Acknowledgement This thesis is the result of two years of work whereby I have been accompanied and supported by many people. I am extremely indebted to Dr.

The main factors that aaect software understanding are the complexity of the problem solved by the program, the program text, the user's mental ability and experience and the task being performed. This paper describes a planning approach solution to the software understanding problem that focuses on the user's task and expertise. First, user questions about software artifacts have been studied ...

This paper overviews two recently completed vision systems (a rock sampling system for planetary rovers and a bin-picking system for industrial robots). Then, we will examine the reason why these two systems have different architectures although their goals are roughly same, picking up something by visual observation. Based on this discussion, we will develop the task-oriented vision paradigm, ...

Multimodal interface aims at overcoming the shortcomings of conventional human-computer communication -serialized input, excessive accuracy, and low input efficiency -by exploiting the complementary nature of multiple modalities in interpreting user intent, thus improving the efficiency and naturalness of humancomputer interaction. In this paper, we present motivations driving multimodal interf...

A common tool for improving the performance quality of natural language processing systems is the use of contextual information for disambiguation. Here I describe the use of a finite state machine (FSM) to disambiguate speech acts in a machine translation system. The FSM has two layers that model, respectively, the global and local structures found in naturally-occurring conversations. The FSM...