【24h】

Dynamic behaviour conception for EmI companion robot

机译:EmI伴侣机器人的动态行为概念

获取原文

摘要

This article presents research work done in the domain of nonverbal emotional interaction for the EmotiRob project. It is a component of the MAPH project, the objective of which is to give comfort to vulnerable children and/or those undergoing long-term hospitalisation through the help of an emotional robot companion. It is important to note that we are not trying to reproduce human emotion and behavior, but trying to make a robot emotionally expressive. The studies carried out on perception and emotional synthesis have allowed us to develop our emotional model of interaction: iGrace. iGrace actually allow a system display emotions as a static mode. This mode has ever been evaluated with our avatar: ArtE, we developped in Flash. The rate of satisfaction (86%) of the evaluation allowed us embeded static mode on our robotics platform: EmI - Emotional Model of Interaction. Now, we want add dynamics on EmI robot and add lifelike in its reactions. This paper will present different hypothesis we used for iGrace emotional model, algorithm for behaviour dynamic , evaluation for static and dynamic mode, and EmI robotics conception. We begin the article by MAPH and EmotiRob project presentation. Then, we quickly describe the computational model of emotional experience iGrace that we have created, the integration of dynamics and iGrace evaluation. We conclude with a description of the architecture of Emi, as well as improvements to be made to its next generation.
机译:本文介绍了EmotiRob项目在非语言情感互动领域中所做的研究工作。它是MAPH项目的一个组成部分,其目的是在情感机器人的帮助下为弱势儿童和/或长期住院的儿童提供安慰。重要的是要注意,我们并不是要重现人类的情感和行为,而是要使机器人具有情感表达能力。关于感知和情绪综合的研究使我们能够开发出互动的情绪模型:iGrace。 iGrace实际上允许系统将情绪显示为静态模式。此模式曾被我们的头像评估过:ArtE,我们在Flash中开发。评估的满意率(86%)使我们能够在我们的机器人平台上嵌入静态模式:EmI-交互情感模型。现在,我们要在EmI机器人上添加动态特性,并在其反应中添加逼真的外观。本文将介绍我们用于iGrace情感模型,行为动态算法,静态和动态模式评估以及EmI机器人概念的不同假设。我们从MAPH和EmotiRob项目演示开始本文。然后,我们快速描述我们创建的情感体验iGrace的计算模型,动力学和iGrace评估的集成。最后,我们对Emi的体系结构进行了描述,并对其下一代产品进行了改进。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号