| Abstract |
Evolutionary robotics is the art of employing evolution to develop the brains, the bodies, or both for autonomous robots. In this talk I explain the benefits of the Evolution of Things for engineering as well as for fundamental research. I argue that constructing systems of self-reproducing machines will lead to an exciting mix of evolutionary computing, robotics, and artificial life with new opportunities and challenges. I outline the concept of EvoSphere, a robotic ecosystem that evolves in real space and real time and its underlying system architecture, the Triangle of Life. Regarding the feasibility, I review the first proof-of-concept implementation, our in-house “Robot Baby” project and two international research projects I participate in, PHOENIX (EU, FET-Open) and “Autonomous Robot Evolution” (UK, EPSRC). Finally, I discuss the perspectives for studies into evolution, the emergence of intelligence, and the interplay between body and brain. |