We describe an approach to integrate dialogue management, machine-learning and action planning in a system for dialogue between a human and a robot. Case-based techniques are used because they permit life-long learning from experience and demand little prior knowledge and few static hand-written structures. This approach has been developed through the work on an experimental dialogue system, called CEDERIC, that is connected to an unmanned aerial vehicle (UAV). A single case base and case-based reasoning engine is used both for understanding and for planning actions by the UAV. Dialogue experiments both with experienced and novice users, where the users have solved tasks by dialogue with this system, showed very adequate success rates.

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.

We present a discourse model integrated with a case-based reasoning dialogue system which learns from experience. The discourse model is capable of solving references, manage subdialogues and respect the current topic in a dialogue in natural language. The framework is flexible enough not to disturb the learning functions, but allows dynamic changes to a large extent. The system is tested in a traffic surveillance domain together with a simulated UAV and is found to be robust and reliable.

We present a robotic dialogue system built on casebased reasoning. The system is capable of solving references and manage sub-dialogues in a dialogue with an operator in natural language. The approach to handle dialogue acts and physical acts in a unison manner together with the use of plans and subplans makes the system very flexible. This flexibility is used for learning purposes where the operator teaches the system a new word and the new knowledge can directly be integrated and used in the old plans. The learning from explanation capability makes the system adaptable to the operator's use of language and the domain it is currently operating in. The implementation of a case-based planner suggested in the paper will further increase the learning and adaptation degree.