Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Modeling Human Imitation as Probabilistic Inference and an Application in Robotics

Mike Chung
March 02, 2015

Modeling Human Imitation as Probabilistic Inference and an Application in Robotics

A part of the invited talk, "Infant imitation, brain, and social cognition" by Andrew N. Meltzoff, at HRI 2015 "Cognition: A Bridge between Robotics and Interaction" Workshop (http://www.macs.hw.ac.uk/~kl360/HRI2015W/index.html)

Mike Chung

March 02, 2015
Tweet

More Decks by Mike Chung

Other Decks in Research

Transcript

  1. The “Like-Me” Hypothesis Self-experience allows infants to interpret the act

    of other Self-experience plays an important role in goal inference and imitation Meltzoff, Dev Sci, 2007
 Meltzoff, Acta Psychologica, 2007 Computational Model: Probabilistic instantiation of “Like-me” hypothesis
  2. Computational Model : goal : action : start state :

    final state Friesen & Rao, Cog Sci, 2011
  3. Computational Model: Gaze Following : desired fixation location : head

    motor commands : start head pose : final head pose Friesen & Rao, Cog Sci, 2011
  4. Computational Model: Gaze Following : desired fixation location : head

    motor commands : start head pose : final head pose Random Variables are Continuous Relations are Probabilistic Functions
  5. Probabilistic Functions: Gaussian Processes (GP) ‣ nonparametric ‣ probabilistic distribution

    over functions Effective with small numbers of training examples
  6. Goal-directed Planning G A B Xi Xf Given goal and

    start state, infer action. Closed form solutions.
  7. Goal Inference G A B Xi Xf Given start state

    and final state, infer goal. Approximate via Bayesian Monte Carlo.
  8. Gaze Following Gm Am Bm Xm i Xm f A

    G B Xi X f change of coords. Given: mentor start state, mentor final state, start state
 Infer: mentor goal, action OTHER SELF Infer goal
  9. Model Simulation 0 200 400 600 −600 −400 −200 0

    200 400 x position (cm) y position (cm) Agent Mentor true fixation points inferred fixation points 500 -500 500 100
  10. Model Performance 0 200 400 600 −600 −400 −200 0

    200 400 x position (cm) y position (cm) Agent Mentor true fixation points inferred fixation points
  11. Blindfold Self-Experience Task Gm Am Bm Xm i Xm f

    A G B Xi X f change of coords.
  12. Blindfold Self-Experience Task Baseline Window Opaque 0 1 2 3

    4 Looking Score (a) Computational Model (b) Infant Data AGENT (simulation results) INFANT (actual behavior data) Friesen & Rao, Cog Sci, 2011
  13. Computational Model: Robotic Tabletop Manipulation : desired tabletop position :

    control commands : start object location : final object location Random Variables are Discrete Relations are Probability Tables
  14. Goal-Based Imitation and Action Selection Step1: Goal-Inference Step II: Action-Inference

    Step III:
 Final State Prediction Gm Am Bm Xm i Xm f A G B Xi X f change of coords.
  15. Learned Transition Model Place Right Place Off-table Push Right Push

    Off-table Place Right Place Off-table Push Right Push Off-table
  16. Learned Transition Model Place Right Place Off-table Push Right Push

    Off-table Place Right Place Off-table Push Right Push Off-table
  17. Learned Transition Model Place Right Place Off-table Push Right Push

    Off-table Place Right Place Off-table Push Right Push Off-table
  18. Action Inference Place Left Place Right Place Off Push Left

    Push Right Push Off Place Left Place Right Place Off Push Left Push Right Push Off Goal ✴MAP Prediction Demonstration: Xi = LEFT, Xf = RIGHT
  19. A Bayesian Developmental Approach to Goal-Based Imitation Learning Michael Jae-Yoon

    Chung, Abram L. Friesen,
 Dieter Fox, Andrew N. Meltzoff, and Rajesh P.N. Rao University of Washington HRI2015 Workshop Cognition: A Bridge between robotics and interaction
  20. Imitation Learning in Humans Not mere trajectory following. Imitation based

    on goal inference. Demonstration Goal-based imitation Infants above 1.5 years of age can imitate action even from an unsuccessful demonstration (Meltzoff & Brook 1998)
  21. Another Example: Gaze Following and Blindfolds 12 month olds Meltzoff

    & Brooks, Dev Psych Blind fold experience no training after training
  22. The “Like-Me” Hypothesis Self-experience allows infants to interpret the act

    of others. Self-experience plays an important role in goal inference and imitation. Computational Model: Probabilistic instantiation of “Like-me” hypothesis. Meltzoff, Dev Sci, 2007 Metlzoff, Acta Psychologica, 2007
  23. Model Performance 0 10 20 30 40 0 0.05 0.1

    0.15 0.2 gaze error (degrees) p(error) −40 −20 0 0 0.05 0.1 0.15 0.2 gaze error (degrees) p(error) −40 −20 0 0 0.05 0.1 0.15 0.2 gaze error (degrees) p(error) (a) Forward Inference (b) Reverse Inference (c) Gaze Following