Evidence suggests that metacognition-the ability to monitor the cognitive processes and regulate them-exists not only in humans but also in some animals. In nature, humans and animals use metacognition to self-regulate their learning process. This paper gathers evidence of metacognition in nature from research in various disciplines. It also shows how metacognition can be modeled in artificial systems and how the model is applied in an Air Traffic Control Simulator system.
Agents that operate in the real world have to make decisions on how long they can deliberate before they act. If the agent deliberates for too long, the agent may miss a deadline or the environment may change such that the preconditions for acting may no longer hold true. If the agent acts too quickly without proper deliberation, it may miss opportunities or may even perform the wrong action.Artificial agents with a metacognitive ability to monitor and influence its deliberation and action can potentially make intelligent decisions on when to stop deliberating and start acting. This research is motivated by the evidence that suggests the role of emotions in the cognitive activities of humans. This paper describes how a model of emotions can be applied to enhance the metacognitive capabilities of an artificial agent to choose between deliberation and action. The emotional model is illustrated within the domain of an air traffic control simulation system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.