We describe a model and implementation of evolutionary spiking neurons for embedded microcontrollers with few bytes of memory and very low power consumption. The approach is tested with an autonomous microrobot of less than 1 in^3 that evolves the ability to move in a small maze without human intervention and external computers. Considering the very large diffusion, small size, and low cost of embedded microcontrollers, the approach described here could find its way in several intelligent devices with sensors and/or actuators, as well as in smart credit cards.