Development of SSVEP-based intelligent wheelchair brain computer interface assisted by reactive obstacle avoidance

Abstract

This paper proposed a SSVEP-based brain-computer interface (BCI) for wheelchair controls. SSVEP is an evoked signal which responds to visual flickering stimuli at a specific frequency. A stimulus panel containing 12, 15, 18 and 28-Hz flickering stimuli was presented in front of users. Each flickering stimulus was used to evoke SSVEP and responded to a particular command for the wheelchair control. The power spectrum densities (PSDs) for the specific frequency bands were analyzed. A target stimuli was triggered when the PSD exceeded a defined threshold. Users were able to drive the wheelchair with forward, stop, left-turn and right-turn commands according to their intentions. Additionally, a reactive navigation scheme based on artificial potential field (APF) approach was implemented to improve the security of the proposed system. A laser scanner was outfitted for obstacle detections. The proposed wheelchair system is expected to provide a convenient, safe and comfortable mobile assistance to users suffering spinal cord injuries (SCIs).