A Basal Ganglia Inspired Soft Switching Approach to the Motion Control of a Car-Like Autonomous Vehicle

This paper presents a new brain-inspired, switching control approach for a car-like autonomous vehicle using a basal ganglia (BG) model as an action selection mechanism. The problem domain has challenging nonholonomic and state constraints which imply no single stabilizing controller solution is possible by time-invariant smooth state feedback. To allow the BG make the correct controller selection from a family of candidate motion controllers, a fuzzy logic-based salience model using reference and tracking error only is developed, and applied in a soft switching control mechanism. To demonstrate the effectiveness of our approach for motion tracking control, we show effective control for a circular trajectory tracking application. The performance and advantages of the proposed fuzzy salience model and the BG-based soft switching control scheme against a traditional single control method are compared.