Effects of behavior network as a suggestion system to assist BCI users

Abstract

This work describes the development of an intelligent agent responsible for making relevant action suggestions to a BCI user in the context of an intelligent environment. For the development of this agent, a modified version of a behavior network, embedded into a neuroscience inspired cognitive architecture, has been implemented. A new soft-preconditions list has been introduced in the original model in order for it to be used as an assistant agent. A number of simulated experiments were performed to evaluate if the behavior network was indeed presenting valuable suggestions and performing as expected. Results suggest that the agent was able to take into account predefined goals, scheduled events and topological information about the environment in order to deliberate over the possible behaviors and make relevant suggestions. A discussion is made about the strong points and drawbacks of this approach and future work is suggested.