[1]李敏嘉,解仑,王志良,等.基于生理信号感知的个性化复合情绪机器人[J].东南大学学报(自然科学版),2019,49(2):225-230.[doi:10.3969/j.issn.1001-0505.2019.02.004]
 Li Minjia,Xie Lun,Wang Zhiliang,et al.Personalized complex emotion robot based on physiological signal perception[J].Journal of Southeast University (Natural Science Edition),2019,49(2):225-230.[doi:10.3969/j.issn.1001-0505.2019.02.004]
点击复制

基于生理信号感知的个性化复合情绪机器人()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
49
期数:
2019年第2期
页码:
225-230
栏目:
自动化
出版日期:
2019-03-20

文章信息/Info

Title:
Personalized complex emotion robot based on physiological signal perception
作者:
李敏嘉1解仑1王志良1任福继2
1北京科技大学计算机与通信学院, 北京 100083; 2 合肥工业大学计算机学院, 合肥 230009
Author(s):
Li Minjia1 Xie Lun1 Wang Zhiliang1 Ren Fuji2
1School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
2College of Computer Science, Hefei University of Technology, Hefei 230009, China
关键词:
情感交互 机器人 支持向量机 感知 个性化
Keywords:
emotional interaction robot support vector machine perception personalization
分类号:
TP242.2
DOI:
10.3969/j.issn.1001-0505.2019.02.004
摘要:
为了解决人机情感交互中机器人从感知外界刺激到情绪行为产生过程中的个性化问题,建立了一种基于生理信号感知的个性化复合情绪机器人系统.首先,利用情感空间切比雪夫距离与支持向量机,获取受试者实时的生理情绪状态,作为机器人感知信息的输入;然后,利用二阶阻尼系统生成感知强度;最后,基于大五人格量表实现个性化情绪输出.结果表明,中性激励下正向人格与负向人格的复合情绪出现个性化差异,其中正向人格的快乐情绪维持在高强度0.9附近,负向人格相反.具有正向人格设置的交互机器人输出的平静与快乐行为所占时间百分数分别为54.75%与45.25%.因此,机器人能够根据该系统生成具有不同人格因素的情绪走向,并做出相应的行为决策.
Abstract:
To solve the problem of personalization for robots from the perception of external stimuli to the generation of emotional behavior in human-computer emotional interaction, a personalized complex emotional robotic system based on physiological signal perception is provided. First, by using the Chebyshev distance in the emotional space and the support vector machine, the real-time physiological emotional state of the subject is obtained as the input of the robot’s perception information. Then, a second-order damping system is used to realize the generation of the perceived intensity. Finally, a big five personality scale is used to achieve personalized emotional output. The results show that there is a personalized difference on the complex emotion between the positive personality and the negative personality under neutral stimuli, in which the happy emotion of the positive personality maintains near high intensity 0.9 and the negative personality is opposite. The ratios of the time of calm behavior and happy behavior of the interactive robot with positive personality settings are 54.75% and 45.25%, respectively. Therefore, according to this system, the robot can generate emotional trends with different personality factors and make corresponding behavior decisions.

参考文献/References:

[1] Picard R W. Affective computing:Challenges[J]. International Journal of Human-Computer Studies, 2003, 59(1/2): 55-64. DOI:10.1016/S1071-5819(03)00052-1.
[2] 秦超龙, 宋爱国, 吴常铖, 等. 基于Unity3D与Kinect的康复训练机器人情景交互系统[J]. 仪器仪表学报, 2017, 38(3):530-536. DOI:10.3969/j.issn.0254-3087.2017.03.003.
Qin C L, Song A G, Wu C C, et al. Scenario interaction system of rehabilitation training robot based on Unity3D and Kinect[J]. Chinese Journal of Scientific Instrument, 2017, 38(3):530-536. DOI:10.3969/j.issn.0254-3087.2017.03.003. (in Chinese)
[3] Gibson J J. The senses considered as perceptual systems[M]. Westport, C T, USA: Green Wood Press 1983:335.
[4] 徐上谋, 解仑, 韩晶, 等. 基于情感状态转移模型的外界刺激影响分析[J]. 工程科学学报, 2015, 37(11):1528-1534. DOI:10.13374/j.issn2095-9389.2015.11.020.
Xu S M, Xie L, Han J, et al. Impact analysis of external stimuli based on the emotional state transfer model[J]. Chinese Journal of Engineering, 2015, 37(11):1528-1534. DOI:10.13374/j.issn2095-9389.2015.11.020. (in Chinese)
[5] Belkaid M, Cuperlier N, Gaussier P. Emotional modulation of peripersonal space as a way to represent reachable and comfort areas[C]//2015 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS). Hamburg, Germany, 2015: 353-359. DOI:10.1109/IROS.2015.7353397.
[6] Ramirez-Amaro K, Beetz M, Cheng G. Understanding the intention of human activities through semantic perception: Observation, understanding and execution on a humanoid robot[J]. Advanced Robotics, 2015, 29(5): 345-362. DOI:10.1080/01691864.2014.1003096.
[7] Chao L, Tao J, Yang M, et al. Audio visual emotion recognition with temporal alignment and perception attention [EB/OL].(2016-03-08)[2018-05-01]. https://sci-hub.tw/https://arxiv.org/abs/1603.08321.
[8] Sherman R A,Rauthmann J F, Brown N A, et al. The independent effects of personality and situations on real-time expressions of behavior and emotion[J]. Journal of Personality and Social Psychology, 2015, 109(5): 872-888. DOI:10.1037/pspp0000036.
[9] 路飞, 田国会, 李擎. 智能空间环境下基于本体的机器人服务自主认知及规划[J]. 机器人, 2017, 39(4):423-430. DOI:10.13973/j.cnki.robot.2017.0423.
Lu F, Tian G H, Li Q. Autonomous cognition and planning of robot service based on ontology in intelligent space environment[J]. Robot, 2017, 39(4):423-430. DOI:10.13973/j.cnki.robot.2017.0423. (in Chinese)
[10] Sharma B,Jenkin Suji R, Basu A. Adaptive kalman filter approach and butterworth filter technique for ECG signal enhancement[M]//Sharma B, Jenkin S R, Basu A. Information and communication technology for sustainable development. Singapore: Springer Singapore, 2017: 315-322. DOI:10.1007/978-981-10-3920-1_32.
[11] Grundlehner B, Brown L, Penders J, et al. The design and analysis of a real-time, continuous arousal monitor[C]//2009 Sixth International Workshop on Wearable and Implantable Body Sensor Networks. Berkeley, CA, USA, 2009: 156-161. DOI:10.1109/BSN.2009.21.
[12] Koelstra S, Muhl C, Soleymani M, et al. DEAP: A database for emotion analysis using physiological signals[J]. IEEE Transactions on Affective Computing, 2012, 3(1): 18-31. DOI:10.1109/t-affc.2011.15.
[13] Landowska A. Towards new mappings between emotion representation models[J]. Applied Sciences, 2018, 8(2): 274. DOI:10.3390/app8020274.
[14] Masuyama N, Loo C K, Seera M. Personality affected robotic emotional model with associative memory for human-robot interaction[J]. Neurocomputing, 2018, 272: 213-225. DOI:10.1016/j.neucom.2017.06.069.
[15] Kaplan S, Prato C G. “Them or Us”: Perceptions, cognitions, emotions, and overt behavior associated with cyclists and motorists sharing the road[J]. International Journal of Sustainable Transportation, 2016, 10(3): 193-200. DOI:10.1080/15568318.2014.885621.
[16] Chumkamon S, Hayashi E, Koike M. Intelligent emotion and behavior based on topological consciousness and adaptive resonance theory in a companion robot[J]. Biologically Inspired Cognitive Architectures, 2016, 18: 51-67. DOI:10.1016/j.bica.2016.09.004.
[17] Masuyama N, Islam M N, Seera M, et al. Application of emotion affected associative memory based on mood congruency effects for a humanoid[J]. Neural Computing and Applications, 2017, 28(4): 737-752. DOI:10.1007/s00521-015-2102-x.
[18] Montague P, Dayan P,Sejnowski T. A framework for mesencephalic dopamine systems based on predictive Hebbian learning[J]. The Journal of Neuroscience, 1996, 16(5): 1936-1947. DOI:10.1523/jneurosci.16-05-01936.1996
[19] Ekman P. An argument for basic emotions[J]. Cognition and Emotion, 1992, 6(3/4): 169-200. DOI:10.1080/02699939208411068.
[20] McCrae R R, John O P. An introduction to the five-factor model and its applications[J]. Journal of Personality, 1992, 60(2): 175-215. DOI:10.1111/j.1467-6494.1992.tb00970.x.
[21] Goldberg L R. The development of markers for the Big-Five factor structure.[J]. Psychological Assessment, 1992, 4(1): 26-42. DOI:10.1037//1040-3590.4.1.26.
[22] Hu X, Xie L, Liu X, et al. Emotion expression of robot with personality[J]. Mathematical Problems in Engineering, 2013, 2013: 1-10. DOI:10.1155/2013/132735.
[23] Tapus A, Mataric M J. Socially assistive robots: The link between personality, empathy, physiological signals, and task performance[C]//AAAI Spring Symposium: Emotion, Personality, and Social Behavior. Stanford, California, USA, 2008: 133-140.

相似文献/References:

[1]郭晓波,宋爱国,翟雁.基于变参数的远程康复训练机器人神经网络控制[J].东南大学学报(自然科学版),2008,38(1):54.[doi:10.3969/j.issn.1001-0505.2008.01.011]
 Guo Xiaobo,Song Aiguo,Zhai Yan.Neural network control of tele-rehabilitation robot based on variable parameter[J].Journal of Southeast University (Natural Science Edition),2008,38(2):54.[doi:10.3969/j.issn.1001-0505.2008.01.011]
[2]朱兴龙,周骥平,罗翔,等.一种新型三自由度液压伺服关节的动力学模型[J].东南大学学报(自然科学版),2004,34(1):32.[doi:10.3969/j.issn.1001-0505.2004.01.008]
 Zhu Xinglong,Zhou Jiping,Luo Xiang,et al.Dynamic modeling of a novel hydraulic servo with three degrees of freedom joint[J].Journal of Southeast University (Natural Science Edition),2004,34(2):32.[doi:10.3969/j.issn.1001-0505.2004.01.008]
[3]陈俊杰,黄惟一,宋爱国,等.机器人系统中环境动力学模型及其参数辨识[J].东南大学学报(自然科学版),2002,32(1):64.[doi:10.3969/j.issn.1001-0505.2002.01.015]
 Chen Junjie,Huang Weiyi,Song Aiguo,et al.Dynamic model of environment and its parameters identification in robot systems[J].Journal of Southeast University (Natural Science Edition),2002,32(2):64.[doi:10.3969/j.issn.1001-0505.2002.01.015]
[4]谈士力,万德钧,龚振邦.真空气吸附壁面行走机器人动态路径规划[J].东南大学学报(自然科学版),1996,26(5):88.[doi:10.3969/j.issn.1001-0505.1996.05.017]
 Tan Shili,Wan Dejun,Gong Zhenbang,et al.Dynamic Path Planning of Mobile Robot Capable of Moving on the Vertical Wall Surface by Vacuum Adhering[J].Journal of Southeast University (Natural Science Edition),1996,26(2):88.[doi:10.3969/j.issn.1001-0505.1996.05.017]

备注/Memo

备注/Memo:
收稿日期: 2018-09-28.
作者简介: 李敏嘉(1992—),女,博士生; 解仑(联系人),男,博士,教授,博士生导师,xielun@ustb.edu.cn.
基金项目: 国家重点研发计划重点专项课题资助项目(2017YFB1002804)、国家自然科学基金资助项目(61432004,61672093).
引用本文: 李敏嘉,解仑,王志良,等.基于生理信号感知的个性化复合情绪机器人[J].东南大学学报(自然科学版),2019,49(2):225-230. DOI:10.3969/j.issn.1001-0505.2019.02.004.
更新日期/Last Update: 2019-03-20