A blackboard architecture for control
Artificial Intelligence
Planning for conjunctive goals
Artificial Intelligence
SOAR: an architecture for general intelligence
Artificial Intelligence
Practical planning: extending the classical AI planning paradigm
Practical planning: extending the classical AI planning paradigm
Explaining and repairing plans that fail
Artificial Intelligence
Proceedings of the first international conference on Principles of knowledge representation and reasoning
Handbook of theoretical computer science (vol. A)
Declarative goals in reactive plans
Proceedings of the first international conference on Artificial intelligence planning systems
Building symbolic primitives with continuous control routines
Proceedings of the first international conference on Artificial intelligence planning systems
Deductive planning and plan reuse in a command language environment
ECAI '92 Proceedings of the 10th European conference on Artificial intelligence
Beyond the single planning paradigm: introspective planning
ECAI '92 Proceedings of the 10th European conference on Artificial intelligence
A multivalued logic approach to integrating planning and control
Artificial Intelligence - Special volume on planning and scheduling
Hi-index | 0.00 |
This work is focused on an architecture for {\it systems\ which\ act\ inside\ an\ unpredictable\ world}({\it embedded\ systems}).Several systems dealing with the above issue have been proposed sofar. We classify them by means of their architectures andalgorithms, obtaining, for example, classical, deferred and reactive planning.From the systems developed up to now, we can point out someof the features that embedded systems must have.Namely, each system must have a {\it flexible\ architecture}, so it can deal with different problems.Each system must allow {\it different\ basic\ activities},i.e., actuators and sensors controlling, plan formation andexecution, and so on.Each system must have a flexible {\it failure\ handling\ mechanism},since no action is guaranteed to succeed.In this paper, we propose a system called {\tt MRG}which addresses the above features.Its architecture has several modules which can be combined indifferent ways depending on the problem.A module performs a basic activity.The system is able to detect and to react to failures.The architecture allows {\tt MRG} a parallel activation of modules and a quick reaction to external events.The control of the architecture is reached by means of a planning language which has a small set of powerful control structures. {\tt MRG} has been experimented in a complexlarge-scale application.