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, intimate interface which supports interactions on a scale from direct manipulation to delegation, depending on the user's choice. Another feature of this interface is its two modes of interaction: direct device interaction (mouse clicking) and interpretive, command line or scripting mode. This way, agents can be \forced" to perform certain activities via mouse clicks (direct control), or they can be programmed via scripts on the y. We present examples of the use of the AHA interface from the domain of animating humanlike agents in a virtual world.
[1]
Rodney A. Brooks,et al.
A Robust Layered Control Syste For A Mobile Robot
,
2022
.
[2]
D. Norman.
The psychology of everyday things", Basic Books Inc
,
1988
.
[3]
Innes A. Ferguson.
TouringMachines: an architecture for dynamic, rational, mobile agents
,
1992
.
[4]
Jörg P. Müller,et al.
Modelling Reactive Behaviour in Vertically Layered Agent Architectures
,
1995,
ECAI Workshop on Agent Theories, Architectures, and Languages.
[5]
David P. Miller,et al.
Experiences with an architecture for intelligent, reactive agents
,
1995,
J. Exp. Theor. Artif. Intell..
[6]
Bruce Blumberg,et al.
Multi-level direction of autonomous creatures for real-time virtual environments
,
1995,
SIGGRAPH.
[7]
Thomas W. Calvert,et al.
Knowledge-Driven, Interactive Animation of Human Running
,
1996,
Graphics Interface.