Argumentation-based Agents that Explain their Decisions
This work addresses the need for explainable AI in autonomous systems, particularly for rescue robots, but it is incremental as it builds on existing BDI and argumentation frameworks.
The paper tackles the problem of enabling intelligent agents to explain their goal commitment decisions by proposing an extended BDI model that uses argumentation theory to generate partial and complete explanations, applied to a rescue robot scenario.
Explainable Artificial Intelligence (XAI) systems, including intelligent agents, must be able to explain their internal decisions, behaviours and reasoning that produce their choices to the humans (or other systems) with which they interact. In this paper, we focus on how an extended model of BDI (Beliefs-Desires-Intentions) agents can be able to generate explanations about their reasoning, specifically, about the goals he decides to commit to. Our proposal is based on argumentation theory, we use arguments to represent the reasons that lead an agent to make a decision and use argumentation semantics to determine acceptable arguments (reasons). We propose two types of explanations: the partial one and the complete one. We apply our proposal to a scenario of rescue robots.