RADAR-X: An Interactive Mixed Initiative Planning Interface Pairing Contrastive Explanations and Revised Plan Suggestions
This system addresses the problem of providing intuitive explanations and revised plan suggestions for users of automated planning decision support systems, aiming to enhance the quality of human decision-making.
This paper introduces RADAR-X, a decision support system that facilitates interactive explanatory dialogues. It allows users to propose alternative plans (foils) and then provides contrastive explanations to clarify why a particular plan was chosen over the user's alternative. The system also uses this interaction to infer user preferences and offer revised plan suggestions.
Decision support systems seek to enable informed decision-making. In the recent years, automated planning techniques have been leveraged to empower such systems to better aid the human-in-the-loop. The central idea for such decision support systems is to augment the capabilities of the human-in-the-loop with automated planning techniques and enhance the quality of decision-making. In addition to providing planning support, effective decision support systems must be able to provide intuitive explanations based on specific user queries for proposed decisions to its end users. Using this as motivation, we present our decision support system RADAR-X that showcases the ability to engage the user in an interactive explanatory dialogue by first enabling them to specify an alternative to a proposed decision (which we refer to as foils), and then providing contrastive explanations to these user-specified foils which helps the user understand why a specific plan was chosen over the alternative (or foil). Furthermore, the system uses this dialogue to elicit the user's latent preferences and provides revised plan suggestions through three different interaction strategies.