1997 Papers

Though Strong AI is simply silly, Weak AI—the attempt to engineer systems which at least appear to be have minds—by my lights, is a thing of beauty. The storytelling agent BRUTUS, intended to simulate human literary creativity (and to teach us quite a bit about the nature of human creativity), marks my own latest contribution. Read more

In this paper, we introduce a conversational agent which is applied to the food-ordering dialog system. It uses VenusDictate as speech recognition front-end, then understands the semantics of the input sentence by extracting the keywords of the sentence, finally it interacts with the user by speech. The experimental results show that the performance of this agent is good in this application domain. Read more

Asynchronous, Hierarchical Agents (AHAs) provide a vertically structured multilevel abstraction hierarchy. In this paper, we argue that this multilevel hierarchy is a convenient way to create a human-agent interface at multiple levels of abstraction. In this way, the agent has several layers of specication (input) and visualization (output) which facilitates users with problem solving, because such an interface parallels the hierarchical and iterative nature of human creative thought processes. The AHA interface presents an intuitive,... Read more

As this paper illustrates, a lot of work is being directed at the development of agents. Researchers are exploring ways to make agents smarter, to allow them to learn by observing us, to make them appear more lifelike. However, relatively little work is being focused on how people might actually experience agents, and on how agents might be designed so that we feel comfortable with them. Read more

Since the beginning of recorded history, people have been fascinated with the idea of non-human agencies. Popular notions about androids, humanoids, robots, cyborgs, and science fiction creatures permeate our culture, forming the unconscious backdrop against which software agents are perceived. The word “robot,” derived from the Czech word for drudgery, became popular following Karel Capek’s 1921 play RUR: Rossum Universal Robots. While Capek’s robots were factory workers, the public has also at times embraced the... Read more

We are studying how to create believable agents that perform actions and use natural language in interactive, animated, real-time worlds. Believable agents are autonomous agents that have specific, rich personalities like characters in movies and animation. We have extended Hap, the behavior-based architecture used by the Oz group to construct non-linguistic believable agents, to support natural language text generation. These extensions allow us to tightly integrate text generationwith other aspects of the agent, including action, perception,... Read more

Animated pedagogical agents that inhabit interactive learning environments can exhibit strikingly lifelike behaviors. In addition to providing problem-solving advice in response to students’ activities in the learning environment, these agents may also be able to play a powerful motivational role. To design the most effective agent-based learning environment software, it is essential to understand how students perceive an animated pedagogical agent with regard to affective dimensions such as encouragement, utility, credibility, and clarity. This paper... Read more

The Olga project has developed an animated agent interface for information services. The interface combines a graphical interface, spoken dialogue and an animated 3D ‘human-like’ character for multimodal interaction with users. The interaction is intelligently managed using techniques derived from spoken dialogue but extended for the graphical modality. The Olga agent is innovative in combining an interactive spoken dialogue system with a 3-D animated character using lip-synchronized synthetic speech and gesturing. Particular attention has been... Read more