1. Robot Vision SS 2009 Matthias Rüther 1 710.088 ROBOT VISION 2VO 1KU Matthias Rüther

2. Robot Vision SS 2009 Matthias Rüther 2 Administrative Things VO: Tuesday 14:30-16:00 HS i11 Strongly coupled with KU!! www.icg.tu-graz.ac.at/courses tu-graz.lv.robot_vision_ue Exam: Written Exam Oral Exam if Requested KU: Groups of three students Effort: >=1week per student

3. Robot Vision SS 2009 Matthias Rüther 3 Time Table

4. Robot Vision SS 2009 Matthias Rüther 4 Literature Sciavicco, L., Siciliano, B., Modelling and Control of Robot Manipulators 2nd Ed., Springer, 2000 Sonka M., Hlavac V., Boyle Image Processing, Analysis and Machine Vision, Chapman Hall, 1998 Hartley R., Zissermann A., Multiple View Geometry in Computer Vision, Cambridge, 2001.

5. Robot Vision SS 2009 Matthias Rüther 5 Robotics  What is a robot? "A reprogrammable, multifunctional manipulator designed to move material, parts, tools, or specialized devices through various programmed motions for the performance of a variety of tasks" Robot Institute of America, 1979 … in a three-dimensional environment.  Industrial –Mostly automatic manipulation of rigid parts with well-known shape in a specially prepared environment.  Medical –Mostly semi-automatic manipulation of deformable objects in a naturally created, space limited environment.  Field Robotics –Autonomous control and navigation of a mobile vehicle in an arbitrary environment.

6. Robot Vision SS 2009 Matthias Rüther 6 Experimental/Industrial/Commercial Robots

7. Robot Vision SS 2009 Matthias Rüther 7 Industrial Robots

8. Robot Vision SS 2009 Matthias Rüther 8 Challenging Environments

9. Robot Vision SS 2009 Matthias Rüther 9 Service and Assistance

10. Robot Vision SS 2009 Matthias Rüther 10 FRIEND Project

11. Robot Vision SS 2009 Matthias Rüther 11 Robot vs Human  Robot Advantages : –Strength –Accuracy –Speed –Does not tire –Does repetitive tasks –Can Measure  Human advantages: –Intelligence –Flexibility –Adaptability –Skill –Can Learn –Can Estimate

12. Robot Vision SS 2009 Matthias Rüther 12 Robotics: Goals and Applications  Goal: combine robot and human abilities.  Applications: –Automation (Production) –Inspection (Quality control) –Remote Sensing (Mapping) –Man-Machine interaction („Cobot“) –Robot Companion (Physically challenged people) –See [Brady, M. et. al. (eds). „Robot Motion: Planning and Control“]

13. Robot Vision SS 2009 Matthias Rüther 13 Statistics Yearly installations of industrial robots, 2003-2004 and forecast for 2005-2008

14. Robot Vision SS 2009 Matthias Rüther 14 Statistics Estimated operational stock of industrial robots 2003-2004 and forecast for 2005-2008

15. Robot Vision SS 2009 Matthias Rüther 15 Statistics Number of robots per 10,000 production workers in the motor vehicle industry 2002 and 2004

16. Robot Vision SS 2009 Matthias Rüther 16 Statistics Service robots for professional use. Stock at the end of 2004 and projected installations in 2005-2008

17. Robot Vision SS 2009 Matthias Rüther 17 Statistics Service robots for personal and domestic use. Stock and value of stock at the end of 2004 and projected installations in 2005 - 2008

18. Robot Vision SS 2009 Matthias Rüther 18 What can Computer Vision do for Robotics?  Accurate Robot-Object Positioning  Keeping Relative Position under Movement  Visualization / Teaching / Telerobotics  Performing measurements  Object Recognition (see LV „Bildverarbeitung u. Mustererkennung“, „Bildverstehen“, „AK Computer Vision“)  Registration Visual Servoing

19. Robot Vision SS 2009 Matthias Rüther 19 Computer Vision  What is Computer Vision? "Computer Vision describes the automatic deduction of the structure and the properties of a (possible dynamic) three- dimensional world from either a single or multiple two-dimensional images of the world" [Nalva VS, "A Guided Tour of Computer Vision"]  Measurement –Measure shape and material properties in a 3D environment. Accuracy is important.  Recognition –Cognitive systems interpret a 3D environment (object classification, categorization). Systems are allowed to fail to a certain extent (similar to humans).  Navigation –Navigation Systems orient themselves in a 3D environment. Robustness and time are important.

20. Robot Vision SS 2009 Matthias Rüther 20 Shape from Stereo

21. Robot Vision SS 2009 Matthias Rüther 21 Shape from Stereo

22. Robot Vision SS 2009 Matthias Rüther 22 Shape from Focus

23. Robot Vision SS 2009 Matthias Rüther 23 Shape from Structured Light  Structured Light Sensor Figures from PRIP, TU Vienna

24. Robot Vision SS 2009 Matthias Rüther 24 Shape from Shading

25. Robot Vision SS 2009 Matthias Rüther 25 Navigation  SLAM: Simultaneous Localization and Mapping. –Where am I on my map? –If the place is unknown, build a new map, try to merge it with the original map.  Visual Odometry: calculate the relative motion of the camera between two frames. Summing up the motion gives the camera path. Error propagation!  Visual Servoing: move to / maintain a relative position between robot end effector and an object.  Tracking: continuously measure the position of an object within the sensor coordinate frame.

26. Robot Vision SS 2009 Matthias Rüther 26 SLAM Mapping:

27. Robot Vision SS 2009 Matthias Rüther 27 SLAM The final map:

28. Robot Vision SS 2009 Matthias Rüther 28 SLAM Navigation:

29. Robot Vision SS 2009 Matthias Rüther 29 Visual Odometry

30. Robot Vision SS 2009 Matthias Rüther 30 Visual Servoing

31. Robot Vision SS 2009 Matthias Rüther 31 Tracking

32. Robot Vision SS 2009 Matthias Rüther 32 Registration  Registration of CAD models to scene features: Figures from P.Wunsch: Registration of CAD-Models to Images by Iterative Inverse Perspective Matching