Bin-Picking (eBook)
XV, 117 Seiten
Springer International Publishing (Verlag)
978-3-319-26500-1 (ISBN)
This book is devoted to one of the most famous examples of automation handling tasks - the 'bin-picking' problem. To pick up objects, scrambled in a box is an easy task for humans, but its automation is very complex. In this book three different approaches to solve the bin-picking problem are described, showing how modern sensors can be used for efficient bin-picking as well as how classic sensor concepts can be applied for novel bin-picking techniques. 3D point clouds are firstly used as basis, employing the known Random Sample Matching algorithm paired with a very efficient depth map based collision avoidance mechanism resulting in a very robust bin-picking approach. Reducing the complexity of the sensor data, all computations are then done on depth maps. This allows the use of 2D image analysis techniques to fulfill the tasks and results in real time data analysis. Combined with force/torque and acceleration sensors, a near time optimal bin-picking system emerges. Lastly, surface normal maps are employed as a basis for pose estimation. In contrast to known approaches, the normal maps are not used for 3D data computation but directly for the object localization problem, enabling the application of a new class of sensors for bin-picking.
Acknowledgments 7
Contents 8
List of Figures 10
Abstract 13
1 Introduction---Automation and the Need for Pose Estimation 14
2 Bin-Picking---5 Decades of Research 16
2.1 The Early Years: Basic Developments 16
2.2 Modern Bin-Picking Approaches 21
2.3 Yet Another Bin-Picking-Approach? 22
2.3.1 Revisiting Robotic Bin-Picking---Problems to Be Solved 23
2.3.2 Contributions and Organization of This Work 24
3 3D Point Cloud Based Pose Estimation 26
3.1 Generic Pose Estimation Using 3D Point Clouds 27
3.1.1 3D Point Cloud Based Pose Estimation 27
3.1.2 3D Edge Based Pose Estimation 33
3.2 Bin-Picking Application---Collision Avoidance and Grasp Planning 36
3.2.1 Efficient 3D Collision Avoidance 36
3.2.2 Depth Image Based Collision Measurement 38
3.3 Experimental 3D Point Cloud Based Pose Estimation 41
3.3.1 Simulation 42
3.3.2 Real World Scenario 43
3.4 Discussion 50
4 Depth Map Based Pose Estimation 51
4.1 Gripper Pose Estimation 52
4.1.1 Fast Gripper Pose Hypotheses Generation 53
4.1.2 Hypothesis Evaluation and Gripper Pose Estimation 54
4.2 Modifications and Enhancements 57
4.2.1 Pitch and Yaw Angles of the Pick Pose 57
4.3 Bin-Picking Application---Grasp Pose Estimation 58
4.3.1 Vision Based Grasp Pose Estimation 59
4.3.2 Force/Torque/Acceleration Based Grasp Pose Estimation 60
4.4 Experimental Depth Map Based Bin-Picking 64
4.4.1 Hardware 64
4.4.2 Grasping Unknown Objects 65
4.4.3 Bin-Picking 66
4.5 Discussion 68
5 Normal Map Based Pose Estimation 69
5.1 The Normal Map 70
5.2 Generic Pose Estimation Using Normal Maps 70
5.2.1 Orientation Estimation 71
5.2.2 Accurate Monocular Translation Estimation 89
5.3 Bin-Picking Application---Collision Avoidance 96
5.4 Experimental Normal Map Based Grasping 96
5.4.1 Simulation 97
5.4.2 Real World Scenario 103
5.5 Discussion 106
6 Summary and Conclusion 108
Appendix A Data Acquisition 111
Own Publications and References 122
Erscheint lt. Verlag | 29.11.2015 |
---|---|
Reihe/Serie | Studies in Systems, Decision and Control | Studies in Systems, Decision and Control |
Zusatzinfo | XV, 117 p. 63 illus., 23 illus. in color. |
Verlagsort | Cham |
Sprache | englisch |
Themenwelt | Mathematik / Informatik ► Informatik ► Grafik / Design |
Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
Technik ► Maschinenbau | |
Schlagworte | 3D Point Clouds • Bin-Picking • computer vision • Depth Maps • Image Analysis • Industrial Robotics • Normal Maps • object localization • pose estimation |
ISBN-10 | 3-319-26500-8 / 3319265008 |
ISBN-13 | 978-3-319-26500-1 / 9783319265001 |
Haben Sie eine Frage zum Produkt? |
Größe: 4,7 MB
DRM: Digitales Wasserzeichen
Dieses eBook enthält ein digitales Wasserzeichen und ist damit für Sie personalisiert. Bei einer missbräuchlichen Weitergabe des eBooks an Dritte ist eine Rückverfolgung an die Quelle möglich.
Dateiformat: PDF (Portable Document Format)
Mit einem festen Seitenlayout eignet sich die PDF besonders für Fachbücher mit Spalten, Tabellen und Abbildungen. Eine PDF kann auf fast allen Geräten angezeigt werden, ist aber für kleine Displays (Smartphone, eReader) nur eingeschränkt geeignet.
Systemvoraussetzungen:
PC/Mac: Mit einem PC oder Mac können Sie dieses eBook lesen. Sie benötigen dafür einen PDF-Viewer - z.B. den Adobe Reader oder Adobe Digital Editions.
eReader: Dieses eBook kann mit (fast) allen eBook-Readern gelesen werden. Mit dem amazon-Kindle ist es aber nicht kompatibel.
Smartphone/Tablet: Egal ob Apple oder Android, dieses eBook können Sie lesen. Sie benötigen dafür einen PDF-Viewer - z.B. die kostenlose Adobe Digital Editions-App.
Zusätzliches Feature: Online Lesen
Dieses eBook können Sie zusätzlich zum Download auch online im Webbrowser lesen.
Buying eBooks from abroad
For tax law reasons we can sell eBooks just within Germany and Switzerland. Regrettably we cannot fulfill eBook-orders from other countries.
aus dem Bereich