Evolving Diverse Design Populations Using Fitness Sharing and Random Forest Based Fitness Approximation

  • Kate Reed
  • Duncan F. Gillies
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9027)


A large, diverse design space will contain many non-viable designs. To locate the viable designs we need to have a method of testing the designs and a way to navigate the space. We have shown that using machine learning on artificial data can accurately predict the viability of chairs based on a range of ergonomic considerations. We have also shown that the design space can be explored using an evolutionary algorithm with the predicted viability as a fitness function. We find that this method in conjunction with a fitness sharing technique can maintain a diverse population with many potential viable designs.


Chair design Generative design Fitness sharing Multimodel evolutionary algorithms 


  1. 1.
    Dabbeeru, M.M., Mukerjee, A.: Discovering implicit constraints in design. Artif. Intell. Eng. Des. Anal. Manuf. 25, 57–75 (2011)CrossRefGoogle Scholar
  2. 2.
    Reed, K.: Aesthetic measures for evolutionary vase design. In: Machado, P., McDermott, J., Carballal, S. (eds.) EvoMUSART 2013. LNCS, vol. 7834, pp. 59–71. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  3. 3.
    Schütze, O., et al.: On the detection of nearly optimal solutions in the context of single-objective space mission design problems. Proc. Inst. Mech. Eng. Part G: J. Aerosp. Eng. 225, 1229–1242 (2011)CrossRefGoogle Scholar
  4. 4.
    Deb, K., Saha, A.: Multimodal optimization using a bi-objective evolutionary algorithm. Evol. Comput. 20(1), 27–62 (2012). MIT PressCrossRefGoogle Scholar
  5. 5.
    Črepinšek, M., Liu, S.-H.: Exploration and exploitation in evolutionary algorithms: a survey. ACM Comput. Surv. 45, 3 (2013)Google Scholar
  6. 6.
    Xu, K., Zhang, H., Cohen-Or, D., Chen, B.: Fit and diverse: set evolution for inspiring 3D shape galleries. ACM Trans. Graph. 31(4), 57:1–57:10 (2012). Article 57CrossRefGoogle Scholar
  7. 7.
    Kalogerakis, E., Chaudhuri, S., Koller, D., Koltun, V.: A probabilistic model for component-based shape synthesis. ACM Trans. Graph. 31(4), 55:1–55:11 (2012). Article 55CrossRefGoogle Scholar
  8. 8.
    Clune J., Lipson H.: Evolving three-dimensional objects with a generative encoding inspired by developmental biology. In: Proceedings of the European Conference on Artificial Life, pp 141–148 (2011)Google Scholar
  9. 9.
    Jin, Y.: A comprehensive survey of fitness approximation in evolutionary computation. Soft Comput. 9(1), 3–12 (2005). SpringerCrossRefGoogle Scholar
  10. 10.
    Yüksel, A.Ç.: Automatic music generation using evolutionary algorithms and neural networks. In: 2011 International Symposium on Innovations in Intelligent Systems and Applications (INISTA), pp 354–358 (2011)Google Scholar
  11. 11.
    Hsiao, S.-W., Tsai, H.-C.: Applying a hybrid approach based on fuzzy neural network and genetic algorithm to product form design. Int. J. Ind. Ergon. 35, 411–428 (2005)CrossRefGoogle Scholar
  12. 12.
    Trimble SketchUp.
  13. 13.
  14. 14.
    TU Delft DINED Database.
  15. 15.
    Winter, D.A.: Biomechanics and Motor Control of Human Movement, 4th edn. Wiley, New York (2009)CrossRefGoogle Scholar
  16. 16.
  17. 17.
    Todd, B.A.: Three-dimensional computer model of the human buttocks in vivo. J Rehabil. Res. Dev. 31(2), 111–119 (1994)Google Scholar
  18. 18.
    Zhu, H.: Modeling of pressure distribution of human body load on an office chair seat. Masters thesis. Department of Mechanical Engineering, Blekinge Institute of Technology (2013)Google Scholar
  19. 19.
  20. 20.
  21. 21.
    Yu, X., Gen, M.: Introduction to Evolutionary Algorithms. Decision Engineering. Springer, London (2012)Google Scholar
  22. 22.
    Umetani, N., Igarashi, T., Mitra, N.J.: Guided exploration of physically valid shapes for furniture design. ACM Trans. Graph. 31(4), 86:1–86:11 (2012). Article 86CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of ComputingImperial College LondonLondonUK

Personalised recommendations