This paper presents two models of goal generation which enable a motivated autonomous agent to generate goals in response to changes in its underlying drives or motivations, while it is both planning and executing. A Mars rover domain is used to illustrate the two models: the first model involves goals being generated explicitly in response to changes to the agent's motivations where such goals are then provided to a planner, while the second model involves encoding the motivations and the goals that they may generate as part of the planner's domain model. Results from experiments on integrating the models with different planners suggest that while they may bring the benefits of autonomy that we seek, they also introduce more complexity into the planning problem.
[1]
Rob Sherwood,et al.
Casper: Space Exploration through Continuous Planning
,
2001,
IEEE Intell. Syst..
[2]
Z. Kunda,et al.
The case for motivated reasoning.
,
1990,
Psychological bulletin.
[3]
Christian Balkenius,et al.
The roots of motivation
,
1993
.
[4]
Michael Luck,et al.
A motivation-based planning and execution framework
,
2004,
Int. J. Artif. Intell. Tools.
[5]
Ivan Serina,et al.
MADbot: A Motivated and Goal Directed Robot
,
2005,
AAAI.
[6]
A. Maslow.
The Farther Reaches of Human Nature
,
1971
.
[7]
Jacques Ferber,et al.
Multi-agent systems - an introduction to distributed artificial intelligence
,
1999
.