Sosyal robotlar için davranış modüllerinin otomatik kümelenmesi

Loading...
Thumbnail Image

Date

2023

Journal Title

Journal ISSN

Volume Title

Publisher

Open Access Color

OpenAIRE Downloads

OpenAIRE Views

Research Projects

Organizational Units

Organizational Unit
Mechatronics Engineering
(2002)
The Atılım University Department of Mechatronics Engineering started its operation in 2002 as the Education Program in Mechatronics Engineering holding a “department” status in Turkey. In addition, it is the first and the only institution for mechatronic engineering education to obtain a MÜDEK (Association for Evaluation and Accreditation of Engineering Programs) accreditation for a duration of 5 years. Mechatronics engineering is a discipline of engineering that combines mechanical, electrical and electronic engineering and software technologies on a machine or a product. These features place the field on a pedestal in today’s industry. The education at our department is also backed by substantial laboratory opportunities. Our students create interesting products of their skills and creativity for their dissertation projects. Should they wish to do so, our students may also proceed with a double-major program in the fields of Computer Engineering, Electrical - Electronics Engineering, Industrial Engineering, or Mechanical, Automotive or Software Engineering. Upon their demands, the Department of Mechatronic Engineering also offers a “Cooperative Education” program implemented in coordination with industrial institutions. Students receiving a portion of their training at industrial institutions and prepare for professional life under this program

Journal Issue

Abstract

Bu tezde, sosyal robotların davranış modüllerinin kümeleme algoritmaları kullanılarak otomatik oluşturulması için bir yöntem sunulmuştur. Davranış modülleri, kişiselleştirilmiş sosyal robotların tasarımında büyük önem taşımaktadır. Sunulan araştırmada, sosyal robotların 'algı', 'biliş' ve 'motorik eylem' olarak adlandırılan davranış öğelerini kümelemek için K-means, Aglomerative Clustering ve BRICH gibi farklı kümeleme tekniklerinin uygulanabilirliği incelenmiştir. Bu amaçla, daha önce yapılan bir çalışmada elde edilen 28x3 boyutunda ve yukarıdaki üç davranış için dilsel değerlerden oluşan bir veri listesi kullanılmıştır. Geliştirilen bir haritalama yöntemi ile sayısal olarak temsil edilen verilerle sekiz farklı kümeleme algoritması kullanılarak oluşturulan çeşitli davranış modülleri değerlendirilmiş ve üç algoritma başarılı kabul edilmiştir. Kümeleme algoritmalarıyla otomatik olarak elde edilen davranış modüllerinin 3 boyutlu gösterimi de yapılmıştır. Elde edilen modüller maliyet, hareketlilik, karmaşıklık ve güç tüketimi olmak üzere dört farklı ölçüt kullanılarak değerlendirilmiştir. Bu çalışmanın sonuçları kişiselleştirilmiş sosyal robotların sistematik tasarımı alanındaki araştırmalarda ve uygulamalarda kullanılabilir.
This thesis presents a method for automatically generating behaviour modules for social robots using clustering algorithms. Behavioural modules are considered a vital element of social robot family design which falls in the benefit of individual's needs. The work includes the implementation of different clustering techniques such as K-means, Agglomerative Clustering, and BRICH to cluster behavioural elements of social robot which are categorized as 'perception', 'cognition' and 'motoric action'. In this thesis, a previously generated data list consisting of linguistic values from these elements in size of 28 by 3 is used. A mapping method is developed to represent the data in numeric form. Also, a 3D graphical representation of the data is obtained. In addition, a variety of behavioural modules are generated and evaluated using right clustering algorithms, three algorithms of which are decided as successful. The generated modules are evaluated based on four criteria as, cost, mobility, complexity, and power consumption. The results of this work can be used by researchers and engineers in the field of social robotics particularly during the conceptual design of personalized social robots. Additionally, the proposed criteria and visualization techniques can be used as a starting point for future research in this area.

Description

Keywords

Mekatronik Mühendisliği, Mechatronics Engineering

Turkish CoHE Thesis Center URL

Fields of Science

Citation

WoS Q

Scopus Q

Source

Volume

Issue

Start Page

0

End Page

111