2. © sebastian thrun, CMU, 20001 16-899C Statistical Techniques In Robotics Sebastian Thrun and Geoffrey Gordon Carnegie Mellon University www.cs.cmu.edu/~thrun www.cs.cmu.edu/~ggordon

3. © sebastian thrun, CMU, 20002 notes  Pointer to Larry’s material

4. © sebastian thrun, CMU, 20003 Administrative Information  Sebastian Thrun thrun@cs.cmu.edu  Geoffrey Gordonggordon@cs.cmu.edu  Web: http://www.cs.cmu.edu/~16899  Email list: 16-899@cs.cmu.edu  Time:Mon/Wed, 10:30-11:50am  Location:NSH 3302  TA:n/a  Appointments: send Email!

5. © sebastian thrun, CMU, 20004

6. 5 Goals  Enable you to program robots and embedded systems in a robust fashion  Enable you to understand the intrinsic assumptions in your robot software  Enable you to pursue original research in probabilistic robotics  Sway you into joining a young and fascinating research field: probabilistic robotics

7. © sebastian thrun, CMU, 20006 What this course is not  Intro to robotics  Little work  Low on math

8. © sebastian thrun, CMU, 20007 Course Schedule Localization Sept 4-16 Mapping Sept 30-Oct 16 Decision Making Oct 21-30 Multi-Agent Nov 4-11 Advanced Perception Nov 13-25

9. © sebastian thrun, CMU, 20008 What You Should Do  Think  Think differently  Be critical  Come up with Original Research

10. © sebastian thrun, CMU, 20009 What Is A Good Project  Mine Mapping  Multi-Agent Control

11. © sebastian thrun, CMU, 200010 Requirements  In teams of three: Warm-up project (mobile robot localization) Written assignment(s) Research Project  Class Presence: all but two sessions (send me email)  Quizzes (all but at most two)  No exams

12. © sebastian thrun, CMU, 200011 Your next tasks  Check out Web site Read assigned paper Download map+sensor data and program robot localization algorithm  Send Sebastian mail with your name and names of team mates (for warm-up project)  Come to class on Sept 9 th (10:30am-11:50am)

13. © sebastian thrun, CMU, 200012

14. © sebastian thrun, CMU, 200013

15. © sebastian thrun, CMU, 200014

16. © sebastian thrun, CMU, 200015

17. © sebastian thrun, CMU, 200016 Five Sources of Uncertainty Environment Dynamics Random Action Effects Sensor Limitations Inaccurate Models Approximate Computation

18. © sebastian thrun, CMU, 200017 Trends in Robotics Reactive Paradigm (mid-80’s) no models relies heavily on good sensing Probabilistic Robotics (since mid-90’s) seamless integration of models and sensing inaccurate models, inaccurate sensors Hybrids (since 90’s) model-based at higher levels reactive at lower levels Classical Robotics (mid-70’s) exact models no sensing necessary

19. © sebastian thrun, CMU, 200018

20. © sebastian thrun, CMU, 200019 Rhino

21. © sebastian thrun, CMU, 200020 Minerva

22. © sebastian thrun, CMU, 200021 The CMU/Pitt Nursebot Initiative

23. © sebastian thrun, CMU, 200022 People Detection Mike Montemerlo

24. © sebastian thrun, CMU, 200023 Learning Models of People Maren Bennewitz

25. © sebastian thrun, CMU, 200024 3D Mapping Result With: Christian Martin

26. © sebastian thrun, CMU, 200025 Multi-Robot Exploration

27. © sebastian thrun, CMU, 200026 Mine Mapping (brand new)

28. © sebastian thrun, CMU, 200027 What are interesting problems?  Mapping, automatic, manual, guided?  Probabilistic localization, landmarks?, odometer!,  Route planning, collision avoidance  Mine Mapping?

29. © sebastian thrun, CMU, 200028 How can we solve them?

30. © sebastian thrun, CMU, 200029

31. © sebastian thrun, CMU, 200030 Where Am I/?

32. © sebastian thrun, CMU, 200031 Nature of Sensor Data: Uncertainty Odometry Data Range Data

33. © sebastian thrun, CMU, 200032

34. © sebastian thrun, CMU, 200033 Warm-Up Assignment: Localization, Due Sept 23

35. © sebastian thrun, CMU, 200034 Warm-Up Assignment: Localization

36. © sebastian thrun, CMU, 200035 Warm-Up Assignment: Localization