<p>As long as there have been computers, one goal has been to be able to communicate with them using natural language. It has turned out to be very hard to implement a dialog system that performs as well as a human being in an unrestricted domain, hence most dialog systems today work in small, restricted domains where the permitted dialog is fully controlled by the system.</p><p>In this thesis we present two dialog systems for communicating with an autonomous agent:</p><p>The first system, the WITAS RDE, focuses on constructing a simple and failsafe dialog system including a graphical user interface with multimodality features, a dialog manager, a simulator, and development infrastructures that provides the services that are needed for the development, demonstration, and validation of the dialog system. The system has been tested during an actual flight connected to an unmanned aerial vehicle.</p><p>The second system, CEDERIC, is a successor of the dialog manager in the WITAS RDE. It is equipped with a built-in machine learning algorithm to be able to learn new phrases and dialogs over time using past experiences, hence the dialog is not necessarily fully controlled by the system. It also includes a discourse model to be able to keep track of the dialog history and topics, to resolve references and maintain subdialogs. CEDERIC has been evaluated through simulation tests and user tests with good results.</p> / Report code: LiU{Tek{Lic{2006:29.

Este trabalho apresenta o sistema de planejamento baseado em casos chamado FAR-OFF (Fast and Accurate Retrieval on Fast Forward). Este sistema usa o planejador FF (Fast-Forward) como um sistema generativo para adaptar os casos resgatados, bem como uma nova regra de similaridade chamada ADG, uma nova política de remoção de casos chamada Minimo-Prejuízo e um método de melhora da qualidade de um plano chamado SQUIRE. Todos esses novos métodos permitem um sistema de planejamento baseado em casos tão eficiente quanto os sistemas de planejamento baseados em busca heurística. / This work presents the FAR-OFF (Fast and Accurate Retrieval on Fast Forward) case-based planning system. This system uses the FF planner (Fast-Forward) as an effective generative system to adapt retrieved cases. It also uses a new similarity rule, called ADG, a new case-deletion policy named Minimal-Injury and a new method to improve the solution quality called SQUIRE. All these features are responsible for the results of the FAR-OFF system that are so efficient as the results of the heuristic search based planning systems.

Este trabalho apresenta o sistema de planejamento baseado em casos chamado FAR-OFF (Fast and Accurate Retrieval on Fast Forward). Este sistema usa o planejador FF (Fast-Forward) como um sistema generativo para adaptar os casos resgatados, bem como uma nova regra de similaridade chamada ADG, uma nova política de remoção de casos chamada Minimo-Prejuízo e um método de melhora da qualidade de um plano chamado SQUIRE. Todos esses novos métodos permitem um sistema de planejamento baseado em casos tão eficiente quanto os sistemas de planejamento baseados em busca heurística. / This work presents the FAR-OFF (Fast and Accurate Retrieval on Fast Forward) case-based planning system. This system uses the FF planner (Fast-Forward) as an effective generative system to adapt retrieved cases. It also uses a new similarity rule, called ADG, a new case-deletion policy named Minimal-Injury and a new method to improve the solution quality called SQUIRE. All these features are responsible for the results of the FAR-OFF system that are so efficient as the results of the heuristic search based planning systems.

As long as there have been computers, one goal has been to be able to communicate with them using natural language. It has turned out to be very hard to implement a dialog system that performs as well as a human being in an unrestricted domain, hence most dialog systems today work in small, restricted domains where the permitted dialog is fully controlled by the system. In this thesis we present two dialog systems for communicating with an autonomous agent: The first system, the WITAS RDE, focuses on constructing a simple and failsafe dialog system including a graphical user interface with multimodality features, a dialog manager, a simulator, and development infrastructures that provides the services that are needed for the development, demonstration, and validation of the dialog system. The system has been tested during an actual flight connected to an unmanned aerial vehicle. The second system, CEDERIC, is a successor of the dialog manager in the WITAS RDE. It is equipped with a built-in machine learning algorithm to be able to learn new phrases and dialogs over time using past experiences, hence the dialog is not necessarily fully controlled by the system. It also includes a discourse model to be able to keep track of the dialog history and topics, to resolve references and maintain subdialogs. CEDERIC has been evaluated through simulation tests and user tests with good results. / <p>Report code: LiU{Tek{Lic{2006:29.</p>