摘要
建立了一个包含多个捕猎机器人和单个猎物机器人的动态空间模型,并构建了捕猎机器人的AIAE-ANN行为决策系统。人工神经网络(ANN)所有的连接权值采用改进型人工免疫算法(AIAE)进行优化,使神经网络的性能不断得到进化,最终可生成一个性能优良的行为决策系统,从而完成捕猎机器人的围捕。仿真实验表明:用AIAE训练,能有效地应用于追捕系统的多移动机器人研究。
A dynamic environment with some predator robots and one prey and the artificial immune algorithm with elitism and artificial neural network （AIAE-ANN） behavior decision-making system are constructed. The AIAE is used to optimize the connection weight values of this neural network, which made the performance of the neural network to be evolved continuously and finally a behavior decision-making system with good performance can be obtained and the predator robots encircled the prey. Simulation experiments show the feasibility and validity of the given algorithm in the research of the multi-robot system in the pursuit game.
出处
《传感器与微系统》
CSCD
北大核心
2007年第8期16-19,共4页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(50275150)
高等学校博士学科点专项科研基金资助项目(20040533035)
关键词
多机器人系统
人工免疫算法
人工神经网络
追捕
multi-robot system
artificial immune algorithm with elitism （AIAE）
artificial neural network （ ANN ）
pursuit
