Prof. Gusz Eiben / Evolving Embodied Intelligence
Abstract
Evolutionary robotics is the art of employing evolution to develop the brains (controllers), the bodies (morphologies), 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, artificial intelligence, robotics, and artificial life with new challenges and opportunities. I will outline the concept of EvoSphere, reflect on the Robot Baby Project, our first proof-of-concept implementation, and the ongoing Autonomous Robot Evolution project (funded by the EPSRC in the UK). Finally, I will discuss a long-term research programme with some “grand questions”, possible applications, and future perspectives.
References
- A.E. Eiben, S. Kernbach, and Evert Haasdijk, Embodied artificial evolution: Artificial evolutionary systems in the 21st Century, Evolutionary Intelligence, 5(4):261-272, 2012
- A.E. Eiben and J. Smith, From evolutionary computation to the evolution of things, Nature, 521:476-482, 2015
- A. E. Eiben, Evolving robot software and hardware, In: Proceedings of the IEEE/ACM 15th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, 2020, pp 1-4.
About the Speaker
A.E. (Gusz) Eiben is professor of Artificial Intelligence on the Vrije Universiteit Amsterdam and visiting professor at the University of York. He is an expert in evolutionary computing and evolutionary robotics with papers in Nature, Science Robotics, and Nature Machine Intelligence. He has been working on multi-parent reproduction, self-adaptation, evolutionary art, and artificial life. Currently he is investigating robots that can reproduce, evolve and learn. In 2016 he carried out the “Robot Baby Project” to showcase the reproduction of two physical robots. His long-term vision aims at demonstrating that artificial evolution can develop artificial intelligence, understanding the role of embodiment and illuminating the evolutionary interplay between the body and the brain.