affordance based perception learning and planning using
play

Affordance-based Perception, Learning and Planning using Range - PowerPoint PPT Presentation

Affordance-based Perception, Learning and Planning using Range Images Erol ahin KOVAN Research Lab. Dept of Computer Eng. Middle East Technical University Ankara, TURKEY http://kovan.ceng.metu.edu.tr Dept. of Computer Engineering 1


  1. Affordance-based Perception, Learning and Planning using Range Images Erol Ş ahin KOVAN Research Lab. Dept of Computer Eng. Middle East Technical University Ankara, TURKEY http://kovan.ceng.metu.edu.tr Dept. of Computer Engineering 1 Middle East Technical University

  2. Developmental/Epigenetic Robotics Behavior development in psychology J. Piaget & E.J. Gibson Controlled Discovery of Repeated Reflexes action capabilities interaction Affordances Use relations Discover Interact Simple in goal-directed general with the pre-coded behavior relations environment behaviors M.Cakmak, M.R.Dogar, E. Ugur and E.Sahin. Affordances as a Framework for Robot Control . Proc. of 2 EpiRob’07.

  3. Learning of Affordances • Differentiation: discovering distinctive features and invariant properties in the environment • Exploratory activities that bring about changes in the environment that an action produces • Perceptual Learning: develop an anticipation of outcomes based on perception of invariants, actions become performatory E.J. Gibson (1910–2002) 3

  4. Equivalence Classes Behavior Equivalence Entity Equivalence (effect, (entity, <behavior>)) (effect, (<entity>, behavior)) Effect Equivalence Affordance Equivalence (effect, <(entity, behavior)>) 4

  5. Experimental Framework (1/2) • 6 wheel, differential drive • MACSim : High-fidelity simulation environment • SICK laser range finder • ODE used as physics engine • 3-D scanning • Sensors and actuators are – 0.25° horizontal resolution calibrated (180°) – 0.23° vertical resolution (165°) 5

  6. Experimental Framework (2/2) Primitive behaviors Limited motor capability Pre-coded 6

  7. Perceptual Features More than 30000 perceptual features! 7

  8. Part 1: Perceptual Learning of Affordances 8

  9. Traversability for KURT3D 9

  10. Representation of entity and effect A single interaction Perceive Act Get result Features(initial) MOVE_FORWARD Success/Fail 3000 x entity behavior effect • E.Ugur, M.R.Dogar, M.Cakmak and E.Sahin. The Learning and Use of Traversability Affordances using Range Images on a mobile robot. ICRA, Rome, Italy, April 2007. 10

  11. Learning: Selecting relevant features 3000 interactions Effect: Filtered Effect: Entity success Entity success Filtered Effect: Effect: Entity Entity fail fail Feature . . Selection . . (ReliefF) . . Effect: Filtered Effect: Entity fail Entity fail 11

  12. Perceptual Economy Scan only this region Only 1% of the features are relevant! 12

  13. Learning: Mapping entity to effect 3000 interactions Target Effect: Filtered success Entity values Effect: Filtered fail Entity . SVM . input . Effect: Filtered fail Entity 13

  14. Prediction of Traversibility for Novel Objects TRAIN TEST prediction prediction 100% 86% 100% 100% 83.8% Successful generalization over novel objects 14

  15. Traversability in a cluttered environment 15

  16. Traversibility on KURT3D 16

  17. Pass-thru-ability on KURT3D • The training used only single object interactions. • The robot has not concept of an object or a gap. • The robot does not have any idea on the size of its body. • Yet, one can see an affordance ratio here.. How would Warren et al. comment? 17

  18. Curiosity-Driven Learning • Large number of training samples were required: – ~3000 virtual interactions with environment. – Learning process is costly, time-consuming, risky. • Minimize number of interactions with minimal degradation in learning process. 2 phase learning: – Bootstrapping: small number of interactions • Learn the relevant features • Initiate an SVM model. – Curiosity-driven • Interact with the environment and update SVM only if the current situation is an interesting one • E.Ugur, M.R.Dogar, M.Cakmak and E.Sahin. Curiosity-driven Learning of Traversability Affordance on a 18 Mobile Robot . ICDL, London, UK, July 2007.

  19. Not interesting! Probably traversable Probably non-traversable No object in the vicinity Cylinder object is very close. 19

  20. Interesting Object is located Cylinder’s surface is at the boundaries for similar to sphere’s Go-forward action 20

  21. Curiosity-Driven Learning PERCEPT SVM (trained upto now) • Within curiosity band • Outside curiosity band • Classifier is less certain about hypothesized effect • Classifier is more certain about hypothesized effect • Execute behavior • Do not execute behavior • Learn from this sample. (Update SVM). • Skip this sample. 21

  22. Two parameters of learning • Bootstrapping duration: No improvement after a certain level (25) • Width of curiosity-band is optimized. (0.5) • With bootstrapping of 25 and curiosity of 0.5, 200 interactions delivers as good/better performance than 3000 interactions! 22

  23. Performance comparison Curiosity-based interaction is more economical 23

  24. Part 2: From Primitive to Goal-Directed Behaviors 24

  25. Representation of entity and effect A single interaction Perceive Act Perceive Features(initial) MOVE_FORWARD Features(final) Features(final-initial) 3000 x entity behavior effect M.R.Dogar, M. Cakmak, E. Ugur and E. Sahin. From Primitive Behaviors to Goal-Directed Behavior Using Affordances. IROS, San Diego, October 2007. 25

  26. Learning: Cluster Effects For each behavior: Effect Effect mean 3000 interactions category-1 prototype-1 Entity Effect Entity Effect mean Effect K-means Effect . prototype-2 category-2 (k=10) . . . . . . . Entity Effect Effect mean Effect category-10 prototype-10 No fail/success criteria! 26

  27. Learning: Selecting relevant features 3000 interactions Effect Filtered Effect Entity category Entity category Filtered Effect Effect Entity Entity category category Feature . . Selection . . (ReliefF) . . Effect Filtered Effect Entity category Entity category 27

  28. Learning: Mapping entity to effect Target 3000 interactions Effect Filtered category Entity values Effect Filtered category Entity . SVM . input . Effect Filtered category Entity 28

  29. Goal-directed Behaviors Behavior … Behavior Perception Execution Perception Selection Selection 29

  30. Goal: Approach 30

  31. Goal-directed Behaviors on KURT3D Goal is provided at run-time not during learning! 31

  32. Blending Behaviors Motor parameters 0.4 x Weighted sum Similarity 0.6 x 0 x Inspiration source: Population coding in motor cortex • M.R.Dogar. Using Learned Affordances for Robotic Behavior Development. M.Sc. Thesis, Middle East Technical University, Ankara, September 2007. • M.R.Dogar, E.Ugur, E.Sahin and M.Cakmak. Using Learned Affordances for Robotic Behavior 32 Development. . Accepted to ICRA’08.

  33. Goal: Approach Using primitive behaviors Using behavioral generalization Primitive behavior Blending of behaviors 33

  34. Blending Behaviors on KURT3D Behavior blending allows to span a whole range of behaviors from a limited pre-coded primitive behaviors 34

  35. Part 3: Planning with Learned Affordances 35

  36. Behaviors Movement Behaviors Lift Behavior • E.Ugur, M.R.Dogar and E.Sahin. Planning with Learned Object Affordances . Submitted to AAAI’08. 36

  37. Perception 37

  38. Predicting the next state of the entity • Adding the effect prototype of the behavior to be applied to the current entity representation provides us a prediction of the expected state of the entity. 38

  39. Plan Generation 39

  40. Sample Plans 40

  41. Analysis of effect classes 41

  42. Learning Process 42

  43. Planning Performance 43

  44. Goal: Activate the Button • Goal: – Any object: The range image coordinate features should be high – Button object: Mean distance should be small 44

  45. Planning on KURT3D 45

  46. Acknowledgements Maya Cakmak Mehmet R. Dogar Emre Ugur Multi-sensory Autonomous Cognitive Systems supported within the Cognitive Systems Call of FP6-IST (FP6-IST-2-004381) 46

Recommend


More recommend