GoalMorph: partial goal satisfaction for flexible service composition

AI planning has proven to be a valuable tool for service composition. However, it can fail to satisfy a composite service request if not all the goal states can be reached, due to the context changes or missing service descriptions. Goals themselves are complex structures, conjuctions of goals states, and each representing partial solution. Therefore satisfying some goal states instead of all can be better than satisfying none of the goal states at all. In this paper, we present GoalMorph, a framework for context aware goal transformation that (a) constructs context aware goals and (b) reformulates failed goals into problems that can be solved by the AI planner. We discuss initial evaluation results, and demonstrate that our implementation provides a practical and scalable solution.