Convolutional Neural Network 기반 실시간 자율 댄싱 로봇 시스템

다국어 초록 (Multilingual Abstract)

This paper proposes a real-time autonomous dancing robot system that listens to arbitrary music inputted in real time and then can dance according to the genre of the music. The proposed system autonomously performs the whole dancing by selecting the dancing motion that matches the music genre and predicting the beat-related information for synchronization between the robot motion and the music. The proposed system updates the data of the input audio signal every 5 second using the first-in first-out method. In addition, the updated data are used as the input for both the short-term music genre classifier based on CNN (Convolutional Neural Network) and the beat detector to detect the beat interval time and the beat start time. A rule-based decision algorithm is suggested to improve the decision success rates of both the genre classifier and the bit detector and to detect the change of music genre simultaneously. Also the proposed system is verified by some examples.

목차 (Table of Contents)

• Abstract
• I. 서론
• II. CNN 기반 단 구간 음악 장르 분류기와 비트 검출기
• III. 실시간 자율 댄싱 로봇 시스템
• IV. 자율 댄싱 로봇 시스템의 구현
• V. 실험 및 검증
• VI. 결론
• REFERENCES

참고문헌 (Reference)

1 유제훈, "컨볼루셔널 신경망과 케스케이드 안면 특징점 검출기를 이용한 얼굴의 특징점 분류" 제어·로봇·시스템학회 22 (22): 241-246, 2016

2 천경민, "제스처 할당 모드를 이용한 마리오네트 조정 시스템" 제어·로봇·시스템학회 21 (21): 150-156, 2015

3 J. Foote, "The Beat Spectrum: A New Approach To Rhythm Analysis" 2001

4 M. Alonso, "Tempo And Beat Estimation Of Musical Signals" 158-163, 2004

5 S. Han, "Open software platform for robotic services" 9 (9): 467-481, 2012

6 김성훈, "OPRoS 기반 로봇시스템의 Robot-in-the-Loop Simulation 구조" 제어·로봇·시스템학회 19 (19): 248-255, 2013

7 M. Goto, "Music understanding at the beat level : Real-time beat tracking for audio signals" 68-75, 1998

8 Q. Kong, "Music Genre Classification Using Convolutional Neural Networks"

9 B. Logan, "Mel Frequency Cepstral Coefficients for Music Modeling" 2000

10 F. Chollet, "Keras: Deep learning library for theano and tensorflow"

11 P. Baxter, "From Characterising Three Years of HRI to Methodology and Reporting Recommendations" 391-398, 2016

12 H. S. Park, "Development of an open software platform for robotics services" 4773-4775, 2009

13 F. Masahiro, "Development of an autonomous quadruped robot for robot entertainment" 5 (5): 7-18, 1998

14 D. Grunberg, "Development of an autonomous dancing robot" 3 (3): 33-44, 2010

15 T. Shiratori, "Detecting dance motion structure through music analysis" 857-862, 2004

16 K. Shinozaki, "Concept and construction of a robot dance system" 6 (6): 29-34, 2007

17 K. Ichiro, "Biomechanism" University of Tokyo Press 173-214, 1973

18 J. H. Seo, "Autonomous humanoid robot dance generation system based on real-time music input" 204-209, 2013

19 A. Manfrè, "An automatic system for humanoid dance creation" 15 : 1-9, 2016

20 M. Goto, "An audio-based real-time beat tracking system for music with or without drum-sounds" 30 (30): 159-171, 2001

21 P. Zhang, "A Deep Neural Network for Modeling Music" ACM 2015