1. From Imprinting to Adaptation: Building a History of Affective Interaction Adaptive System Research Group School of Computer Science University of Hertfordshire, UK Arnaud J. Blanchard BlanchardArnaud@Gmail.com Lola Cañamero L.Canamero@herts.ac.uk

2. From Imprinting to Adaptation2 Introduction ‏Imitation / synchronisation useful in development To learn To communicate To survive, satisfy needs ‏Problems What and how to imitate When to imitate Who to imitate What makes a successful imitation

3. From Imprinting to Adaptation3 Approach ‏Approach Bottom up: as simple as possible Per-Ac: no explicit representation of the world Biologically possible Developmental ‏Consequences Perception and action at the same level (Gaussier, Prinz) The goal is not to do an action but to obtain a perception We will use “Goal Perception”

4. From Imprinting to Adaptation4 Who and when to imitate ? ‏Imitation has to be done At the right moment With the right agents ‏During the development The agent has to learn: Where is better to be Who is better to imitate ‏Affectivity between new born and care-taker

5. From Imprinting to Adaptation5 Affective bonds ‏“Emotional Contagion” E. Hatfield (1994) Affective bonds increase imitation / synchronization Imitation / synchronization increase affective bonds ‏Problems How to manage the affective bonds ? When to lead interaction ? ‏To start these bonds we can observe the nature

6. From Imprinting to Adaptation6 Imprinting phenomena ‏1930’s Lorenz Birds follow the first thing they saw Usually the mother but also humans or objects The birds try to keep the first perception This phenomena can be a cue to create affective bonds in robots

7. From Imprinting to Adaptation7 Implementation ‏Goal Perception Average of the first perceptions We can express this as a stochastic learning The learning rate decreases with the time from “hatching” time from “hatching” learning rate

8. From Imprinting to Adaptation8 Experimentation ‏We apply it to distance perception

9. From Imprinting to Adaptation9 Adaptation ‏Observations Interesting as it reproduces natural behavior But not very useful for daily interaction ‏Bateson (2000) Imprinting is not an “instantaneous, irreversible process” ‏Notion of comfort Distance to ideal values (homeostatic control) Comfort between 0 and 1 Decreases when the distance increases

10. From Imprinting to Adaptation10 Relativity of the comfort ‏The learning rate Does not depend on the absolute value of comfort Depends only on the relative value of comfort ‏Learning faster when the comfort is high How fast is “faster” ? …

11. From Imprinting to Adaptation11 Times scales ‏We use different time scales – “Desired Perceptions” Long terms: very slow changes Short terms: very fast changes We use several time scales in between learning rate time from “hatching”

12. From Imprinting to Adaptation12 Acting ‏Selecting a time scale High comfort: using short time scale Low comfort: using long time scale time comfort current time start ? future

13. From Imprinting to Adaptation13 New perceptions ‏To learn, the robot has to accept new perceptions When the comfort is very high (no risk) When the comfort is very low (waiting for help) ‏  Varying openness to the world comfort activity

14. From Imprinting to Adaptation14 Final architecture

15. From Imprinting to Adaptation15 Experimentation ‏Comfort management The comfort increases by touching a side sensor The comfort decreases with the time The robot tries to keep a high level of contact The frequency of beeps reflects the level of discomfort comfort lot of contactsfew contacts

16. From Imprinting to Adaptation16 Video

17. From Imprinting to Adaptation17 Results

18. From Imprinting to Adaptation18 Conclusion ‏Affective bonds without symbolic representation Similarity with biology Robustness of the learning with the time Learning and acting simultaneous Continuity with reinforcement learning Capacity to decide when to lead the interaction

19. From Imprinting to Adaptation19 Perspectives ‏Further works Notion of fear or avoidance Active exploration with notion of pleasure Taking account of different contexts Taking account of different modalities More analysis with biology Low level of imitation depending on affective bonds

20. From Imprinting to Adaptation20 Synchronization seems to make happy

21. From Imprinting to Adaptation21 I want make my robot happy …

22. From Imprinting to Adaptation22 Thank you for your attention Silvia Helena Cardoso, PhD and Renato M.E. Sabbatini, PhD Arnaud J. Blanchard e-mail: BlanchardArnaud@Gmail.com homepage: arnaudblanchard.free.fr Lola Cañamero e-mail: L.Canamero@herts.ac.uk homepage: homepages.feis.herts.ac.uk/~comqlc/