JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/14771

Title: ERIS: Epigenetic Robot Intelligent System
Authors: Pratama, Ferdian
Mastrogiovanni, Fulvio
Chong, Nak Young
Keywords: developmental robotics
subjectivity principle
epigenetic architecture
robot past experience
progreesive knowledge development
developmental psychology
Issue Date: 2015
Publisher: RO-MAN2015
Magazine name: IEEE Ro-Man 2015 Workshop on MemX: Memory-inspired Robot Architectures for Human-Robot Interaction
Abstract: We present our ongoing long-term project on how a robot may develop its own knowledge using Epigenetic Robot Intelligent System (ERIS), an epigenetic architecture that provides a robot the means to gather its own knowledge based on visual observation, and in particular, to deliver the knowledge for a personalized human-robot interaction. ERIS is inspired by the current Developmental Psychology studies, which core concept is based on human memory organization, and we have developed the interconnected knowledge models as different forms of Long-Term Memory, and the means to process them as a simulated Working Memory Model. ERIS is also capable of acquiring and revising relevant knowledge during the interaction process. To demonstrate these features, experiments are focused on the observation and analysis of two identical robots exposed with a different visual stimuli and interaction processes. The results show that the identical robots integrated with ERIS exposed to different interaction history and external stimuli, yields a personalized human-robot interaction experience.
Rights: Copyright (C) 2015 Authors. Ferdian Pratama, Fulvio Mastrogiovanni, Nak Young Chong, IEEE Ro-Man 2015 Workshop on MemX: Memory-inspired Robot Architectures for Human-Robot Interaction, 2015.
URI: http://hdl.handle.net/10119/14771
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
21857.pdf313KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology