Cognitive systems engineering: new wine in new bottles
International Journal of Man-Machine Studies
Planning english referring expressions
Artificial Intelligence - Lecture notes in computer science 178
Intelligent interfaces: user models and planners
CHI '86 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Planning for conjunctive goals
Artificial Intelligence
Plans and situated actions: the problem of human-machine communication
Plans and situated actions: the problem of human-machine communication
The berkeley UNIX consultant project
Computational Linguistics
Automatically abstracting the effects of operators
Proceedings of the first international conference on Artificial intelligence planning systems
Participating in explanatory dialogues: interpreting and responding to questions in context
Participating in explanatory dialogues: interpreting and responding to questions in context
Situated plan attribution for intelligent tutoring
AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Using abstraction and nondeterminism to plan reaction loops
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
| Hi-index | 0.00 |
We describe the modular architecture of a generic dialogue systemthat assists a user/operator in performing a task with a tool. Thiscoaching system is named CALLIOPE after the Greek goddess of eloquence. Itaims at being an active partner in an intelligent man-machine dialogue. Theintelligent dimension of the coaching system is reflected by its ability toadapt to the user and the situation at hand. The CALLIOPE system containsan explicit user model and world model to situate its dialogue actions. Aplan library allows it to follow loosely predetermined dialoguescenarios.The heart of the coaching system is an AI planning module, which plans aseries of dialogue actions. We present a coherent set of three dialogue orspeech actions that will make up the physical form of the man-machinecommunication.The use of the AI planning paradigm as a basis forman-machine interaction is motivated by research in various disciplines, ase.g., AI, Cognitive Science and Social Sciences. Starting from the man-mancommunication metaphor, we can view the “thinking beforespeaking” of a human communication partner as constructing anunderlying plan which is responsible for the purposiveness, theorganisation and the relevance of the communication.CALLIOPE has been fully implemented and tested on theoretical examples.At present, also three tailored versions of CALLIOPE are in operational usein different industrial application domains: operator support for remedyingtasks in chemical process industry, operator support for a combined task ofplanning, plan execution and process control in the area of chemical process development, and thirdly decision support in productionscheduling.