We aim at developing autonomous micro-flyers capable of navigating within houses or small indoor environments using vision as principal source of information. Due to severe weight and energy constraints, inspiration is taken from the fly for the selection of sensors, for signal processing, and for the control strategy. The current 30-gram prototype is capable of autonomous steering in a 16x16m textured environment. This paper describes models and algorithms which allow for efficient course stabilization and collision avoidance using optic flow and inertial information.