Integrating reactive and scripted behaviors in a life-like presentation agent
Integrating reactive and scripted behaviors in a life-like presentation agent
复制标题
将反应式和脚本化行为集成到逼真的演示代理中
DOI：
10.1145/280765.280842
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
Jochen Müller
中科院分区：
文献类型：
--
作者：
E. André;T. Rist;Jochen Müller
1.基于真实的视频、卡通风格的绘图甚至基于模型的3D图形的动画代理为基于计算机的演示提供了巨大的希望，因为它们使演示更加生动和吸引人，并且允许从人与人的交流中已知的对话风格的仿真。在本文中，我们描述了一个生活般的接口代理，它提供多媒体材料给用户以下的指令的脚本。呈现主体的整体行为部分地由这样的脚本决定，部分地由主体的自我行为决定。在我们的方法中，代理的行为被定义在一个声明性的规范语言，行为规范被用来自动生成一个控制模块的代理显示系统。论文的第一部分描述了生成过程，其中包括人工智能规划和两步编译。由于手动创建的演示文稿脚本是繁琐和容易出错的，我们还解决了自动生成的演示文稿脚本，可以转发到接口代理。本文的第二部分提出了一种结合层次规划和时序推理的多媒体演示设计方法。
1. ABSTRACT Animated agents - based either on real video, cartoon-style drawings or even model-based 3D graphics - offer great promise for computer-based presentations as they make presentations more lively and appealing and allow for the emulation of conversation styles known from human-human communication. In this paper, we describe a life-like interface agent which presents multimedia material to the user following the directives of a script. The overall behavior of the presentation agent is partly determined by such a script, and partly by the agent’s self-behavior. In our approach, the agent’s behavior is deiined in a declarative specification language, Behavior specifications are used to automatically generate a control module for an agent display system. The first part of the paper describes the generation processw hich involves AI planning and a two-step compilation. Since the manual creation of presentation scripts is tedious and error-prone, we also address the automated generation of presentation scripts which may be forwarded to the interface agent. The second part of the paper presents an approach for multimedia presentation design which combines hierarchical pIanning with temporal reasoning.