Papers

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

The advent of software agents gave rise to much discussion of just what such an agent is, and of how they differ from programs in general. Here we propose a formal definition of an autonomous agent which clearly distinguishes a software agent from just any program. We also offer the beginnings of a natural kinds taxonomy of autonomous agents, and discuss possibilities for further classification. Finally, we discuss subagents and multiagent systems. Read more

In this paper King and Ohya explored people’s reactions to human and nonhuman visual forms of embodied agents. They asked participants to rate 20 different visual forms of agents ranging from simple geometric shapes to wire frames of humans to detailed 2D and 3D human forms. Read more

It is still an open question whether software agents should be personified in the interface. In order to study the effects of faces and facial expressions in the interface, a series of experiments was conducted to compare subjects’ responses to and evaluation of different faces and facial expressions. The experimental results obtained demonstrate that: 1) personified interfaces help users engage in a task, and are well suited for an entertainment domain; 2) people’s impressions of a face... Read more

Agent software is a rapidly developing area of research. However, the overuse of the word ‘agent’ has tended to mask the fact that, in reality, there is a truly heterogeneous body of research being carried out under this banner. This overview paper presents a typology of agents. Next, it places agents in context, defines them and then goes on, inter alia, to overview critically the rationales, hypotheses, goals, challenges and state-of-the-art demonstrators of the various agent... Read more