基于人工情感与CMAC网络的机器人行为学习  

Robot's Behavioral Learning Based on Artificial Emotion and CMAC Network

作　　者：祝宇虹[1] 魏金海[1] 

机构地区：[1]哈尔滨工业大学机电工程学院机器人技术与系统国家重点实验室,黑龙江哈尔滨150001

出　　处：《机械与电子》2012年第9期72-76,共5页Machinery & Electronics

摘　　要：人工情感是一个新兴的研究方向,情感智能是人工智能对人类智能的重要逼近。该文利用模糊情感模型来指导机器人学习,在CMAC网络框架内实现机器人的新的行为学习方式。仿真实验结果表明基于人工情感与CMAC网络的机器人行为学习能够学习到一条好的行为策略,具有良好的学习性能。该方法对于提高机器人在恶劣环境下的生存能力和自主决策能力具有很大理论意义和实际应用价值。Artificial emotion is a new and developing research area,affective intelligence is an important approach to human intelligence. This paper uses a fuzzy artificial emotion model which is used for guiding robot behavior scheme learning and it is to realize a new behavior schem learning method in the frame of CMAC network. The result of simulation tells that the robot behavior scheme learning based on artificial emotion and CMAC network can generate a sheme good enough and the learning is of good performance. This method has great theoretical significance and high application value for enhancing robot＇s survivability and autonomous decisionmaking capacity in harsh and complex environment.

关 键 词：人工情感 CMAC网络 机器学习 

分 类 号：TP273.22[自动化与计算机技术—检测技术与自动化装置]