施形態,由於具備把持位置姿勢調整部341,因此使用者可調整已輸出的把持位置姿勢。 Even in such a configuration, as in the first embodiment, at least one holding position posture can be generated for each input posture of the component 10. Furthermore, according to the present embodiment, since the grip position and posture adjustment unit 341 is provided, the user can adjust the output grip position and posture.
又,在實施形態1至5中,係針對機械手20具有以夾住來把持零件10之複數個指部21的情況進行了說明,但亦可為以吸住來把持零件10之吸取式機械手。第19圖顯示吸取式機械手的一例。吸取式機械手20的上部係安裝至機器人200的手腕部22。吸取式機械手20的下部係具有吸住零件10之圓形的吸取部24,利用吸取部 24吸住來把持零件10。把持姿勢選定部320中,將機械手20的把持面作為吸取部24而選定把持姿勢。把持位置區域抽出部330及把持位置姿勢輸出部340也進行與上述的具有指部21之機械手20一樣之處理。 In addition, in the first to fifth embodiments, the case where the robot 20 has a plurality of fingers 21 that grip the component 10 by gripping has been described, but it may be a suction-type machine that grips the component 10 by gripping hand. Figure 19 shows an example of a suction robot. The upper part of the suction robot 20 is attached to the wrist 22 of the robot 200. The lower part of the suction-type manipulator 20 has a circular suction part 24 that sucks the part 10, and the suction part 24 holds the part 10 by suction. In the holding posture selection unit 320, the holding surface of the robot 20 is used as the suction unit 24 to select the holding posture. The grip position area extraction unit 330 and the grip position posture output unit 340 also perform the same processing as the manipulator 20 having the finger 21 described above.
又,在實施形態1至5中,說明了將機器人200與把持位置姿勢教導裝置300設成分別獨立的之例,但亦可為在機器人控制部202中內建具有與把持位置姿勢教導裝置300同等的機能之教導部之構成。 In the first to fifth embodiments, the robot 200 and the holding position and posture teaching device 300 are separately provided. However, the robot control unit 202 may be provided with the holding position and posture teaching device 300. The composition of the teaching department of the same function.
Claims (9)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
??PCT/JP2017/035937 | 2017-10-03 | ||
PCT/JP2017/035937 WO2019069361A1 (en) | 2017-10-03 | 2017-10-03 | Gripping position and attitude teaching device, gripping position and attitude teaching method, and robot system |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI649169B TWI649169B (en) | 2019-02-01 |
TW201914782A true TW201914782A (en) | 2019-04-16 |
Family
ID=65037057
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW107103224A TWI649169B (en) | 2017-10-03 | 2018-01-30 | Holding position and posture teaching device, holding position and posture teaching method, and robot system |
Country Status (5)
Country | Link |
---|---|
JP (1) | JP6456557B1 (en) |
CN (1) | CN111163907B (en) |
DE (1) | DE112017007903B4 (en) |
TW (1) | TWI649169B (en) |
WO (1) | WO2019069361A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI834194B (en) * | 2021-06-16 | 2024-03-01 | 美商靈巧公司 | Robotic system, method to control a robot and computer program product to control a robot |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7481427B2 (en) * | 2020-03-05 | 2024-05-10 | ファナック株式会社 | Removal system and method |
DE102022203410A1 (en) | 2022-04-06 | 2023-10-12 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method for controlling a robotic device |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3782679B2 (en) | 2001-05-09 | 2006-06-07 | ファナック株式会社 | Interference avoidance device |
JP4235214B2 (en) * | 2006-07-04 | 2009-03-11 | ファナック株式会社 | Apparatus, program, recording medium, and method for creating robot program |
JP4226623B2 (en) | 2006-09-29 | 2009-02-18 | ファナック株式会社 | Work picking device |
JP2009078310A (en) * | 2007-09-25 | 2009-04-16 | Seiko Epson Corp | Robot hand, its control method and control system |
JP4835616B2 (en) | 2008-03-10 | 2011-12-14 | トヨタ自動車株式会社 | Motion teaching system and motion teaching method |
JP5436460B2 (en) * | 2009-02-12 | 2014-03-05 | 三菱電機株式会社 | Industrial robot system |
JP5685027B2 (en) | 2010-09-07 | 2015-03-18 | キヤノン株式会社 | Information processing apparatus, object gripping system, robot system, information processing method, object gripping method, and program |
JP5879704B2 (en) * | 2011-03-10 | 2016-03-08 | 富士電機株式会社 | Robot control apparatus, article take-out system, program, and robot control method |
CN104245243B (en) * | 2012-04-25 | 2016-05-25 | 松下知识产权经营株式会社 | The bearing calibration of the mechanism error of articulated robot |
JP5620445B2 (en) | 2012-09-13 | 2014-11-05 | ファナック株式会社 | Article takeout device for determining holding position and posture of robot based on selection condition |
JP2016093879A (en) * | 2014-11-17 | 2016-05-26 | 富士通株式会社 | Gripping plan decision program, gripping plan determination method, and engineering support device |
CN105598965B (en) * | 2015-11-26 | 2018-03-16 | 哈尔滨工业大学 | The autonomous grasping means of robot drive lacking hand based on stereoscopic vision |
-
2017
- 2017-10-03 JP JP2018519496A patent/JP6456557B1/en active Active
- 2017-10-03 WO PCT/JP2017/035937 patent/WO2019069361A1/en active Application Filing
- 2017-10-03 CN CN201780095375.2A patent/CN111163907B/en active Active
- 2017-10-03 DE DE112017007903.9T patent/DE112017007903B4/en active Active
-
2018
- 2018-01-30 TW TW107103224A patent/TWI649169B/en not_active IP Right Cessation
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI834194B (en) * | 2021-06-16 | 2024-03-01 | 美商靈巧公司 | Robotic system, method to control a robot and computer program product to control a robot |
Also Published As
Publication number | Publication date |
---|---|
JPWO2019069361A1 (en) | 2019-11-14 |
WO2019069361A1 (en) | 2019-04-11 |
CN111163907B (en) | 2022-11-25 |
JP6456557B1 (en) | 2019-01-23 |
TWI649169B (en) | 2019-02-01 |
DE112017007903B4 (en) | 2022-04-14 |
CN111163907A (en) | 2020-05-15 |
DE112017007903T5 (en) | 2020-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Morales et al. | Integrated grasp planning and visual object localization for a humanoid robot with five-fingered hands | |
Bagnell et al. | An integrated system for autonomous robotics manipulation | |
Ekvall et al. | Learning and evaluation of the approach vector for automatic grasp generation and planning | |
Alonso et al. | Current research trends in robot grasping and bin picking | |
Saut et al. | Efficient models for grasp planning with a multi-fingered hand | |
WO2011065035A1 (en) | Method of creating teaching data for robot, and teaching system for robot | |
JP6640060B2 (en) | Robot system | |
Suzuki et al. | Grasping of unknown objects on a planar surface using a single depth image | |
US20130054030A1 (en) | Object gripping apparatus, object gripping method, and object gripping program | |
WO2020190166A1 (en) | Method and system for grasping an object by means of a robotic device | |
TWI649169B (en) | Holding position and posture teaching device, holding position and posture teaching method, and robot system | |
JP2012218119A (en) | Information processing apparatus, method for controlling the same, and program | |
Ullmann et al. | Intuitive virtual grasping for non haptic environments | |
Ottenhaus et al. | Visuo-haptic grasping of unknown objects based on gaussian process implicit surfaces and deep learning | |
TW202122225A (en) | System and method for robotic bin picking using advanced scanning techniques | |
Jaquier et al. | Analysis and transfer of human movement manipulability in industry-like activities | |
Aleotti et al. | Grasp programming by demonstration in virtual reality with automatic environment reconstruction | |
Lopez et al. | Taichi algorithm: Human-like arm data generation applied on non-anthropomorphic robotic manipulators for demonstration | |
El-Khoury et al. | 3d objects grasps synthesis: A survey | |
RU2745380C1 (en) | Method and system for capturing objects using robotic device | |
Haschke et al. | Geometry-based grasping pipeline for bi-modal pick and place | |
CN112533739B (en) | Robot control device, robot control method, and storage medium | |
Scharfe et al. | Hybrid physics simulation of multi-fingered hands for dexterous in-hand manipulation | |
Xu et al. | Vision‐Based Intelligent Perceiving and Planning System of a 7‐DoF Collaborative Robot | |
US11712797B2 (en) | Dual hand detection in teaching from demonstration |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
MM4A | Annulment or lapse of patent due to non-payment of fees |