Three-fold Adaptivity in Groups of Robots: The Effect of Social Learning

ABSTRACT

Adapting the control systems of robots on the fly is important in robotic systems of the future. In this paper we present and investigate a three-fold adaptive system based on evolution, individual and social learning in a group of robots and report on a proof-of-concept study based on e-pucks. We distinguish inheritable and learnable components in the robots' makeup, specify and implement operators for evolution, learning and social learning, and test the system in an arena where the task is to learn to avoid obstacles. In particular, we make the sensory layout evolvable, the locomotion control system learnable and investigate the effects of including social learning in the `adaptation engine'. Our simulation experiments demonstrate that the full mix of three adaptive mechanisms is practicable and that adding social learning leads to better controllers faster.

References

1. K. Balakrishnan and V. Honavar. On sensor evolution in robotics. In Proceedings of the 1st annual conference on genetic programming, pages 455--460. MIT Press, 1996.
2. H.-G. Beyer. Evolutionary algorithms in noisy environments: theoretical issues and guidelines for practice. Computer Methods in Applied Mechanics and Engineering, 186(2--4):239 -- 267, 2000.
3. J. Bongard. Evolutionary robotics. Communications of the ACM, 56(8):74--85, 2013.
4. N. Bredeche, E. Haasdijk, and A. E. Eiben. On-line, on-board evolution of robot controllers. In P. Collet, N. Monmarché, P. Legrand, M. Schoenauer, and E. Lutton, editors, Proceedings of the 9th international conference on Artificial evolution, pages 110--121, Berlin, 2009. Springer.
5. N. Bredeche, J.-M. Montanier, W. Liu, and A. F. Winfield. Environment-driven distributed evolutionary adaptation in a population of autonomous robotic agents. Mathematical and Computer Modelling of Dynamical Systems, 18(1):101--129, 2012.
6. K. Dautenhahn, D. Polani, and T. Uthmann. Guest editors' introduction: Special issue on sensor evolution. Artificial Life, 7(2):95--97, 2001.
7. S. Doncieux, N. Bredeche, and J.-B. Mouret, editors. New Horizons in Evolutionary Robotics, volume 341 of Studies in Computational Intelligence. Springer, 2011.
8. A. E. Eiben. Grand challenges for evolutionary robotics. Frontiers in Robotics and AI, 1(4), 2014.
9. A. E. Eiben. In Vivo Veritas: towards the Evolution of Things. In T. Bartz-Beielstein, J. Branke, B. Filipi\v c, and J. Smith, editors, Parallel Problem Solving from Nature -- PPSN XIII, volume 8672 of LNCS, pages 24--39. Springer, 2014.
10. S. Elfwing, E. Uchibe, K. Doya, and H. Christensen. Biologically inspired embodied evolution of survival. In 2005 Congress on Evolutionary Computation (CEC'2005), volume 3, pages 2210--2216, Edinburgh, UK, 2005. IEEE Press, Piscataway, NJ.
11. D. Federici. Combining genes and memes to speed up evolution. In 2003 Congress on Evolutionary Computation (CEC'2003), volume 2, pages 747--754, Edinburgh, UK, 2003. IEEE Press, Piscataway, NJ.
12. D. Floreano, P. Husbands, and S. Nolfi. Evolutionary robotics. In B. Siciliano and O. Khatib, editors, Springer Handbook of Robotics, volume Part G.61, pages 1423--1451. Springer, 2008.
13. E. Haasdijk, A. E. Eiben, and A. F. Winfield. Individual, Social and Evolutionary Adaptation in Collective Systems, chapter 12, pages 413--471. Pan Stanford, Singapore, 2013.
14. F. Heylighen and K. Chielens. Cultural evolution and memetics. Encyclopedia of complexity and System Science, pages 1--27, 2008.
15. R.-J. Huijsman, E. Haasdijk, and A. E. Eiben. An on-line on-board distributed algorithm for evolutionary robotics. In J.-K. Hao, P. Legrand, P. Collet, N. Monmarché, E. Lutton, and M. Schoenauer, editors, Artificial Evolution, 10th International Conference Evolution Artificielle, number 7401 in LNCS, pages 73--84. Springer, 2011.
16. A. L. Nelson, G. J. Barlow, and L. Doitsidis. Fitness functions in evolutionary robotics: A survey and analysis. Robotics and Autonomous Systems, 57(4):345 -- 370, 2009.
17. S. Nolfi and D. Floreano. Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press, Cambridge, MA, 2000.
18. M. E. Payton, M. H. Greenstone, and N. Schenker. Overlapping confidence intervals or standard error intervals: what do they mean in terms of statistical significance? Journal of Insect Science, 3(1):34, 2003.
19. P. Vargas, E. D. Paolo, I. Harvey, and P. Husbands, editors. The Horizons of Evolutionary Robotics. MIT Press, 2014.
20. J. H. Walker, S. M. Garrett, and M. S. Wilson. The balance between initial training and lifelong adaptation in evolving robot controllers. IEEE Trans. Syst., Man, Cybern. B, 36(2):423--432, 2006.
21. R. A. Watson, S. G. Ficici, and J. B. Pollack. Embodied evolution: Distributing an evolutionary algorithm in a population of robots. Robotics and Autonomous Systems, 39(1):1--18, Apr. 2002.
22. A. Winfield and J. Timmis. Evolvable robot hardware. In M. Trefzer and A. Tyrrell, editors, Evolvable Hardware, Natural Computing Series, pages 331--348. Springer, 2015.
23. A. F. T. Winfield and M. D. Erbas. On embodied memetic evolution and the emergence of behavioural traditions in robots. Memetic Computing, 3(4):261--270, July 2011.
24. S. Wischmann, K. Stamm, and F. Wörgötter. Embodied evolution and learning: The neglected timing of maturation. In F. Almeida e Costa, editor, Advances in Artificial Life: 9th European Conference on Artificial Life, volume 4648 of Lecture Notes in Artificial Intelligence, pages 284--293. Springer-Verlag, Lisbon, Portugal, September 10--14 2007.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Control methods

    • Search methodologies

• Theory of computation

  • Design and analysis of algorithms

    • Algorithm design techniques

      • Dynamic programming