Rule based Intention Generalization through Human-Robot Interaction

Humans have the capability of concept generalization. They can generalize an operation specific to an object on different objects present in the scene. In this paper we introduce a novel approach of rule based human intention generalization. The generalization is performed through Human-Robot Interaction (HRI) by inducing the rules online. The online rule induction corresponds to the performed human action on a known object with known characteristics. The novel generalization of an induced rule is performed based on the acceptance, rejection or correction by the human in response to the robot reaction while HRI. A novel method of conflict resolution is also proposed for the generalized rules. The experiments performed for the rule based intention generalization and online rule induction include teaching the robot of a specialized human intention. The robot tries to generalize the taught human intention by applying the actions on the related objects. The robot generalizes the human intention while HRI, based on acceptance, rejection or correction by the human. The intention generalization is performed by embedding the generalized rule into the probabilistic finite state machine. A finite state machine represents a human intention.