social assistive robotics for children with cerebral palsy

24
MOTIVATION OF CHILDREN WITH CEREBRAL PALSY BY RAC-CP FUN (ROBOTICS AGENT COACHER FOR CP MOTOR FUN CTION) Dr. Marina Fridin 1 Dr. Mark Belokopytov 2,3 1 Ariel University Center 2 Assaf Harofeh Medical Center 3 Ben-Gurion University of the Negev The T herapeutic and E ducational S ocial R obotics L ab Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012

Upload: marina-fridin

Post on 07-May-2015

453 views

Category:

Technology


0 download

TRANSCRIPT

  • 1.MOTIVATION OF CHILDREN WITH CEREBRAL PALSY BY RAC-CP FUN (ROBOTICS AGENT COACHER FOR CP MOTOR FUNCTION) Dr. Marina Fridin1 Dr. Mark Belokopytov2,3 1Ariel University Center 2Assaf Harofeh Medical Center 3Ben-Gurion University of the Negev The Therapeutic and Educational Social Robotics Lab Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012

2. CEREBRAL PALSY (CP) - Spectrum of non-progressive syndromes of posture and motor impairments that result from an insult to the developing central nervous system Characterized by: body function impairments activity limitations participation limitations Often accompanied by disturbances of sensation, cognition, communication, perception, and/or behaviour. Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 3. SOCIAL ASSISTIVE ROBOTICS (SAR) - SAR is the class of robots that provide various types of assistance to various vulnerable populations primarily through social, rather than physical interaction. POPULATIONS: Elderly: Post- stroke rehabilitation, Matari, et al., 2007 Alzheimers disease , Tapus et..al. ,2009 Hospital delivery robot, Mutlu & Forlizzi ,2008 Nursing home residents , Wada et.al. , 2004 Children, mainly for children with autism spectrum disorders (ASD) Scassellati, et al. 2007. Robins, et al., 2005. Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 4. Hands off RAC CP Fun Body Structure & Functions Activity Participation Environmental Factors Personal Factors Health condition (disorder or disease)Therapist Hands on Motor Actions I N T E R N AT I O N A L C L A S S I F I C AT I O N O F F U N C T I O N I N G , D I S A B I L I T Y A N D H E A LT H ( I C F ) F R A M E W O R K , ( W H O , 2 0 0 2 ) Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 5. RAC CP Fun Body Structure & Functions Activity Participation Environmental Factors Personal Factors Therapist RAC CP Fun Health condition (disorder or disease) Hands on Conceptual Interference Environment Taxonomy Learning Algorithm Hands off Human-Robot Interaction Motor GamesMotor Actions Adaptation to personality, mood and motor performance Motivation: feedback, mirroring effect Team Decomposition Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 6. MOTIVATION AS PART OF A GAME Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 Embedded features: Play-like activate Toy appearance of the robot Emotional arousal Variety of games NOT ENOUGH 7. SUBJECTS Subject Gender Age (yrs) GMFCS 1 M 5.8 III 2 M 5.9 III 3 M 6.3 I 4 F 5.7 II 5 M 6.2 IV 6 M 5.8 III 7 M 6.1 II 8 M 6.3 III 9 M 4.9 IV 10 M 5.1 II 11 F 5.4 II Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 All diagnosed as CP 8. SETUP Operator Cameras Staff ~0.8m ~0.5m ~2 m Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 0.5m 1.2m 0.5m 9. DATA ANALYSIS Interaction Level (IL) Cognitive Performance (V) Motor Performance 3 1 ** F FSss FWSignECIL Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 RT AVE V )(1 Coding Performance 0 did not perform 1 attempt to perform - 2nd attempt 2 incomplete performance- 2nd attempt 3 attempt to perform - 1st attempt 4 complete performance- 2nd attempt 5 incomplete performance- 1st attempt 6 complete performance- 1st attempt 10. EXPERIMENT 1: FIRST MEETING PROCEDURE AIM: the robot introduces itself to the children, explains its intention, demonstrates games, explains its limitations (ethical issues) MOTIVATION: the robots create enjoyable interaction, emotional arousal, creates personal contact, reduces childrens and staffs concern RESULT: children enjoyed, actively played with robot, participated in the conversation with the robot , allowed the robot to be in their personal space Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 11. Procedureflow Interaction level -10 0 10 20 30 40 Hello Introduction Song Conversation Motor game Robot falls down Explanation Parting 0 1 2 Execution CP ND 12. AIM: motor exercises (symmetrical, asymmetrical, and dual tasks) MOTIVATION: the robot is personal toy, personal feedback RESULTS: high interaction, high performance (better then educational staff expected), possible correlation between exercise difficulty and motivation EXPERIMENT 2: ONE-TO-ONE MOTOR INVOLVEMENT Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 13. Procedureflow Interaction level 0 5 10 15 20 Intro SM AM DT Motor performance 0 2 4 6 CP ND 14. EXPERIMENT 3 : ROBY SAID AIM: collaborative motor game (symmetrical, asymmetrical, and complex tasks), selective attention MOTIVATION: the robot initiates and mediates a social game RESULTS: children enjoy, high interaction, improvement in motor performance and selective attention CHALLENGE: variability of childrens reactions and abilities, need of social psychology approach (despair attention, feedback, adaptive games flow) Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 15. EXPERIMENT 4: FOUR SEASONS AIM: to explore a possibility to facilitate the development of spatial cognition (as example of cognitive abilities) of the children MOTIVATION: competition between children, experience in operating the robot, classical music, dancing RESULTS: children enjoyed, their cognitive performance were improved CHALLENGE: adjustment of the robots behavior to the variability of the physical and mental abilities of the children Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 16. Sketch Picture IL V 17. EXPERIMENT 5: COMPLEX INTERACTION AIM: to test a constructive learning approach (using books and furniture), accompanied with motor and cognitive development MOTIVATION: the robot is a help-seeker, natural environment RESULT: help-seeker is efficient, single robots can not fit complex interaction CHALLENGE: need for assortment of behaviors driven by the childs personality Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 18. VARIABILITY of REACTIONS Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 E., 4 yrs, Hemiplegia, ADHD, GMFSC I M., 4 yrs, Spastic diplegia, ADHD, GMFCS II A., 6 yrs, Hemiplegia, GMFSC III D., 6 yrs, Spastic syndrome, ADHD, GMFSC I Fragment of long scenario. Goal: to induce arm rising to maximal range 19. THE SCHEME OF THE RAC CP FUN MODULES AND DATA FLOW Low-level Perception Kinect: Motion processing Robots Video: High color saturation filters Skin-color filters Edge detection Disparity computation Robots Sensors: Data filtering Motor module Visual-motor skills Manipulation skills (reaching/ grasping) Expressive skills (bodily/facial/vocalizations) Attention module Attention on a child with fastest/slowest reactions Attention on a child defined by physiotherapist Motivation module Positive-negative reinforcement Qualitive and quantative feedback Empathy and mirroring effect Behavior module Behavior selection Decomposition to the set of operations: body movements, operational vocabulary, sounds, emotiona l expressions High-level Perception Visual: Scene analysis and segmentation Face and eye detection Whole body labeling Subjects identification Gaze direction Emotional Recognition Kinect: Extremities movement analysis Sensory Data fusion Adaptation module Adjustment to the stage of motor learning Mood and current success level Personality matching: hyperactive/passive Information analysis module Subjects motor behavior analysis Subjects cognitive behavior analysis Monitoring of the level of interaction strength Recognition of subjects attention state Input Robot: Sensors data, including Scene video Kinect: Movement tracking Physiotherapist: Settings Personal and Anthropometric data Functional (pathological) restrictions Tasks difficulty Session scenario components Safety module Avoid children in robots working space Databas e Self-awareness module Error detection/Success measuring Locomotion, Falling, Manipulation Robot localization Personal Information Pathology characteristics: GMFCS, Altered side, Assistive device Motor functions : Time of sit-stand initiation, Symmetry of holding arms Child-Robot Interaction Measurements: Emotional status, Responsiveness Environment: Place, # participants Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 20. SUMMARY Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 Unconstrained interaction Personal toy Social mediator Combined: competitive, entertaining, operated by a child Help-seeker Strategy for motivation Assortment of behaviors Taskcomplexity Variabilityofreactions Need 21. CONCLUSIONS RAC CP FUN is a feasible and promising new research area of social assistive technology with immeasurable potential RAC CP FUN may stimulate the development of new treatments for a wide variety of diseases and disorders through effective physiotherapy practice Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 22. RESEARCH GROUP Dr. Mark BelokopytovDr. Simona Bar-Haim Bella DavidovGuy Keren Ronit Aviram MESHI Jerusalem Workshop on Motivational Aspects of Robotics in Physical Therapy, IROS 2012 23. IROS 2012 THANK YOU FOR ATTENTION