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 ….
Contents
1 Introduction
1.1 Motivation
1.2 Research Challenges
1.3 Research Contributions
1.4 Publications
1.5 Thesis Outline
2 Language and Dialog
2.1 The Dream of the Talking Machine
2.2 Dialog Manager Foundations
2.3 Syntactic Models
2.3.1 Syntactic Parsing
2.3.2 Pattern Matching
2.4 Dialog Models
2.4.1 Dialog Grammars
2.4.2 Plan-Based Models of Dialog
2.4.3 Learning Dialog Policies
2.5 Dialog Histories
2.6 Domain Models
2.7 Dialog with Robots
3 Planning and Learning
3.1 Problem Solving versus Planning
3.2 Learning
3.3 Case-Based Reasoning
3.3.1 Case-Based Planning
3.3.2 Conversational Case-Based Reasoning
4 State of the Art
4.1 The WITAS-Stanford Dialog System
4.1.1 The WITAS UAV System
4.1.2 The Dialog System
4.2 The SmartKom Project
4.2.1 The Discourse Model
4.3 Robotic Dialog Systems
4.3.1 Shakey
4.3.2 KAMRO
4.3.3 Jijo-2
4.3.4 Godot
4.3.5 Carl
4.4 Planning in Dialog Systems
4.4.1 TRIPS
4.5 Case-Based Reasoning and Dialog
4.5.1 SiN
4.5.2 The Discourse Goal Stack Model
4.5.3 Case-Based Dialog Systems
5 Phase I – The WITAS RDE
5.1 Background
5.2 The WITAS RDE Architecture
5.3 The Autonomous Operator’s Assistant
5.3.1 The SGUI
5.3.2 The DOSAR Dialog Manager
5.4 Simulations and Test Flights
6 The Research Problem for phase II
6.1 Ideas Behind the Research Problem
6.2 Problem Formulation
7 Phase II – CEDERIC
7.1 Introduction to CEDERIC
7.2 Design Choices
7.2.1 The CBR Architecture
7.2.2 Case-Based Planning
7.2.3 Syntactic Model
7.2.4 Dialog Model
7.2.5 Dialog History
7.2.6 Domain Model
7.3 Discourse Model
7.4 The Case Base
7.4.1 Plan Case
7.4.2 Plan Item
7.5 Case-Base Manager
7.5.1 Dialog Handling
7.5.2 Syntactic Categorization of Words
7.5.3 Case Retrieval
7.5.4 Case Reuse
7.5.5 Replanning
7.5.6 Case Retention
7.6 Learning from Explanation
7.7 An Example
8 Tests and Results
8.1 Development Tests
8.2 Simulation Tests
8.2.1 Scenario I
8.2.2 Scenario II
8.2.3 Results
8.3 User Tests
8.3.1 Results
9 Conclusion
9.1 Retrospective
9.1.1 Predecessors within WITAS
9.1.2 Robot Dialog
9.1.3 Case-Based Reasoning and Planning
9.2 Main Results
9.3 Future Work
Bibliography
Author: Eliasson, Karolina
Source: Linköping University
Download URL 2: Visit Now