| Description |
1 online resource (xx, 164 pages) : color illustrations |
| Series |
Synthesis lectures on artificial intelligence and machine learning, 1939-4616 ; #50 |
|
Synthesis lectures on artificial intelligence and machine learning ; #50.
|
| Contents |
1. Introduction -- 1.1. Humans and AI agents : an ambivalent relationship -- 1.2. Explanations in humans -- 1.3. Dimensions of explainable ai systems -- 1.4. Our perspective on human-aware and explainable AI agents -- 1.5. Overview of this book |
|
2. Measures of interpretability -- 2.1. Planning models -- 2.2. Modes of interpretable behavior -- 2.3. Communication to improve interpretability -- 2.4. Other considerations in interpretable planning -- 2.5. Generalizing interpretability measures -- 2.6. Bibliographic remarks |
|
3. Explicable behavior generation -- 3.1. Explicable planning problem -- 3.2. Model-based explicable planning -- 3.3. Model-free explicable planning -- 3.4. Environment design for explicability -- 3.5. Bibliographic remarks |
|
4. Legible behavior -- 4.1. Controlled observability planning problem -- 4.2. Goal legibility -- 4.3. Plan legibility -- 4.4. Bibliographic remarks |
|
5. Explanation as model reconciliation -- 5.1. Model-reconciliation as explanation -- 5.2. Explanation generation -- 5.3. Approximate explanations -- 5.4. User studies -- 5.5. Other explanatory methods -- 5.6. Bibliographic remarks |
|
6. Acquiring mental models for explanations -- 6.1. The urban search and reconnaissance domain -- 6.2. Model uncertainty -- 6.3. Model-free explanations -- 6.4. Assuming prototypical models -- 6.5. Bibliographic remarks |
|
7. Balancing communication and behavior -- 7.1. Modified usar domain -- 7.2. Balancing explanation and explicable behavior generation -- 7.3. Balancing communication and behavior for other measures -- 7.4. Bibliographic remarks |
|
8. Explaining in the presence of vocabulary mismatch -- 8.1. Representation of robot model -- 8.2. Setting -- 8.3. Acquiring interpretable models -- 8.4. Query-specific model acquisition -- 8.5. Explanation confidence -- 8.6. Handling uncertainty in concept mapping -- 8.7. Acquiring new vocabulary -- 8.8. Bibliographic remarks |
|
9. Obfuscatory behavior and deceptive communication -- 9.1. Obfuscation -- 9.2. Multi-observer simultaneous obfuscation and legibility -- 9.3. Lies -- 9.4. Bibliographical remarks |
|
10. Applications -- 10.1. Collaborative decision-making -- 10.2. Humans as actors -- 10.3. Model transcription assistants -- 10.4. Bibliographic remarks -- 11. Conclusion |
| Summary |
From its inception, artificial intelligence (AI) has had a rather ambivalent relationship with humans--swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever-increasing pace, there is a greater need for AI systems to work synergistically with humans. One critical requirement for such synergistic human-AI interaction is that the AI systems' behavior be explainable to the humans in the loop. To do this effectively, AI agents need to go beyond planning with their own models of the world, and take into account the mental model of the human in the loop. At a minimum, AI agents need approximations of the human's task and goal models, as well as the human's model of the AI agent's task and goal models. The former will guide the agent to anticipate and manage the needs, desires and attention of the humans in the loop, and the latter allow it to act in ways that are interpretable to humans (by conforming to their mental models of it), and be ready to provide customized explanations when needed. The authors draw from several years of research in their lab to discuss how an AI agent can use these mental models to either conform to human expectations or change those expectations through explanatory communication. While the focus of the book is on cooperative scenarios, it also covers how the same mental models can be used for obfuscation and deception. The book also describes several real-world application systems for collaborative decision-making that are based on the framework and techniques developed here. Although primarily driven by the authors' own research in these areas, every chapter will provide ample connections to relevant research from the wider literature. The technical topics covered in the book are self-contained and are accessible to readers with a basic background in AI |
| Bibliography |
Includes bibliographical references and index |
| Notes |
Description based on print version record |
| Subject |
Human-computer interaction.
|
|
Human-computer interaction
|
| Form |
Electronic book
|
| Author |
Kulkarni, Anagha, author
|
|
Kambhampati, Subbarao, author.
|
| ISBN |
9781636392905 |
|
1636392903 |
|
