Evolvable Morphologies

Evolvable Morphologies is my current PhD project. The long-term vision behind this project foresees the evolution of populations of autonomous robots, without human intervention. For example, in changing environments, robots must be able to adapt to situations not known beforehand when they were designed. In situations as exploring inhospitable locations, like when extracting oil in offshore drilling, for instance, a population of robots should evolve autonomously towards one type of robot able to achieve success in the desired task, and this process of evolution should happen as fast as possible. For such, it must be experimented, analyzed and understood what are the most proper conditions for evolution to occur in the evolutive system to be deployed. This project aims at developing robotic morphologies in a way by which the evolutionary process might be speeded up through the use of epigenetic regulation in the DNA of the robots, taking into consideration cyclic variations of the environment that might benefit from a genetic memory.

Team

Karine Miras
PhD Student

Karine Miras

Prof. dr. Guszti Eiben
Head of the Group

Prof. dr. Guszti Eiben