A Review of Children, Humanoid Robots and Caregivers (Arsenio, 2004)

1. A Review of Children, Humanoid Robots and Caregivers(Arsenio, 2004) COM3240 – Week 3 Presented by Gizdem Akdur

2. A learning framework for a humanoid robot • Human-robot interactions • The importance of a human actor • Teaching humanoids as children • Inspired by cognitive development of a child • Dependence on mother • Awareness of his/her own individuality • Self-exploration of his/her surroundings • Implementation of concepts on the humanoid robot Cog

3. Inspiration from Mahler’s child development theory • Margaret Mahler (1897-1985) – Hungarian physician and psychoanalyst with a main interest in mother-infant duality and childhood development • Was influenced by Freud and Piaget • Developed the Separation-Individuation Theory of Child Development (1979)

4. Mahler’s theory (1979) • Autistic Phase (from birth – 1 month old) • Symbiotic Phase (until around 5 months old) • Separation and Individuation Phase • Differentiation (5-9 months) • Practising (10-18 months) • Re-approximation (15-24 months) • Individuality and Object Constancy (24-36 months)

5. Learning on the Autistic and Symbiotic Phases • Autistic phase • The newborn is mostly in a sleeping state. Awakens to eat and satisfy other necessities • Motor skills mainly consist of primitive reflexes • Symbiotic phase • Infant’s attention dropped to repeatedly moving objects and to sudden changes of motion • Repetition helps • Motivated the design of algorithms for detection of events • Object Segmentation algorithm • extending the algorithms of previous studies – Arsenio, 2003 and Fitzpatrick, 2003

6. Help from a human tutor • will guide the robot learning about its physical surroundings • Correlate data among its own senses • Control and integrate situational cues from its surrounding world • Learn about out-of-reach objects and the different representations they might appear • therefore special emphasis will be placed on social learning along a child’s physical topological spaces robot executes a simple learned task (waving), and associates the sound to the movement of its own body

7. Physical topological spaces (1) the robot's personal space, consisting of itself and familiar, manipulable objects (2) its living space, such as a bedroom or living room (3) its outside, unreachable world, such as the image of a bear on a forest

8. (1) Learning about objects and itself • Strategy described for a robot to associate data from several resources • from its own senses • from its senses and information stored on the world/robot’s memory • 3 main schemes to be implemented • Cross-modal data association • Object recognition • Educational activities

9. (1.1) Cross-modal data association • Extracting visual and audio features – patches of pixels and sound frequency bands. The algorithm was therefore extended to detect both • Identification of robot’s own acoustic rhythms and the visual recognition of robot’s mirror image Child and robot looking at a mirror, associating their image to their body (image/sound association for the robot has been amplified)

10. (1.2) Object recognition • A recognition scheme for objects (other than the robot’s body part) with 3 independent algorithms • Colour • Luminance • Shape • Geometric hashing for high-speed performance • Adaptive Hash Table was implemented Object recognition and location in a computer generated bedroom. Scene lines matched to the train are outlined.

11. (1.3) Learning from educational activities • Corresponds to child’s practising (10-18 months) developmental sub-phase towards re-approximation (15-24 months) sub-phase • Robot learns object properties not only through cross-modal data correlations, but also by correlating human gestures and information stored in the world structure or on its own database • Object recognition algorithm applied to extract correlations between sensorial signals perceived from the world and geometric shapes present in such world

12. (2) Learning the world structure of the robot’s physical surroundings • Determining where objects should be stored based on probability of finding them on that place later • If a book is placed in the fridge, the robot will hardly find it! • The framework, developed to capture knowledge stored in robot’s surrounding world, consists of: • (1) Learning 3D scenes from cues provided by a human actor • (2) Learning the spatial configuration of the objects within a scene

13. (2.1) Learning about scenes • The environment surrounding the robot provides additional structure that can be learned through supervised learning techniques • Defining scenes as a collection of objects with an uncertain geometric configuration, each object at a minimum distance from another Segmentation error analysis for furniture items on a scene – samples also shown

14. (2.2) Learning about objects in scenes • Humanoids (like children) need to learn the relative probability distribution of objects in a scene • Constraining the search space is important to optimise computational resources • Contextual features incorporate functional constraints • Wavelet transformation (Strang and Nguyen, 1996) used • Holistic representation of the scene • Main spectral characteristics of a scene encoded with a rough description of its spatial arrangement Reconstruction of the original image by the Wavelet transform. An holistic representation of the scene.

15. (3) Learning about the outside world through books • Books are useful to teach different object representations and to communicate properties of unknown objects to them • Human-robot interactions are very essential at this stage. A human tutor does the job of a mother of a child who teaches from books by tapping on the book’s representations • Segmentation by demonstration algorithm used

16. (3.1) Matching multiple representations • Object representations obtained from a book are put into a database for future recognition tasks • Methods were developed to establish a link between an object representation and real objects from surroundings using the object recognition technique • The framework can be applied on paintings, prints, photos and computer generated objects • Object recognition helps with the recognition of similar shapes with different colours but same geometric contours

17. Conclusion • A developmental object perception framework has been described which aims to teach humanoids as children • The epigenetic principle taken as a foundation • Robot learned about its surrounding world by building scene descriptions of world structures • Contextual selections by using probabilities • Storing information about object shapes for later use • The learning process with the guidance of a human tutor is essential to help the humanoid through its cognitive development

18. Thanks for listening