ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 End-to-End Learning of Social Behaviors for Humanoid Robots
Cited 2 time in scopus Download 4 time Share share facebook twitter linkedin kakaostory
저자
고우리, 이재연, 장민수, 김재홍
발행일
202010
출처
International Conference on Systems, Man, and Cybernetics (SMC) 2020, pp.1-6
DOI
https://dx.doi.org/10.1109/SMC42975.2020.9283177
협약과제
20HS2500, 고령 사회에 대응하기 위한 실환경 휴먼케어 로봇 기술 개발, 이재연
초록
Social robots should understand the user's nonverbal behavior and respond appropriately. Machine learning is one way of implementing the social intelligence. It provides the ability to automatically learn and improve from experience instead of explicitly telling the robot what to do. This paper proposes an end-to-end machine learning method to learn social behaviors for humanoid robots. We adapt sequence-to-sequence architecture consisting of two long short-term memory (LSTM) units. One is an LSTM encoder for encoding the previous sequence of human poses, and the other is an LSTM decoder for generating the next sequence of robot poses. The weights of the LSTMs are trained using human-human interaction data such as greeting and handshaking. The trained model is implemented in a humanoid robot, Pepper, to show its feasibility. Experimental results show that the robot can generate gestures appropriate to the situation and recognize subtle differences in user behavior. In addition, when a user's behavior changes, the transition to another behavior occurs naturally.
키워드
deep learning, gesture generation, interaction behavior, social behavior, Social robot
KSP 제안 키워드
End to End(E2E), Gesture generation, Human-Human Interaction, Interaction behavior, Long short-term memory, Machine Learning Methods, Sequence architecture, Social Intelligence, Social behavior, User behavior, User's Behavior