Journal of KIISE:Software and Applications (한국정보과학회논문지:소프트웨어및응용)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Mixed-Initiative Interaction between Human and Service Robot using Hierarchical Bayesian Networks

계층적 베이지안 네트워크를 사용한 서비스 로봇과 인간의 상호 주도방식 의사소통

  • 송윤석 (연세대학교 컴퓨터과학과) ;
  • 홍진혁 (연세대학교 컴퓨터과학과) ;
  • 조성배 (연세대학교 컴퓨터과학과)
  • Published : 2006.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

In daily activities, the interaction between humans and robots is very important for supporting the user's task effectively. Dialogue may be useful to increase the flexibility and facility of interaction between them. Traditional studies of robots have only dealt with simple queries like commands for interaction, but in real conversation it is more complex and various for using many ways of expression, so people can often omit some words relying on the background knowledge or the context of the discourse. Since the same queries can have various meaning by this reason, it is needed to manage this situation. In this paper we propose a method that uses hierarchical bayesian networks to implement mixed-initiative interaction for managing vagueness of conversation in the service robot. We have verified the usefulness of the proposed method through the simulation of the service robot and usability test.

일상 생활에서 서비스 로봇이 효과적으로 사람들의 업무를 보조하기 위해서는 인간과의 상호작용이 매우 중요하다. 그 중 대화는 인간과 로봇이 보다 유연하고 풍부한 의사전달을 하는데 유용하다. 전통적인 로봇 연구에서는 의사소통 방법으로 명령과 같은 간단한 질의 등을 사용하였으나 실제 사람들의 대화는 보다 복잡하고 다양하며 배경 지식이나 대화의 문맥 등에 의해 중요한 정보가 생략되기도 한다. 따라서 동일한 질의라도 다양한 의미를 갖기 때문에 정확한 해석을 위해서는 이를 다루어야 한다. 본 논문에서는 계층적 베이지안 네트워크를 사용하여 '상호-주도형' 의사 소통 방식을 서비스 로봇에 구현함으로써 대화의 모호성을 처리하는 방법을 제안한다. 또한 서비스 로봇의 시뮬레이션과 사용자 평가를 통해 제안하는 방법의 유용성을 확인하였다.

Keywords

References

  1. C. Breazeal, 'Social interactions in HRI: The robot view,' IEEE Trans. Systems, Man, and Cybernetics-Part C: Applications and Reviews, vol. 34, no. 2, pp. 181-186, 2004 https://doi.org/10.1109/TSMCC.2004.826268
  2. A. Agah, 'Human interactions with intelligent systems: Research taxonomy,' Computers and Electrical Engineering, vol. 27, no. 1, pp. 71-107, 2001 https://doi.org/10.1016/S0045-7906(00)00009-4
  3. S. Lauria, et aI., 'Personal robots using natural language instruction,' IEEE Intelligent Systems, vol. 16, no. 3, pp. 38-45, 2001 https://doi.org/10.1109/5254.956080
  4. T. Fong, et al., 'Robot, asker of questions,' Robotics and Autonomous Systems, vol. 42, no. 3-4, pp, 235-243, 2003 https://doi.org/10.1016/S0921-8890(02)00378-0
  5. V. Zue and J. Glass, 'Conversational interfaces: Advances and challenges,' Proc. of the IEEE. vol. 88, no. 8, pp. 1166-1180, 2000 https://doi.org/10.1109/5.880078
  6. H. Meng, et aI., 'The use of belief networks for mixed-initiative dialog modeling,' IEEE Trans. Speech and Audio 'Processing, vol. 11, no. 6, pp. 757-773, 2003 https://doi.org/10.1109/TSA.2003.814380
  7. J. Allen, 'Mixed initiative interaction,' IEEE Intelligent Systems, vol. 15, no. 4, pp. 14-23, 1999 https://doi.org/10.1109/MIS.1999.10022
  8. E. Horvitz, 'Uncertainty, action, and interaction: In pursuit of mixed-initiative computing,' IEEE Intelligent Systems, vol. 14, no. 5, pp. 17-20, 1999
  9. H. Huttenrauch, et al., 'Involving users in the design of a mobile office robot,' IEEE Trans. Systems, Man, and Cybernetics- Part C: Applications and Reviews, vol. 34, no. 2, pp. 113-124, 2004 https://doi.org/10.1109/TSMCC.2004.826281
  10. F. Mizoghchi, et al., 'Smart office robot collaboration based on multi-agent programming,' Artificial Intelligence, vol. 114, no. 1-2, pp. 57-94, 1999 https://doi.org/10.1016/S0004-3702(99)00068-5
  11. M Skubic, et al., 'Spatial language for human-robot dialogs,' IEEE Trans. Systems, Man, and Cybernetics-Part C: Applications and Reviews, vol. 34, no. 2, pp. 154-167, 2004 https://doi.org/10.1109/TSMCC.2004.826273
  12. E. Horvitz and T. Pack, 'A computational architecture for conversation,' Proc. of the 7th Int. Conf. on User Modeling, pp. 201-210, 1999
  13. G. Ferguson, et al., 'TRAlNS-95: Towards a mixed-initiative planning assistant,' Proc. of the 3rd Int. Conf. on Artificial Intelligence Planning Systems, pp. 70-77, 1996
  14. S. Perugini, et al., 'Personalizing Web Sites with Mixed-Initiative Interaction,' IT Professional, vol. 5, no. 2, pp. 9-15, 2003 https://doi.org/10.1109/MITP.2003.1191787
  15. A. Onisko, et al., 'Comparison of rule-based and Bayesian network approaches in medical diagnostic Systems,' Proc. of the 8th Int. Conf. on Artificial Intelligence in Medicine, pp. 283-292, 2001
  16. W. W. Gibbs, 'Considerate Computing,' Scientific American, January, 2005
  17. J.-H. Hong and S.-B. Cho, 'A two-stage bayesian network for effective development of conversational agent,' Lecture Notes in Computer Science 2690, Springer, Berlin, pp. 1-9, 2003
  18. A. Ranganathan, et al., 'ConChat: A context- aware chat program,' IEEE Pervasive Computing, vol. 1, no. 3, pp. 51-57, 2002 https://doi.org/10.1109/MPRV.2002.1037722
  19. http://www.cyberbotics.com - Webots software