Fast plan recognition through graph construction and analysis

Goal graph exemplifies plan recognition achievable without a plan library. It´s in this spirit that EFG-graph recognizer is introduced. This method doesn´t suffer the problem of acquisition and handcoding a larger plan library as traditional methods do. It can recognize goals even when actions are only partially observed, and it can make early predications, and these are both problematic for goal graph. Since the recognizer is a domain independent one, the method can be adapted in almost every domain. The experimental results also show that the algorithm has excellent performance in terms of accuracy, efficiency, and scalability.