Do You Get It? User-Evaluated Explainable BDI Agents
نویسندگان
چکیده
In this paper we focus on explaining to humans the behavior of autonomous agents, i.e., explainable agents. Explainable agents are useful for many reasons including scenario-based training (e.g. disaster training), tutor and pedagogical systems, agent development and debugging, gaming, and interactive storytelling. As the aim is to generate for humans plausible and insightful explanations, user evaluation of different explanations is essential. In this paper we test the hypothesis that different explanation types are needed to explain different types of actions. We present three different, generically applicable, algorithms that automatically generate different types of explanations for actions of BDIbased agents. Quantitative analysis of a user experiment (n=30), in which users rated the usefulness and naturalness of each explanation type for different agent actions, supports our hypothesis. In addition, we present feedback from the users about how they would explain the actions themselves. Finally, we hypothesize guidelines relevant for the development of explainable BDI agents.
منابع مشابه
iRoute: Cognitive Support for Independent Living Using BDI Agent Deliberation
Self-care will be a key driver to save the economy in Western countries, and technology can support it. This paper proposes to use the well-known BeliefDesire-Intention (BDI) [3] [8] architecture, in addition to guidance mobility patterns in order that people with dementia, their caretakers and relatives can feel more safe while maintaining freedom of mobility. Agent architectures are evaluated...
متن کاملIt Ain’t What You Do (But the Way That You Do It): Will Safety II Transform the Way We Do Patient Safety; Comment on “False Dawns and New Horizons in Patient Safety Research and Practice”
Mannion and Braithwaite outline a new paradigm for studying and improving patient safety – Safety II. In this response, I argue that Safety I should not be dismissed simply because the safety management strategies that are developed and enacted in the name of Safety I are not always true to the original philosophy of ‘systems thinking.’
متن کاملEven grues get full - the fourth user friendly collection
Come with us to read a new book that is coming recently. Yeah, this is a new coming book that many people really want to read will you be one of them? Of course, you should be. It will not make you feel so hard to enjoy your life. Even some people think that reading is a hard to do, you must be sure that you can do it. Hard will be felt when you have no ideas about what kind of book to read. Or...
متن کاملNo Pizza for You: Value-based Plan Selection in BDI Agents
Autonomous agents are increasingly required to be able to make moral decisions. In these situations, the agent should be able to reason about the ethical bases of the decision and explain its decision in terms of the moral values involved. This is of special importance when the agent is interacting with a user and should understand the value priorities of the user in order to provide adequate s...
متن کاملAssessing Reference and User Services in a Digital Age
That's it, a book to wait for in this month. Even you have wanted for long time for releasing this book assessing reference and user services in a digital age; you may not be able to get in some stress. Should you go around and seek fro the book until you really get it? Are you sure? Are you that free? This condition will force you to always end up to get a book. But now, we are coming to give ...
متن کامل