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

Slides:



Advertisements
Similar presentations
Cognitive Systems, ICANN panel, Q1 What is machine intelligence, as beyond pattern matching, classification and prediction. What is machine intelligence,
Advertisements

Face Alignment by Explicit Shape Regression
Copyright © Allyn & Bacon 2004 Development Through the Lifespan Chapter 5 Cognitive Development in Infancy and Toddlerhood This multimedia product and.
Perception and Perspective in Robotics Paul Fitzpatrick MIT Computer Science and Artificial Intelligence Laboratory Humanoid Robotics Group Goal To build.
Infants - Intellectual Development. Intellectual Development I.D. is how people learn, what they learn and how they express what they know through language.
Patch to the Future: Unsupervised Visual Prediction
Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects by Paul A. Viola Presented By: Emrah Ceyhan Divin Proothi Sherwin Shaidee.
COGNITIVE VIEWS OF LEARNING Information processing is a cognitive theory that examines the way knowledge enters and is stored in and retrieved from memory.
Current Trends in Image Quality Perception Mason Macklem Simon Fraser University
Knowledge Acquisitioning. Definition The transfer and transformation of potential problem solving expertise from some knowledge source to a program.
True music must repeat the thought and inspirations of the people and the time. My people are children and my time is today.
Computational Vision Jitendra Malik University of California at Berkeley Jitendra Malik University of California at Berkeley.
CS292 Computational Vision and Language Visual Features - Colour and Texture.
CHAPTER 5. ◦ Key battleground of nature vs. nuture debate ◦ Nativism (inborn) vs. empiricism (skills are learned)  WAYS OF STUDYING EARLY PERCEPTUAL.
Chapter 2: Piaget's Stages of Cognitive Development Jean Piaget ( )
 For many years human being has been trying to recreate the complex mechanisms that human body forms & to copy or imitate human systems  As a result.
Cognitive Development Cognitive development refers to the growth and change of a person’s ability to process information, solve problems and gain knowledge.
Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Cognitive Robots © 2014, SNU CSE Biointelligence Lab.,
Shape Recognition and Pose Estimation for Mobile Augmented Reality Author : N. Hagbi, J. El-Sana, O. Bergig, and M. Billinghurst Date : Speaker.
Cognitive Development in Infancy and Toddlerhood
Multimedia Databases (MMDB)
Prakash Chockalingam Clemson University Non-Rigid Multi-Modal Object Tracking Using Gaussian Mixture Models Committee Members Dr Stan Birchfield (chair)
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
Intelligent Vision Systems ENT 496 Object Shape Identification and Representation Hema C.R. Lecture 7.
Lecture 2b Readings: Kandell Schwartz et al Ch 27 Wolfe et al Chs 3 and 4.
Shane T. Mueller, Ph.D. Indiana University Klein Associates/ARA Rich Shiffrin Indiana University and Memory, Attention & Perception Lab REM-II: A model.
Cognitive Views of Learning
Physical Development In Utero: – Zygote: conception-2 weeks – Embryo: 2 weeks-2 months (8 weeks) Cell differentiation – Fetus: 2 months to birth Functioning.
Visual Information Systems Recognition and Classification.
WestEd.org California’s Infant/Toddler Learning & Development Foundations.
Natural Tasking of Robots Based on Human Interaction Cues Brian Scassellati, Bryan Adams, Aaron Edsinger, Matthew Marjanovic MIT Artificial Intelligence.
Computer Graphics and Image Processing (CIS-601).
Advances in digital image compression techniques Guojun Lu, Computer Communications, Vol. 16, No. 4, Apr, 1993, pp
Interactive Learning of the Acoustic Properties of Objects by a Robot
2005/12/021 Content-Based Image Retrieval Using Grey Relational Analysis Dept. of Computer Engineering Tatung University Presenter: Tienwei Tsai ( 蔡殿偉.
Event retrieval in large video collections with circulant temporal encoding CVPR 2013 Oral.
2005/12/021 Fast Image Retrieval Using Low Frequency DCT Coefficients Dept. of Computer Engineering Tatung University Presenter: Yo-Ping Huang ( 黃有評 )
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
Object Lesson: Discovering and Learning to Recognize Objects Object Lesson: Discovering and Learning to Recognize Objects – Paul Fitzpatrick – MIT CSAIL.
Week 2-1: Human Information Processing
Chapter 1. Cognitive Systems Introduction in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans Park, Sae-Rom Lee, Woo-Jin Statistical.
Exploiting cross-modal rhythm for robot perception of objects Artur M. Arsenio Paul Fitzpatrick MIT Computer Science and Artificial Intelligence Laboratory.
Digital Video Library Network Supervisor: Prof. Michael Lyu Student: Ma Chak Kei, Jacky.
Colour and Texture. Extract 3-D information Using Vision Extract 3-D information for performing certain tasks such as manipulation, navigation, and recognition.
Competencia 16 Matematicas The teacher understands how children learn mathematical skills and uses knowledge to plan, organize, and implement instruction.
Chapter 8. Learning of Gestures by Imitation in a Humanoid Robot in Imitation and Social Learning in Robots, Calinon and Billard. Course: Robots Learning.
Give examples of the way that virtual reality can be used in Psychology.
HFE 760 Virtual Environments Winter 2000 Jennie J. Gallimore
CognitiveViews of Learning Chapter 7. Overview n n The Cognitive Perspective n n Information Processing n n Metacognition n n Becoming Knowledgeable.
Feel the beat: using cross-modal rhythm to integrate perception of objects, others, and self Paul Fitzpatrick and Artur M. Arsenio CSAIL, MIT.
1 Applying Principles To Reading Presented By Anne Davidson Michelle Diamond.
Pattern Recognition. What is Pattern Recognition? Pattern recognition is a sub-topic of machine learning. PR is the science that concerns the description.
CHAPTER 2 Cognitive development Identify the four factors that, according to Piaget, influence children’s thinking from early childhood to adulthood.
Copyright 2012 Pearson Education. Vukelich, Helping Young Children Learn Language and Literacy: Birth Through Kindergarten 3/e Chapter 1 Foundations of.
Natalija Budinski Primary and secondary school “Petro Kuzmjak” Serbia
Christina Pelletier Columbus State University
Processing visual information for Computer Vision
San Diego May 22, 2013 Giovanni Saponaro Giampiero Salvi
- photometric aspects of image formation gray level images
DIGITAL SIGNAL PROCESSING
JEAN PAIGET "The principle goal of education in the schools should be creating men and women who are capable of doing new things, not simply repeating.
Learning about Objects
Concept Development NYDBC Chris Russell.
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Chapter 7: Social Behaviour and Personality in Infants and Toddlers
Chris Russell Hunter College SPED 746 Fall 2014
Grouping/Segmentation
Theories of Development
Cognitive Development in Infancy and Toddlerhood
Presentation transcript:

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

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

Inspiration from Mahler’s child development theory Margaret Mahler ( ) – 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)

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)

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

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

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

(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

(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)

(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.

(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

(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

(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

(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.

(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

(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

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

Thanks for listening