Evolution and Morphogenesis of Simulated Modular Robots: A Comparison Between a Direct and Generative Encoding
Abstract
Modular robots offer an important benefit in evolutionary robotics, which is to quickly evaluate evolved morphologies and control systems in reality. However, artificial evolution of simulated modular robotics is a difficult and time consuming task requiring significant computational power. While artificial evolution in virtual creatures has made use of powerful generative encodings, here we investigate how a generative encoding and direct encoding compare for the evolution of locomotion in modular robots when the number of robotic modules changes. Simulating less modules would decrease the size of the genome of a direct encoding while the size of the genome of the implemented generative encoding stays the same. We found that the generative encoding is significantly more efficient in creating robot phenotypes in the initial stages of evolution when simulating a maximum of 5, 10, and 20 modules. This not only confirms that generative encodings lead to decent performance more quickly, but also that when simulating just a few modules a generative encoding is more powerful than a direct encoding for creating robotic structures. Over longer evolutionary time, the difference between the encodings no longer becomes statistically significant. This leads us to speculate that a combined approach – starting with a generative encoding and later implementing a direct encoding – can lead to more efficient evolved designs.
Keywords
Modular robots Evolutionary algorithms Direct and generative encodingsNotes
Acknowledgement
This project was in part funded by Project ‘flora robotica’ which has received funding from the European Unions Horizon 2020 research and innovation program under the FET grant agreement, no. 640959. Computation/simulation for the work described in this paper was supported by the DeIC National HPC Centre, SDU. Special thanks to Rodrigo Moreno Garca (Universidad Nacional de Colombia) and Ceyue Liu (China University of Mining & Technology) that helped shape the design and implementation of the robotic Modules.
References
- 1.Lipson, H., Pollack, J.B.: Automatic design and manufacture of robotic lifeforms. Nature 406(6799), 974–978 (2000)CrossRefGoogle Scholar
- 2.Hornby, G.S., Lipson, H., Pollack, J.B.: Generative representations for the automated design of modular physical robots. IEEE Trans. Robot. Autom. 19(4), 703–719 (2003)CrossRefGoogle Scholar
- 3.Eiben, A.E., Bredeche, N., Hoogendoorn, M., Stradner, J., Timmis, J., Tyrrell, A.M., Winfield, A.F.T.: The triangle of life: evolving robots in real-time and real-space. In: Advances in Artificial Life, ECAL 2013, pp. 1056–1063 (2013)Google Scholar
- 4.Stoy, K.: The deformatron robot: a biologically inspired homogeneous modular robot. In: Proceedings - IEEE International Conference on Robotics and Automation, pp. 2527–2531, May 2006Google Scholar
- 5.Reece, J.B., Urry, L.A., Cain, M.L., Wasserman, S.A., Minorsky, P.V., Jackson, R.B.: Campbell Biology. Pearson, Boston (2010)Google Scholar
- 6.Floreano, D., Mattiussi, C.: Bio-Inspired Artificial Intelligence. MIT Press, Cambridge (2008)Google Scholar
- 7.Marbach, D., Ijspeert, A.J.: Online optimization of modular robot locomotion. In: IEEE International Conference Mechatronics and Automation, vol. 1, pp. 248–253, July 2005Google Scholar
- 8.Faíña, A., Bellas, F., López-Peña, F., Duro, R.J.: EDHMoR: evolutionary designer of heterogeneous modular robots. Eng. Appl. Artif. Intell. 26(10), 2408–2423 (2013)CrossRefGoogle Scholar
- 9.Guettas, C., Cherif, F., Breton, T., Duthen, Y.: Cooperative co-evolution of configuration and control for modular robots. In: 2014 International Conference on Multimedia Computing and Systems, ICMCS 2014, pp. 26–31, October 2015Google Scholar
- 10.Sims, K.: Evolving virtual creatures. In: Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, pp. 15–22, July 1994Google Scholar
- 11.Sims, K.: Evolving 3D morphology and behavior by competition. Artif. Life 1(4), 353–372 (1994)CrossRefGoogle Scholar
- 12.Hornby, G., Pollack, J.: The advantages of generative grammatical encodings for physical design. In: Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No. 01TH8546), vol. 1, pp. 600–607 (2001)Google Scholar
- 13.Auerbach, J.E., Bongard, J.C.: Evolving complete robots with CPPN-NEAT: the utility of recurrent connections. In: Proceedings of the 13th Annual Genetic and Evolutionary Computation Conference, GECCO 2011, pp. 1475–1482 (2011)Google Scholar
- 14.Cheney, N., MacCurdy, R., Clune, J., Lipson, H.: Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding. In: Proceeding of the Fifteenth Annual Conference on Genetic and Evolutionary Computation, GECCO 2013, p. 167 (2013)Google Scholar
- 15.Bonardi, S., Vespignani, M., Moeckel, R., Kieboom, J.V.D., Pouya, S., Sproewitz, A., Ijspeert, A.J.: Automatic generation of reduced CPG control networks for locomotion of arbitrary modular robot structures. In: Proceedings of Robotics: Science and Systems (2014)Google Scholar
- 16.Auerbach, J.E., Heitz, G., Kornatowski, P.M., Floreano, D.: Rapid evolution of robot gaits. In: GECCO 2015, pp. 743–744 (2015)Google Scholar
- 17.Lindenmayer, A.: Mathematical models for cellular interactions in development I. Filaments with one-sided inputs. J. Theor. Biol. 18(3), 280–299 (1968)CrossRefGoogle Scholar
- 18.Kamimura, A., Kurokawa, H., Yoshida, E., Murata, S., Tomita, K., Kokaji, S.: Automatic locomotion design and experiments for a modular robotic system. IEEE/ASME Trans. Mechatron. 10(3), 314–325 (2005)CrossRefGoogle Scholar
- 19.Sproewitz, A., Moeckel, R., Maye, J., Ijspeert, A.J.: Learning to move in modular robots using central pattern generators and online optimization. Int. J. Robot. Res. 27(3–4), 423–443 (2008)CrossRefGoogle Scholar
- 20.Still, S., Hepp, K., Douglas, R.J.: Neuromorphic walking gait control. IEEE Trans. Neural Netw. 17(2), 496–508 (2006)CrossRefGoogle Scholar
- 21.Ijspeert, A.J.: Central pattern generators for locomotion control in animals and robots: a review. Neural Netw. 21(4), 642–653 (2008)CrossRefGoogle Scholar
- 22.Rohmer, E., Singh, S.P.N., Freese, M.: V-REP: a versatile and scalable robot simulation framework. In: IEEE International Conference on Intelligent Robots and Systems, pp. 1321–1326 (2013)Google Scholar
- 23.Faiña, A., Orjales, F., Bellas, F., Duro, R.: First steps towards a heterogeneous modular robotic architecture for for intelligent industrial operation. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2011 (2011)Google Scholar
- 24.Cheney, N., Bongard, J., Sunspiral, V., Lipson, H.: On the difficulty of co-optimizing morphology and control in evolved virtual creatures. In: Proceedings of the Artificial Life Conference 2016, ALIFE XV, pp. 226–234 (2016)Google Scholar
- 25.Lindenmayer, A., Jürgensen, H.: Grammars of development: discrete-state models for growth, differentiation, and gene expression in modular organisms. In: Rozenberg, G., Salomaa, A. (eds.) Lindenmayer Systems: Impacts on Theoretical Computer Science, Computer Graphics, and Developmental Biology, pp. 3–21. Springer, Heidelberg (1992)CrossRefGoogle Scholar
- 26.Veenstra, F., Faina, A., Stoy, K., Risi, S.: Generating artificial plant morphologies for function and aesthetics through evolving L-Systems. In: Proceedings of the Artificial Life Conference 2016, pp. 692–699. MIT Press (2016)Google Scholar
- 27.Veenstra, F., Faina, A., Risi, S., Stoy, K.: Video: evolving modular robots using direct and generative encodings (2017). https://www.youtube.com/watch?v=HCDftic1AdA
- 28.Cook, O.F.: Factors of species-formation. Science 23(587), 506–507 (1906)CrossRefGoogle Scholar
- 29.Stanley, K.O., Miikkulainen, R.: Efficient evolution of neural network topologies. In: Proceedings of the 2002 Congress on Evolutionary Computation, CEC 2002, pp. 1757–1762 (2002)Google Scholar
- 30.Lehman, J., Stanley, K.O.: Exploiting open-endedness to solve problems through the search for novelty. In: Artificial Life XI, pp. 329–336 (2008)Google Scholar
- 31.Hornby, G.S.: ALPS: the age-layered population structure for reducing the problem of premature convergence. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, pp. 815–822 (2006)Google Scholar
- 32.Hornby, G.S.: The age-layered population structure (ALPS) evolutionary algorithm. In: Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation (2009)Google Scholar
- 33.Stanley, K.O.: Compositional pattern producing networks: a novel abstraction of development. Genet. Program. Evolvable Mach. 8(2), 131–162 (2007)CrossRefGoogle Scholar
- 34.Christensen, D.J., Schultz, U.P., Stoy, K.: A distributed and morphology-independent strategy for adaptive locomotion in self-reconfigurable modular robots. Robot. Auton. Syst. 61(9), 1021–1035 (2013)CrossRefGoogle Scholar
- 35.Pfeifer, R., Iida, F.: Morphological computation: connecting body, brain and environment. Japan. Sci. Mon. 58(2), 48–54 (2005)Google Scholar
- 36.Prusinkiewicz, P., Lindenmayer, A.: The algorithmic beauty of plants. Plant Sci. 122(1), 109–110 (1997). doi: 10.1016/S0168-9452(96)04526-8CrossRefMATHGoogle Scholar