The concept of an intelligent, bio-inspired and brain controlled robotic system

Abstract

Between the information transfer rate and the classification accuracy of a brain computer interface (BCI) system a balance occurs. If we want higher correct classification rates the BCI system will consequently become slower. Otherwise, a faster (online) BCI system assumes a lower classification rate. If we analyze the human motor system (HMS) we can view the hierarchical organization (with different control levels that receive specific sensorial information) as a corresponding biological solution to solve the problem of the system complexity versus the real time control. The muscular proprioceptors and the receptors from the vestibular system inform (especially at the low motor control levels) the central nervous system about the locomotor mechanics and the body posture. The tactile, visual and auditory information is mainly used by the high control/command levels of the HMS. HMS requires a training time interval for executing a specific motor program (e.q. walking), followed then by a systematic adaptation to the changing of the human living system parameters and of the environment characteristics. This paper presents the concepts of an intelligent, bio-inspired and with auto-organization robotic system (e.g. a wheelchair), iBiAoRS, that will be capable both: to control the system movement dynamics based on a BCI system and to obey the successive hierarchical subordination principle that characterizes the HMS. An auto-organization robotic system is developed and some preliminary results are presented in order to test one of the main concept of iBiAoRS.