SlideShare uma empresa Scribd logo
1 de 26
S. Makita (Sasebo National College of Tech.)
K. Okita (Canon Inc.)
Y. Maeda (Yokohama National University)


            ICMA 2012 in Chengdu, Sichuan, China, Aug.5-8, 2012
            WP2-7 Algorithm #232781
   3D Multifingered caging
    ◦ Geometrical constraint
       No force sensor and
        control

    ◦ By position-controlled
      robot

    ◦ Only geometrical
      information of objects
      are required

                               2
 Caging a concave object by 2
 fingertips in 2D [Rimon1999]
 ◦ Not in 3D space
 Caging
       an object by pointed finger in
 n-dimension [Pipattanasomporn2007]
 ◦ Not practical hands
 Caginggrasps by a humanoid robot
 [Diankov2008]
 ◦ Caging conditions were not derived
                                        3
 Caging for some simple-shaped
 objects by a practical robot hand
 [Makita2008]
 ◦ Theories to confine the target object
 ◦ RRT-based planning of finger
   configuration




                                           4
 Automatic   caging system
 ◦ Planning caging motions of arm/hand
   robot
 ◦ Object recognition using AR picture
   marker
                           How to cage
                           the object…




                                         5
1.   Classify the patterns of caging to
     determine strategies

2.   Motion planning by RRT (Rapidly-
     exploring Random Trees [Lavalle])

3.   Biased Sampling by solving inverse
     kinematics of the robot arm

4.   Object recognition using AR picture
     marker
                                           6
7
 Envelope-type   Caging
 ◦ A robot hand surrounds the object.




                                        8
 Ring-type   Caging
 ◦ The fingers of the hand are inserted to
   the hollow of the object.




                                             9
 Waist-type   Caging
 ◦ The fingers are wound around the
   constricted part of the object.




                                      10
Both fingertips are
    closer than the
thickness of the object



   The finger goes
 through the hollow
 region of the object

                          11
The constricted part
cannot escape from the
gap between fingertips

  The constricted part
goes through the hollow
   region of the hand

 The disk-shaped part
cannot escape from the
  ring-formed hand
                          12
13
 Make    configuration path
                                     Satisfying
                                      sufficient
                                     conditions




                            Random sampling




                         Collision
                          check
 Initial
 configuration
                                                   14
Randomly-sampled
configuration




 Biased sampling




                   15
Lhand:
                  Presumption of the length of
                  the hand

1. Give a desired position of the tool
   center point of the manipulator.
2. Give a desired orientation randomly.
3. Solve the inverse kinematics
                                                 16
 Necessary   info. for planning
 ◦ Category of objects
 ◦ Size
 ◦ Posture




                                   17
Camera



         Object
                  18
19
 6-DOF  manipulator
    (Yaskawa MOTOMAN-HP3J)
 Hand: 2 fingers and 2 joints for each




                                          20
50      124                    50
     38
                                  124
                         16   8
50                                             150


     cylinder   ring                    mug




                                                 21
1

           26


45

         222




                22
 Caging   a mug




                   23
24
 Some  sufficient conditions for caging
  are derived
 Motion planning for caging by a robot
  arm/hand system can be succeeded
  for four objects.
 Biased-sampling by solving IK
  contributes to searching efficiency.
 Object recognition by using AR
  marker is presented.
                                       25
 Reducing   planning time

 Object   recognition only by cameras

 More   variations on caging patterns
 ◦ Especially, envelope-type caging




                                         26

Mais conteúdo relacionado

Mais de Satoshi Makita

把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...
把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...
把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...
Satoshi Makita
 

Mais de Satoshi Makita (20)

ロボットマニピュレーションの作業・動作計画 / rosjp_planning_for_robotic_manipulation_20240521
ロボットマニピュレーションの作業・動作計画 / rosjp_planning_for_robotic_manipulation_20240521ロボットマニピュレーションの作業・動作計画 / rosjp_planning_for_robotic_manipulation_20240521
ロボットマニピュレーションの作業・動作計画 / rosjp_planning_for_robotic_manipulation_20240521
 
メカノクロミック構造色ゲルの色調変化に基づく接触荷重の推定-Contact_load_estimation_by_structural_color_cha...
メカノクロミック構造色ゲルの色調変化に基づく接触荷重の推定-Contact_load_estimation_by_structural_color_cha...メカノクロミック構造色ゲルの色調変化に基づく接触荷重の推定-Contact_load_estimation_by_structural_color_cha...
メカノクロミック構造色ゲルの色調変化に基づく接触荷重の推定-Contact_load_estimation_by_structural_color_cha...
 
RSJ2021: 押し操作における滑りに非平行な摩擦力の実験的検討 - Anisotropic frictional forces in sliding ...
RSJ2021: 押し操作における滑りに非平行な摩擦力の実験的検討 - Anisotropic frictional forces in sliding ...RSJ2021: 押し操作における滑りに非平行な摩擦力の実験的検討 - Anisotropic frictional forces in sliding ...
RSJ2021: 押し操作における滑りに非平行な摩擦力の実験的検討 - Anisotropic frictional forces in sliding ...
 
ロボットにぴったりの物体操作や作業の方法を探求する / Appropriate approaches to robotic manipulation
ロボットにぴったりの物体操作や作業の方法を探求する / Appropriate approaches to robotic manipulationロボットにぴったりの物体操作や作業の方法を探求する / Appropriate approaches to robotic manipulation
ロボットにぴったりの物体操作や作業の方法を探求する / Appropriate approaches to robotic manipulation
 
20210323 男性高専教員で育児休業した話
20210323 男性高専教員で育児休業した話 20210323 男性高専教員で育児休業した話
20210323 男性高専教員で育児休業した話
 
オンライン学会を支えるツール群 / Many web services for on-line academic conferences
オンライン学会を支えるツール群 / Many web services for on-line academic conferencesオンライン学会を支えるツール群 / Many web services for on-line academic conferences
オンライン学会を支えるツール群 / Many web services for on-line academic conferences
 
Robosemi - a brief survey on surveys on robotic manipulation researches
Robosemi - a brief survey on surveys on robotic manipulation researchesRobosemi - a brief survey on surveys on robotic manipulation researches
Robosemi - a brief survey on surveys on robotic manipulation researches
 
Homogeneous Quantitative Measure of Caging Grasps with both Geometrical and M...
Homogeneous Quantitative Measure of Caging Grasps with both Geometrical and M...Homogeneous Quantitative Measure of Caging Grasps with both Geometrical and M...
Homogeneous Quantitative Measure of Caging Grasps with both Geometrical and M...
 
凖静的な物体操作における動摩擦力と静止摩擦力の発生可能性 - Both kinetic and static friction on the slidin...
凖静的な物体操作における動摩擦力と静止摩擦力の発生可能性 - Both kinetic and static friction on the slidin...凖静的な物体操作における動摩擦力と静止摩擦力の発生可能性 - Both kinetic and static friction on the slidin...
凖静的な物体操作における動摩擦力と静止摩擦力の発生可能性 - Both kinetic and static friction on the slidin...
 
Electromyograph Classification of Six Hand-Actions for Twisting Manipulation ...
Electromyograph Classification of Six Hand-Actions for Twisting Manipulation ...Electromyograph Classification of Six Hand-Actions for Twisting Manipulation ...
Electromyograph Classification of Six Hand-Actions for Twisting Manipulation ...
 
把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...
把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...
把持のロバスト性解析に基づくパーシャルなケージングの定量的指標 / A quantitative index of partial caging base...
 
report slide for internship
report slide for internshipreport slide for internship
report slide for internship
 
ロボット研究のためのコミュニケーション活動 - Scientific Communication for Robotics Research / Sci2...
ロボット研究のためのコミュニケーション活動 - Scientific Communication for Robotics Research / Sci2...ロボット研究のためのコミュニケーション活動 - Scientific Communication for Robotics Research / Sci2...
ロボット研究のためのコミュニケーション活動 - Scientific Communication for Robotics Research / Sci2...
 
文部科学省 情報ひろばサイエンスカフェ「ロボット・情報×つながり」 / 20170126 mext science_cafe
文部科学省 情報ひろばサイエンスカフェ「ロボット・情報×つながり」 / 20170126 mext science_cafe文部科学省 情報ひろばサイエンスカフェ「ロボット・情報×つながり」 / 20170126 mext science_cafe
文部科学省 情報ひろばサイエンスカフェ「ロボット・情報×つながり」 / 20170126 mext science_cafe
 
Around northern kyushu - access guide
Around northern kyushu - access guideAround northern kyushu - access guide
Around northern kyushu - access guide
 
A use case of telepresence robots for science communication
A use case of telepresence robots for science communicationA use case of telepresence robots for science communication
A use case of telepresence robots for science communication
 
このロボットがすごい in 福岡
このロボットがすごい in 福岡このロボットがすごい in 福岡
このロボットがすごい in 福岡
 
バレーボールのオーバーハンドパスにおける手指の筋腱複合体の弾性特性に基づく コーチングへの一考察
バレーボールのオーバーハンドパスにおける手指の筋腱複合体の弾性特性に基づくコーチングへの一考察バレーボールのオーバーハンドパスにおける手指の筋腱複合体の弾性特性に基づくコーチングへの一考察
バレーボールのオーバーハンドパスにおける手指の筋腱複合体の弾性特性に基づく コーチングへの一考察
 
離島地区特有の資源と課題を考慮した科学コミュニケーション(RSJ2016)
離島地区特有の資源と課題を考慮した科学コミュニケーション(RSJ2016)離島地区特有の資源と課題を考慮した科学コミュニケーション(RSJ2016)
離島地区特有の資源と課題を考慮した科学コミュニケーション(RSJ2016)
 
サイエンスアイランドプロジェクト:リーフレット,science islands project: leaflet
サイエンスアイランドプロジェクト:リーフレット,science islands project: leafletサイエンスアイランドプロジェクト:リーフレット,science islands project: leaflet
サイエンスアイランドプロジェクト:リーフレット,science islands project: leaflet
 

Último

Último (20)

Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
 
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomSalesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
 
What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024
 
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
 
Buy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdfBuy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdf
 
Connecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAKConnecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAK
 
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya HalderCustom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
Custom Approval Process: A New Perspective, Pavel Hrbacek & Anindya Halder
 
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptxUnpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
 
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfWhere to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
 
PLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. StartupsPLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. Startups
 
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeFree and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
 
Intro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджераIntro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджера
 
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdfThe Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
The Value of Certifying Products for FDO _ Paul at FIDO Alliance.pdf
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2
 
Strategic AI Integration in Engineering Teams
Strategic AI Integration in Engineering TeamsStrategic AI Integration in Engineering Teams
Strategic AI Integration in Engineering Teams
 
Speed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in MinutesSpeed Wins: From Kafka to APIs in Minutes
Speed Wins: From Kafka to APIs in Minutes
 
A Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System StrategyA Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System Strategy
 
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
 

Motion Planning for 3D Multifingered Caging with Object Recognition using AR Picture Markers / Icma2012 presentation

  • 1. S. Makita (Sasebo National College of Tech.) K. Okita (Canon Inc.) Y. Maeda (Yokohama National University) ICMA 2012 in Chengdu, Sichuan, China, Aug.5-8, 2012 WP2-7 Algorithm #232781
  • 2. 3D Multifingered caging ◦ Geometrical constraint  No force sensor and control ◦ By position-controlled robot ◦ Only geometrical information of objects are required 2
  • 3.  Caging a concave object by 2 fingertips in 2D [Rimon1999] ◦ Not in 3D space  Caging an object by pointed finger in n-dimension [Pipattanasomporn2007] ◦ Not practical hands  Caginggrasps by a humanoid robot [Diankov2008] ◦ Caging conditions were not derived 3
  • 4.  Caging for some simple-shaped objects by a practical robot hand [Makita2008] ◦ Theories to confine the target object ◦ RRT-based planning of finger configuration 4
  • 5.  Automatic caging system ◦ Planning caging motions of arm/hand robot ◦ Object recognition using AR picture marker How to cage the object… 5
  • 6. 1. Classify the patterns of caging to determine strategies 2. Motion planning by RRT (Rapidly- exploring Random Trees [Lavalle]) 3. Biased Sampling by solving inverse kinematics of the robot arm 4. Object recognition using AR picture marker 6
  • 7. 7
  • 8.  Envelope-type Caging ◦ A robot hand surrounds the object. 8
  • 9.  Ring-type Caging ◦ The fingers of the hand are inserted to the hollow of the object. 9
  • 10.  Waist-type Caging ◦ The fingers are wound around the constricted part of the object. 10
  • 11. Both fingertips are closer than the thickness of the object The finger goes through the hollow region of the object 11
  • 12. The constricted part cannot escape from the gap between fingertips The constricted part goes through the hollow region of the hand The disk-shaped part cannot escape from the ring-formed hand 12
  • 13. 13
  • 14.  Make configuration path Satisfying sufficient conditions Random sampling Collision check Initial configuration 14
  • 16. Lhand: Presumption of the length of the hand 1. Give a desired position of the tool center point of the manipulator. 2. Give a desired orientation randomly. 3. Solve the inverse kinematics 16
  • 17.  Necessary info. for planning ◦ Category of objects ◦ Size ◦ Posture 17
  • 18. Camera Object 18
  • 19. 19
  • 20.  6-DOF manipulator (Yaskawa MOTOMAN-HP3J)  Hand: 2 fingers and 2 joints for each 20
  • 21. 50 124 50 38 124 16 8 50 150 cylinder ring mug 21
  • 22. 1 26 45 222 22
  • 23.  Caging a mug 23
  • 24. 24
  • 25.  Some sufficient conditions for caging are derived  Motion planning for caging by a robot arm/hand system can be succeeded for four objects.  Biased-sampling by solving IK contributes to searching efficiency.  Object recognition by using AR marker is presented. 25
  • 26.  Reducing planning time  Object recognition only by cameras  More variations on caging patterns ◦ Especially, envelope-type caging 26