In this talk, I will give a brief overview of our recent works in adaptive swarm robotics. I will describe embodied evolutionary robotics, a method used to design lifelong learning algorithms for collectives of robots with limited computation and communication capabilities. While originally loosely inspired from the process of biological evolution, these algorithms face challenges that are usually not addressed in robotics, but arise from the interactions of robots with their environment, and with each other. I will also present some recent results regarding the evolution of coordination in cooperation, which relevance may go beyond robotics.
