2. CS 547: Sensing and Planning in Robotics Gaurav S. Sukhatme Computer Science Robotics Research Laboratory University of Southern California gaurav@usc.edu http://robotics.usc.edu/~gaurav

3. Administrative Matters Signup - please fill in the details on one of the sheets Web page http://robotics.usc.edu/~gaurav/CS547 http://robotics.usc.edu/~gaurav/CS547 Email list cs547@robotics.usc.educs547@robotics.usc.edu Grading (3 quizzes 45%, class participation 5%, and project 50%) TA: Mike Rubenstein (mrubenst@usc.edu) Note: First quiz on Sept 8, scores available on Sept 10 by 1pm

4. Project and Textbook Project –Team projects only (exceptions are hard to obtain) –Equipment (Pioneer/Segway robots with sensors, Player/Stage/Gazebo software) Book –Probabilistic Robotics (Thrun, Burgard, Fox) –Available at the Paper Clip in University Village (North of Jefferson Blvd.)

5. I expect you to come REGULARLY to class visit the class web page FREQUENTLY read email EVERY DAY SPEAK UP when you have a question START EARLY on your project If you don’t –the likelihood of learning anything is small –the likelihood of obtaining a decent grade is small

6. In this course you will –learn how to address the fundamental problem of robotics i.e. how to combat uncertainty using the tools of probability theory –We will explore the advantages and shortcomings of the probabilistic method –Survey modern applications of robots –Read some cutting edge papers from the literature

7. Syllabus and Class Schedule 8/25Introduction, math review 9/1Math review, Bayes filtering 9/8Math review, Quiz 1 9/15Quiz 1 discussion, Player/Stage/Gazebo tutorial 9/22Kalman and Particle filters 9/29Probabilistic Kinematics 10/6Sensor Models 10/13Localization papers 10/20No class, but Project Proposals due to the TA 10/27Cooperative localization papers and Quiz 2 11/3Quiz 2 discussion, Mapping 11/10SLAM 11/17Acting under uncertainty 11/24Quiz 3 12/1Final project demos

8. Robotics Yesterday

9. Robotics Today

10. Robotics Tomorrow?

11. What is robotics/a robot ? Background –Term robot invented by Capek in to mean a machine that would willing and ably do our dirty work for us –The first use of robotics as a word appears in Asimovs science Definition (Brady): Robotics is the intelligent connection of perception of action

12. Trends in Robotics Research 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 Robots are moving away from factory floors to Entertainment, Toys, Personal service. Medicine, Surgery, Industrial automation (mining, harvesting), Hazardous environments (space, underwater)

13. Examples

14. Entertainment Robots: Toys

15. Entertainment Robots: RoboCup

16. Autonomous Flying Machines

17. Humanoids

18. Mobile Robots as Museum Tour- Guides

19. Tasks to be Solved by Robots  Planning  Perception  Modeling  Localization  Interaction  Acting  Manipulation  Cooperation ...

20. Uncertainty is Inherent/Fundamental Uncertainty arises from four major factors: –Environment is stochastic, unpredictable –Robots actions are stochastic –Sensors are limited and noisy –Models are inaccurate, incomplete

21. Nature of Sensor Data Odometry Data Range Data

22. Probabilistic Robotics Key idea: Explicit representation of uncertainty using the calculus of probability theory Perception = state estimation Action = utility optimization

23. Advantages and Pitfalls Can accommodate inaccurate models Can accommodate imperfect sensors Robust in real-world applications Best known approach to many hard robotics problems Computationally demanding False assumptions Approximate

24. Pr(A) denotes probability that proposition A is true. Axioms of Probability Theory

25. A Closer Look at Axiom 3 B

26. Using the Axioms

27. Discrete Random Variables X denotes a random variable. X can take on a finite number of values in {x 1, x 2, …, x n }. P(X=x i ), or P(x i ), is the probability that the random variable X takes on value x i. P( ) is called probability mass function. E.g..

28. Continuous Random Variables X takes on values in the continuum. p(X=x), or p(x), is a probability density function. E.g. x p(x)

29. Joint and Conditional Probability P(X=x and Y=y) = P(x,y) If X and Y are independent then P(x,y) = P(x) P(y) P(x | y) is the probability of x given y P(x | y) = P(x,y) / P(y) P(x,y) = P(x | y) P(y) If X and Y are independent then P(x | y) = P(x)

30. Law of Total Probability Discrete caseContinuous case

31. Reverend Thomas Bayes, FRS (1702-1761) Clergyman and mathematician who first used probability inductively and established a mathematical basis for probability inference

32. Bayes Formula

33. Normalization Algorithm:

34. Conditioning Total probability: Bayes rule and background knowledge:

35. Simple Example of State Estimation Suppose a robot obtains measurement z What is P(open|z)?

36. Causal vs. Diagnostic Reasoning P(open|z) is diagnostic. P(z|open) is causal. Often causal knowledge is easier to obtain. Bayes rule allows us to use causal knowledge: count frequencies!

37. Example P(z|open) = 0.6P(z|  open) = 0.3 P(open) = P(  open) = 0.5 z raises the probability that the door is open.

38. Combining Evidence Suppose our robot obtains another observation z 2. How can we integrate this new information? More generally, how can we estimate P(x| z 1...z n ) ?

39. Recursive Bayesian Updating Markov assumption: z n is independent of z 1,...,z n-1 if we know x.

40. Example: Second Measurement P(z 2 |open) = 0.5P(z 2 |  open) = 0.6 P(open|z 1 )= 2/3 z 2 lowers the probability that the door is open.

41. Actions Often the world is dynamic since –actions carried out by the robot, –actions carried out by other agents, –or just the time passing by change the world. How can we incorporate such actions?

42. Typical Actions The robot turns its wheels to move The robot uses its manipulator to grasp an object Plants grow over time… Actions are never carried out with absolute certainty. In contrast to measurements, actions generally increase the uncertainty.

43. Modeling Actions To incorporate the outcome of an action u into the current “belief”, we use the conditional pdf P(x|u,x’) This term specifies the pdf that executing u changes the state from x’ to x.

44. Example: Closing the door

45. State Transitions P(x|u,x’) for u = “close door”: If the door is open, the action “close door” succeeds in 90% of all cases.

46. Integrating the Outcome of Actions Continuous case: Discrete case:

47. Example: The Resulting Belief