Primjena skrivenih Markovljevih modela za raspoznavanje gesti u funkcionalnoj i simboličkoj imitaciji

master's thesis

• Title (english): Application of Hidden Markov Models for Gesture Recognition in Functional and Symbolic Imitation
• Author: Luka Malovan
• Mentor: Zdenko Kovačić (mentor)
• Committee member: Zdenko Kovačić (predsjednik povjerenstva)
• Committee member: Stjepan Bogdan (član povjerenstva)
• Committee member: Matko Orsag (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovome radu opisana je implementacija funkcionalnosti potrebnih za evaluaciju interakcije NAO robota i djeteta kao pomoć pri dijagnostici autizma. Evaluacija interakcije između robota i djeteta vrši se prema ADOS protokolu (Autism Diagnostic Observation Schedule). Interakcija se svodi na pokazivanje geste te praćenja reakcije djeteta kada se od njega očekuje imitacija iste. Funkcionalna i simbolička imitacija sastoji se od nekoliko cjelina. Iz tog razloga protokol je implementiran kao automat s konačnim brojem stanja. Protokol počinje inicijalizacijom robota i programa te se zatim izvršava detekcija predmeta, njegovih dimenzija i oblika te poznavajući te informacije robot izvodi manipulaciju predmetom. Zadnja cjelina protokola je prepoznavanje geste iz trajektorije predmeta pomoću skrivenih Markovljevih modela. U svrhu preciznijeg praćenja predmeta implementiran je Kalmanov filtar čime je poboljšano prepoznavanje gesti. Dobiven je protokol imitacije koji je robustan i s velikom preciznošću prepoznaje geste. Ovime su ostvarene funkcionalnosti pomoću kojih je moguće evaluirati interakciju. Dobiveni su dobri rezultati u laboratorijskim uvjetima testiranja što je dovelo do uspješnog ostvarenja početne faze evaluacije interakcije robota i djeteta.

Abstract (english)

This work presents implementation of evaluation software for interaction between a
NAO robot and a child in robot assisted autism diagnostic. Evaluation of interaction
between a robot and a child is done through the ADOS (Autism Diagnostic Observation
Schedule) protocol. Interaction is based on a played scenario where the robot is
performing a certain gesture and it observes the child’s response when the imitation
of the same gesture is expected. Functional and symbolic imitation consists of several
parts. This is why it is implemented as a finite state machine. The protocol starts by robot and program initialization which is followed by object detection, assessment of its shape and dimensions which is information crucial for object manipulation. The last part of the protocol is gesture recognition of the object trajectory using Hidden Markov Models(HMM). Kalman filter is implemented in order to achieve better gesture recognition. The result is an imitation protocol which is robust and very precise.Functionalities that enable evaluation of interaction are developed. They have provided good results in laboratory testing conditions which led to successful accomplishment of the first phase of robot and child interaction evaluation.

• Keywords: Autizam; robotom potpomognuta dijagnostika; automat s konačnim brojem stanja; strojno učenje; skriveni Markovljevi modeli; Kalmanov filtar; NAO robot
• Keywords (english): Autism; robot assisted diagnosis; Finite state machine; machine learning; Hidden Markov Models; Kalman filter; NAO robot
• Language: english
• URN:NBN: urn:nbn:hr:168:634955
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 10:17:23