A multi-agent approach to self-reflection for cognitive robots

We hypothesize that there are three key cognitive abilities a robot must have in order to effectively interact with humans. First, it must be able to reason about the status of its own internal processing. This might be called “self-awareness”. Second, the robot must be able to reason about the states of the humans with which it interacts. This might be called an “awareness of other”. The third critical cognitive ability is that which allows the robot to reason about its own abilities, cognitive processes, and knowledge. This might be called “self-reflection”. In this paper, we discuss one way to address the special challenges that self-reflection poses to multi-agent cognitive architectures. 1