基于PB递归神经网络的陪护机器人多模式交互控制方法  

A multimodal interactive control method based on recurrent neural network with parametric bias model for companion robots

作　　者：徐敏[1] 陶永[2] 魏洪兴[2] 

机构地区：[1]厦门理工学院电子与电气工程系,厦门361024 [2]北京航空航天大学机械工程及自动化学院,北京100191

出　　处：《高技术通讯》2011年第8期861-866,共6页Chinese High Technology Letters

基　　金：863计划（2008AA040201,2009AA043901）资助项目.

摘　　要：本文提出了一种基于PB递归神经网络（RNNPB）算法的陪护机器人多模式交互控制方法。首先，提出了一种包含多模式交互、交互识别与交互决策等智能体组成的陪护机器人多模式交互框架，然后，将基于PB的学习算法应用于陪护机器人的交互过程，形成了一种基于RNNPB模型的陪护机器人多模式交互控制方法，通过交互状态识别及决策判断结果进行交互输出，实现了陪护机器人交互过程中复杂任务的规划和交互的学习适应。实验验证了该交互控制方法的有效性。A muhimodal interactive control method based on the recurrent neural network with parametric bias （RNNPB） model was proposed for the companion robots. Firstly, a multimodal interaction framework, which was composed of the multimodal interaction agent, the interactive recognition agent and the interaction decision agent, was proposed, and then, a PB-based learning algorithm was applied to the interactive process of companion robots to form the multimodal interaction control method based on the RNNPB model. The RNNPB control method can be used to deal with the interactive sates recognition and decision analysis process and generate the patterns of behavior as the out- put of interaction process to realize the complex mission planning, studying and adapting of companion robots＇ interaction process. The experimental results showed the effectiveness of the control method.

关 键 词：陪护机器人 PB递归神经网络(RNNPB) 多模式交互 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]