Shared representations of actions for alternative suggestion with incomplete information

Common coding theory posits there are cycles between perceptions and actions at the fundamental logic of the nervous system. An action performed by an agent modifies its external environment and/or internal states. The agent is able to complete a given goal by performing a sequence of actions. In this work, shared representations for both perception and action and their processing algorithm are presented that suggest goal-oriented alternative actions even with incomplete information. The alternative actions provide more opportunities for a service robot to achieve goals. Knowledge plays significant roles to successfully complete service tasks. Most knowledge inference mechanisms assume complete and correct knowledge about the environment. Real world environments are often uncertain and only partially observable. Thus, intelligent service robots may have an incomplete knowledge base which includes false negatives and false positives as well as true positives. False negatives and false positives can prevent service robots from completing their service tasks. A case study reveals that the proposed method has proved valuable to suggest alternatives for false information as well as to build reactive plans with customary efficiency.