[1]阮晓钢,庞涛,张晓平,等.一种基于情感智能的机器人自主趋光行为研究[J].智能系统学报,2015,10(1):97-102.[doi:10.3969/j.issn.1673-4785.201312035]
RUAN Xiaogang,PANG Tao,ZHANG Xiaoping,et al.Research on the autonomous phototaxis behavior of a robot based on emotion intelligence[J].CAAI Transactions on Intelligent Systems,2015,10(1):97-102.[doi:10.3969/j.issn.1673-4785.201312035]
点击复制
RUAN Xiaogang,PANG Tao,ZHANG Xiaoping,et al.Research on the autonomous phototaxis behavior of a robot based on emotion intelligence[J].CAAI Transactions on Intelligent Systems,2015,10(1):97-102.[doi:10.3969/j.issn.1673-4785.201312035]
一种基于情感智能的机器人自主趋光行为研究
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
10
期数:
2015年第1期
页码:
97-102
栏目:
学术论文—智能系统
出版日期:
2015-03-25
- Title:
- Research on the autonomous phototaxis behavior of a robot based on emotion intelligence
- Keywords:
- cognitive robotics; intrinsic motivation; mobile robot; phototaxis skill; emotion intelligence; sensorimotor system; fuzzy reasoning method; orientation
- 分类号:
- TP242.6
- 文献标志码:
- A
- 摘要:
- 针对移动机器人的自主趋光行为问题,提出了一种基于情感智能的内发动机仿生学习机制。该学习机制以生物体感觉运动系统的学习机制为基础,包括评价环节、行为选择环节和取向环节,采用模糊神经网络构建情感模型,情感模型的输出作为评价环节的内部奖赏信号。该学习机制能够使机器人在未知环境下通过自主的学习和训练逐渐形成、发展和完善趋光行为技能,通过情感智能的作用可以增加试探成功次数和减小学习步数,仿真实验证明了该方法的有效性。
- Abstract:
- In this paper, a kind of bionic learning mechanism of intrinsic motivation on the basis of emotion intelligence is proposed for the autonomous phototaxis behavior of a mobile robot. The learning mechanism is on the basis of the learning mechanism of the sensorimotor system of a living body, including the links of evaluation, behavioral choices and orientation. The emotion model is constructed by the fuzzy neural network and the output of emotion model is taken as the internal reward signal of the evaluation link. The learning mechanism may make a robot gradually form, develop and perfect the phototaxis skills by autonomous learning and training in an unknown environment. The emotion intelligence may increase the number of exploratory successes and reduce the learning steps. The simulation results demonstrated the effectiveness of this method.
- 参考文献/References:
-
[1] OUDEYER P, KAPLAN F. What is intrinsic motivation? a typology of computational approaches[J]. Frontiers in Neurorobotics, 2007, 1(6): 1-14.
[2] SINGH S. Intrinsically motivated reinforcement learning: an evolutionary perspective[J]. IEEE Transactions on Autonomous Mental Development, 2010, 2(2): 70-82.
[3] AHN H, PICARD R W. Affective cognitive learning and decision making: the role of emotions[C]//The 18th European Meeting on Cybernetics and Systems Research. [s.l.], 2006: 1-6.
[4] MALFAZ M, SALICHS M A. Learning to avoid risky actions[J]. Cybernetics and Systems, 2011, 42(8): 636-658.
[5] SEQUEIRA P, MELO F S, PAIVA A. Emotion-based intrinsic motivation for reinforcement learning agents[C]//Affective Computing and Intelligent Interaction. Berlin: Springer, 2011: 326-336.
[6] ABDI J, MOSHIRI B, ABDULHAI B, et al. Short-term traffic flow forecasting: parametric and nonparametric approaches via emotional temporal difference learning[J]. Neural Computing and Applications, 2013,23:141-159.
[7] 刘明, 许力. 人工情感在Agent行为选择策略中的应用[J]. 江南大学学报, 2003, 2(6):564-568.LIU Ming, XU Li. Study on artificial emotion and its application in the behavior selection strategy of agents[J]. Journal of Southern Yangtze University, 2003,2(6): 564-568.
[8] 张惠娣,刘士荣. 基于情感与环境认知的移动机器人自主导航控制[J]. 控制理论与应用, 2008, 25(6): 995-1000.ZHANG Huidi, LIU Shirong. Autonomous navigation control for mobile robots based on emotion and environment cognition[J]. Control Theory & Applications, 2008, 25(6): 995-1000.
[9] 胡云斗,胡丹丹,高庆吉. 一种基于任务的机器人情感决策模型的构建[J]. 机器人, 2010, 32(4):464-477.HU Yundou, HU Dandan, GAO Qingji. Construction of a robot emotion decision-making model based on tasks[J]. Robot, 2010, 32(4):464-477.
[10] 祝宇虹,毛俊鑫. 基于人工情感与Q学习的机器人行为决策[J]. 智能工程, 2008, 61(7): 61-65.ZHU Yuhong, MAO Junxin. Robot’s behavioral decision-making strategy based on artificial emotion and Q-learning[J]. Intelligent Engineering, 2008, 61(7): 61-65.
[11] ASADA M, UCHIBE E, HOSODA K. Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development[J]. Artificial Intelligence, 1999, 110(2): 275-292.
[12] HUMBERT J S, HYSLOP A M. Bioinspired visuomotor convergence[J]. IEEE Transactions on Robotics, 2010, 26: 121-30.
[13] ZOLLO L, ESKIZMIRLILER S, TETI G, et al. An anthropomorphic robotic platform for progressive and adaptive sensorimotor learning[J]. Advanced Robotics, 2008, 22: 91-118.
[14] BARANES A, OUDEYER P Y. Active learning of inverse models with intrinsically motivated goal exploration in robots[J]. Robotics and Autonomous Systems, 2013, 61(1): 49-73.
[15] VIGORITO C M, BARTO A G. Intrinsically motivated hierarchical skill learning in structured environments[J]. IEEE Transactions on Autonomous Mental Development, 2010, 2(2): 132-143.
[16] EI-NASR M S, YEN J. Agents, emotion intelligence and fuzzy logic[C]//Proceedings of the North American Conference on the Fuzzy Information Processing Society. Pensacola Beach, 1998,1:135-140.
[17] DEGAONKAR V N, APTE S D. Emotion modeling from speech signal based on wavelet packet transform[J]. International Journal of Speech Technology, 2013, 16(1): 1-5.
[18] ORTONY A. The cognitive structure of emotions[M]. Cambridge:Cambridge University Press, 1990:35-77.
[19] OUDEYER P Y, KAPLAN F, HAFNER V V. Intrinsic motivation systems for autonomous mental development[J]. IEEE Transactions on Evolutionary Computation, 2007, 11(2): 265-286.
[20] ZORAN M, MARKO M, MIHAILO L, et al. Neural network reinforcement learning for visual control of robot manipulators[J]. Expert Systems with Applications, 2013, 40(5): 1721-1736.
备注/Memo
收稿日期:2013-12-22;改回日期:。
基金项目:国家973计划资助项目(2012CB720000);国家自然科学基金资助项目(61375086;61101161);北京市自然科学基金资助项目/北京市教育委员会科技计划重点资助项目(KZ201210005001).
作者简介:阮晓钢,男,1958年生,博士生导师,主要研究方向为机器人学、自动控制与人工智能技术。先后主持和承担国家自然科学基金重点项目、国家973计划重点项目以及省部级项目30余项,发表学术论文200余篇;庞涛,女,1976年生,讲师,主要研究方向为认知机器人学;张晓平,女,1991年生,博士研究生,主要研究方向为机器人学、人工智能技术。
通讯作者:庞涛.E-mail:pangtao163@126.com.
更新日期/Last Update:
2015-06-16