Robot evolution: Artificial intelligence by artificial evolution

In: Open access government, Band 37, Heft 1, S. 226-227

Abstract

Robot evolution: Artificial intelligence by artificial evolution
Most people think of evolution as a biological phenomenon that produced Life on Earth, plants, animals, and us, the Homo Sapiens. Within Computer Science, however, there is another view: evolution is seen as a metaphor for problem-solving, in particular, as a special approach to optimization, working with a 'population' of solutions and improving them over time through repeated selection-reproduction cycles. This is the research of A.E. Eiben, the Professor of Computational Intelligence at Vrije Universiteit Amsterdam. He notes that the vision of robot evolution foresees a radically new robotic technology where robots can reproduce, evolve, and learn. Robot evolution and development require significant efforts from highly trained experts which is not scalable. This world has an increasing need for novel algorithmic approaches and research tools to explore the space of bodies and brains together and solve the design problem (good body) and the control problem (good brain).In his team, he is discovering new methods needed to tackle complex environments without good models, not only simple, well-known conditions, such as, factories or living rooms.