Integrating Metacognition into Artificial Agents

Artificial agents need to adapt in order to performeffectively in situations outside of their normal operation specifications.Agents that do not have the capability to adapt to unanticipated situations cannotrecover from unforeseen failures and hence are brittle systems. One approach todeal with the brittleness problem is to have a metacognitive component thatwatches the performance of a host agent and suggests corrective actions torecover from failures. This paper presents the architecture of a metacognitiveagent that can be integrated with any host cognitive agent so that theresulting system can dynamically create expectations about observations from ahost agent’s sensors, and make use of these expectations to notice expectationviolations, assess the cause of a violation and guide a correction if requiredto deal with the violation. The agent makes use of the metacognitive loop (MCL)and three generic ontologies — indications of failures, causes of failures andresponses to deal with failures. This paper describes the work undertaken toenhance the current version of an MCL based agent with the ability toautomatically generate expectations.