Abstract:In the process of human-robot interaction, an engagement evaluation algorithm is proposed based on dynamic Bayesian network and domain expert knowledge, which focuses on solving the problem of insufficiency of training samples. Firstly, the social signals during the human-robot interaction and the reasoning process of dynamic Bayesian network are described, and the topology of the evaluation model of the engagement is developed. Then, limitations of the parameterization of the data-driven model are considered. Experts' opinions are collected by designing the linguistic variable set, and are processed by fuzzification and defuzzification. Thus, the construction of evaluation model is completed. Finally, the evaluation model is verified through the robot platform NAO and the design of interactive scenario. The experiment shows that the results of engagement evaluation are consistent with the actual behaviors of the interactive object, so that the robot can correctly identify the engagement intention of the interactive object in the process of human-robot interaction. Compared with the existing methods of engagement evaluation, the proposed method is not limited by training samples, and has high practical value and strong generalization ability.
[1] Lemaignan S, Garcia F, Jacq A, et al. From real-time attention assessment to “with-me-ness” in human-robot interaction[C]//ACM/IEEE International Conference on Human Robot Interaction. Piscataway, USA: IEEE, 2016: 157-164.
[2] Sidner C, Lee C, Kidds C, et al. Explorations in engagement for humans and robots[J]. Artificial Intelligence, 2005, 166(1/2): 140-164.
[3] Schrempf O C, Albrecht D, Hanebeck U D. Tractable probabilistic models for intention recognition based on expert knowledge[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2007: 1429-1434.
[4] Tahboub K A. Intelligent human-machine interaction based on dynamic Bayesian networks probabilistic intention recognition[J]. Journal of Intelligent and Robotic Systems, 2006, 45(1): 31-52.
[5] Krauthausen P, Hanebeck U D. Situation-specific intention recognition for human-robot cooperation[J]. Journal of the European Optical Society Rapid Publications, 2010, 10(6): 3479-3486.
[6] Anzalone S M, Boucenna S, Ivaldi S, et al. Evaluating the engagement with social robots[J]. International Journal of Social Robotics, 2015, 7(4): 75-82.
[7] Koo S, Kwon D S. Recognizing human intentional actions from the relative movements between human and robot[C]//18th International Symposium on Robot and Human Interactive Communication. Piscataway, USA: IEEE, 2009: 939-944.
[8] Feil-Seifer D, MataricMJ. Distance-based computational models for facilitating robot interaction with children[J]. Journal of Human-Robot Interaction, 2012, 1(1): 55-77.
[9] Ooko R, Ishii R, Nakano Y I. Estimating a user's conversational engagement based on head pose information[C]//International Conference on Intelligent Virtual Agents. Berlin, Germany: Springer-Verlag, 2011: 262-268.
[10] 马琼雄.基于视觉的服务机器人人机交互技术研究[D]. 广州:华南理工大学,2014. Ma Q X. Study of human-robot interaction technology based on vision[D]. Guangzhou: South China University of Technology, 2014.
[11] Vaufreydaz D, Johal W, Combe C. Starting engagement detection towards a companion robot using multimodal features[J]. Robotics & Autonomous Systems, 2015, 75(suppl.): 4-16.
[12] Ivaldi S, Lefort S, Peters J, et al. Towards engagement models that consider individual factors in HRI: On the relation of extroversion and negative attitude towards robots to gaze and speech during a human-robot assembly task[J]. International Journal of Social Robotics, 2017, 9: 63-86.
[13] Uusitalo L. Advantages and challenges of Bayesian networks in environmental modelling[J]. Ecological Modelling, 2007, 203(3): 312-318.
[14] 罗素,诺维格.人工智能:一种现代的方法[M].殷建平, 等,译.3 版.北京:清华大学出版社,2013:471-479. Russell S J, Norvig P. Artificial intelligence: A modern approach[M]. Yin J P, et al. Trans. 3rd Ed. Beijing: Tsinghua University Press, 2013: 471-479.
[15] Zhang G, Thai V V. Expert elicitation and Bayesian network modeling for shipping accidents: A literature review[J]. Safety Science, 2016, 87: 53-62.
[16] Ren J,Wang J, Jenkinson I, et al. A Bayesian network approach for offshore risk analysis through linguistic variables[J]. China Ocean Engineering, 2007, 21(3): 371-388.
[17] Hsu H M, Chen C T. Aggregation of fuzzy opinions under group decision making[J]. Fuzzy Sets & Systems, 1996, 79(3): 279-285.
[18] Liou T S, Wang M J J. Ranking fuzzy numbers with integral value[J]. Fuzzy Sets & Systems, 1992, 50(3): 247-255.
[19] Hall E T. Proxemics[J]. Current Anthropology, 1968, 9(2/3): 83-108.