A Comparison of Multiobjective Algorithms in Evolving Quadrupedal Gaits

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9825)

Abstract

Robotic systems, whether physical or virtual, must balance multiple objectives to operate effectively. Beyond performance metrics such as speed and turning radius, efficiency of movement, stability, and other objectives contribute to the overall functionality of a system. Optimizing multiple objectives requires algorithms that explore and balance improvements in each. In this paper, we evaluate and compare two multiobjective algorithms, NSGA-II and the recently proposed Lexicase selection, investigating distance traveled, efficiency, and vertical torso movement for evolving gaits in quadrupedal animats. We explore several variations of Lexicase selection, including different parameter configurations and weighting strategies. A control treatment evolving solely on distance traveled is also presented as a baseline. All three algorithms (NSGA-II, Lexicase, and Control) produce effective locomotion in the quadrupedal animat, but differences arise in performance and efficiency of movement. The NSGA-II algorithm significantly outperforms Lexicase selection in all three objectives, while Lexicase selection significantly outperforms the control in two of the three objectives.

Keywords

Evolutionary robotics Multiobjective algorithms Genetic algorithms Computational evolution Lexicase selection NSGA-II 

References

  1. 1.
    Ackerman, J., Seipel, J.: Energy efficiency of legged robot locomotion with elastically suspended loads. IEEE Trans. Robot. 29(2), 321–330 (2013)CrossRefGoogle Scholar
  2. 2.
    Auerbach, J.E., Bongard, J.C.: Environmental Influence on the Evolution of Morphological Complexity in Machines. PLoS Comput. Biol. 10(1), e1003399 (2014)CrossRefGoogle Scholar
  3. 3.
    Beer, R.D.: Toward the evolution of dynamical neural networks for minimally cognitive behavior. In: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, vol. 1, pp. 421–429. MIT Press (1996)Google Scholar
  4. 4.
    Brooks, R.A.: A robot that walks; emergent behaviors from a carefully evolved network. Neural Comput. 1(2), 253–262 (1989)CrossRefGoogle Scholar
  5. 5.
    Cliff, D., Husbands, P., Harvey, I.: Explorations in evolutionary robotics. Adapt. Behav. 2(1), 73–110 (1993)CrossRefGoogle Scholar
  6. 6.
    Clune, J., Beckmann, B.E., Ofria, C., Pennock, R.T.: Evolving coordinated quadruped gaits with the HyperNEAT generative encoding. In: Proceedings of the IEEE Congress on Evolutionary Computation, Trondheim, Norway, pp. 2764–2771 (2009)Google Scholar
  7. 7.
    Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)CrossRefGoogle Scholar
  8. 8.
    Doncieux, S., Mouret, J.B.: Behavioral diversity with multiple behavioral distances. In: Proceedings of the 2013 IEEE Congress on Evolutionary Computation, pp. 1427–1434. IEEE, Cancun (2013)Google Scholar
  9. 9.
    Floreano, D., Husbands, P., Nolfi, S.: Evolutionary robotics. In: Siciliano, B., Khatib, O. (eds.) Handbook of Robotics, pp. 1423–1451. Springer, Berlin (2008)CrossRefGoogle Scholar
  10. 10.
    Gomez, F., Miikkulainen, R.: Active guidance for a finless rocket using neuroevolution. In: Proceedings of the 2003 Genetic and Evolutionary Computation Conference, Chicago, Illinois, USA, pp. 2084–2095 (2003)Google Scholar
  11. 11.
    Helmuth, T., Spector, L., Matheson, J.: Solving uncompromising problems with Lexicase selection. In: IEEE Transactions on Evolutionary Computation, vol. 99, p. 1 (2014)Google Scholar
  12. 12.
    Koos, S., Mouret, J.B., Doncieux, S.: Crossing the reality gap in evolutionary robotics by promoting transferable controllers. In: Proceedings of the 2010 ACM Genetic and Evolutionary Computation Conference, pp. 119–126. ACM, Portland (2010)Google Scholar
  13. 13.
    Lehman, J., Stanley, K.O.: Efficiently evolving programs through the search for novelty. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 837–844. ACM, Portland (2010)Google Scholar
  14. 14.
    Luke, S., Panait, L.: Lexicographic parsimony pressure. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 829–836. Morgan Kaufmann Publishers, New York (2002)Google Scholar
  15. 15.
    Mouret, J.-B.: Novelty-based multiobjectivization. In: Doncieux, S., Bredèche, N., Mouret, J.-B. (eds.) New Horizons in Evolutionary Robotics. SCI, vol. 341, pp. 139–154. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  16. 16.
    Ollion, C., Doncieux, S.: Towards behavioral consistency in neuroevolution. In: Ziemke, T., Balkenius, C., Hallam, J. (eds.) SAB 2012. LNCS, vol. 7426, pp. 177–186. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  17. 17.
    Paul, C.: Morphological computation: a basis for the analysis of morphology and control requirements. Robot. Auton. Syst. 54(8), 619–630 (2006). http://www.sciencedirect.com/science/article/pii/S0921889006000613 CrossRefGoogle Scholar
  18. 18.
    Paul, C., Bongard, J.C.: The road less travelled: morphology in the optimization of biped robot locomotion. In: Proceedings of the 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems, Maui, Hawaii, USA, pp. 226–232 (2001)Google Scholar
  19. 19.
    Schrum, J., Miikkulainen, R.: Evolving multimodal networks for multitask games. IEEE Trans. Comput. Intell. AI Games 4(2), 94–111 (2012)CrossRefGoogle Scholar
  20. 20.
    Sims, K.: Evolving virtual creatures. In: Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, pp. 15–22 (1994)Google Scholar
  21. 21.
    Smith, R.: Open Dynamics Engine (2013). http://www.ode.org/
  22. 22.
    Spector, L.: Assessment of problem modality by differential performance of Lexicase selection in genetic programming: a preliminary report. In: Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation, pp. 401–408. ACM, Philadelphia (2012)Google Scholar
  23. 23.
    Szerlip, P., Stanley, K.O.: Indirectly encoded sodarace for artificial life. In: Proceedings of the 12th European Conference on Artificial Life, Taormina, Italy, pp. 218–225 (2013)Google Scholar
  24. 24.
    Zitzler, E., Laumanns, M., Thiele, L.: SPEA2: improving the strength Pareto evolutionary algorithm. Technical report, Swiss Federal Institute of Technology (ETH), Zurich (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringMichigan State UniversityEast LansingUSA

Personalised recommendations