The ability to develop Brain-Computer Interfaces (BCI) to Intelligent Systems would\noffer new perspectives in terms of human supervision of complex Artificial Intelligence\n(AI) systems, as well as supporting new types of applications. In this article, we\nintroduce a basic mechanism for the control of heuristic search through fNIRS-based\nBCI. The rationale is that heuristic search is not only a basic AI mechanism but\nalso one still at the heart of many different AI systems. We investigate how usersââ?¬â?¢\nmental disposition can be harnessed to influence the performance of heuristic search\nalgorithm through a mechanism of precision-complexity exchange. From a system\nperspective, we use weighted variants of the AâË?â?? algorithm which have an ability to\nprovide faster, albeit suboptimal solutions. We use recent results in affective BCI\nto capture a BCI signal, which is indicative of a compatible mental disposition in\nthe user. It has been established that Prefrontal Cortex (PFC) asymmetry is strongly\ncorrelated to motivational dispositions and results anticipation, such as approach or\neven risk-taking, and that this asymmetry is amenable to Neurofeedback (NF) control.\nSince PFC asymmetry is accessible through fNIRS, we designed a BCI paradigm\nin which users vary their PFC asymmetry through NF during heuristic search tasks,\nresulting in faster solutions. This is achieved through mapping the PFC asymmetry\nvalue onto the dynamic weighting parameter of the weighted AâË?â?? (WAâË?â??) algorithm.\nWe illustrate this approach through two different experiments, one based on solving\n8-puzzle configurations, and the other on path planning. In both experiments, subjects\nwere able to speed up the computation of a solution through a reduction of search\nspace in WAâË?â??. Our results establish the ability of subjects to intervene in heuristic search\nprogression, with effects which are commensurate to their control of PFC asymmetry:\nthis opens the way to new mechanisms for the implementation of hybrid cognitive\nsystems.
Loading....