Abstract
Designing robots by hand can be costly and time consuming, especially if the robots have to be created with novel materials, or be robust to internal or external changes. In order to create robots automatically, without the need for human intervention, it is necessary to optimise both the behaviour and the body design of the robot. However, when co-optimising the morphology and controller of a locomoting agent the morphology tends to converge prematurely, reaching a local optimum. Approaches such as explicit protection of morphological innovation have been used to reduce this problem, but it might also be possible to increase exploration of morphologies using a more indirect approach. We explore how changing the environment, where the agent locomotes, affects the convergence of morphologies. The agents’ morphologies and controllers are co-optimised, while the environments the agents locomote in are evolved open-endedly with the Paired Open-Ended Trailblazer (POET). We compare the diversity, fitness and robustness of agents evolving in environments generated by POET to agents evolved in handcrafted curricula of environments. Our agents each contain of a population of individuals being evolved with a genetic algorithm. This population is called the agent-population. We show that agent-populations evolving in open-endedly evolving environments exhibit larger morphological diversity than agent-populations evolving in hand crafted curricula of environments. POET proved capable of creating a curriculum of environments which encouraged both diversity and quality in the populations. This suggests that POET may be capable of reducing premature convergence in co-optimisation of morphology and controllers.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Source code can be found at https://github.com/EmmaStensby/poet-morphology.
References
Auerbach, J.E., Bongard, J.C.: Environmental influence on the evolution of morphological complexity in machines. PLoS Comput. Biol. 10(1), 17. e1003399 (2014). https://doi.org/10.1371/journal.pcbi.1003399, http://infoscience.epfl.ch/record/195214
Brant, J.C., Stanley, K.O.: Minimal criterion coevolution: a new approach to open-ended search. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2017, pp. 67–74. Association for Computing Machinery (2017). ISBN 9781450349208, https://doi.org/10.1145/3071178.3071186
Cheney, N., Bongard, J., Sunspiral, V., Lipson, H.: On the difficulty of co-optimizing morphology and control in evolved virtual creatures. Artif. Life Conf. Proc. 28, 226–233 (2016). https://doi.org/10.1162/978-0-262-33936-0-ch042
Cheney, N., Bongard, J., Sunspiral, V., Lipson, H.: Scalable co-optimization of morphology and control in embodied machines. J. R. Soc. Interface 15(143), 20170937 (2018). ISSN 17425689
Geijtenbeek, T., Pronost, N.: Interactive character animation using simulated physics: a state-of-the-art review. Comput. Graphics Forum 31(8), 2492–2515 (2012). ISSN 0167–7055
Goldberg, D.E., Richardson, J.: Genetic algorithms with sharing for multimodal function optimization (1987)
Ha, D.: Reinforcement learning for improving agent design. Artif. Life 25(4), 352–365 (2019). ISSN 1064–5462
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, GECCO 2006, pp. 815–822. Association for Computing Machinery (2006). ISBN 1595931864. https://doi.org/10.1145/1143997.1144142
Hornby, G.S., Lipson, H., Pollack, J.B.: Evolution of generative design systems for modular physical robots. In: Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation, vol. 4, pp. 4146–4151. IEEE (2001). ISBN 0780365763
Jelisavcic, M., Glette, K., Haasdijk, E., Eiben, A.E.: Lamarckian evolution of simulated modular robots. Front. Robot. AI 6, 9 (2019). ISSN 2296-9144. https://doi.org/10.3389/frobt.2019.00009
Lehman, J., Stanley, K.O.: Abandoning objectives: evolution through the search for novelty alone. Evol. Comput. 19(2), 189–223 (2011). ISSN 1063-6560. https://doi.org/10.1162/EVCO_a_00025
Lehman, J., Stanley, K.O.: Evolving a diversity of virtual creatures through novelty search and local competition. In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation, GECCO 2011, pp. 211–218. Association for Computing Machinery (2011). ISBN 9781450305570. https://doi.org/10.1145/2001576.2001606
Mengshoel, O.J., Goldberg, D.E.: The crowding approach to niching in genetic algorithms. Evol. Comput. 16(3), 315–354 (2008). https://doi.org/10.1162/evco.2008.16.3.315
Miras, K., Ferrante, E., Eiben, A.E.: Environmental influences on evolvable robots. PloS One 15(5), e0233848 (2020)
Nordmoen, J., Veenstra, F., Ellefsen, K.O., Glette, K.: Map-elites enables powerful stepping stones and diversity for modular robotics. arXiv preprint arXiv:2012.04375 (2020)
Nygaard, T., Martin, C., Samuelsen, E., Torresen, J., Glette, K.: Real-world evolution adapts robot morphology and control to hardware limitations. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2018, pp. 125–132. ACM (2018). ISBN 9781450356183
Oleg, K.: Bipedalwalkerhardcore-v2 (2016). https://gym.openai.com
Oliveto, P.S., Sudholt, D., Zarges, C.: On the benefits and risks of using fitness sharing for multimodal optimisation. Theor. Comput. Sci. 773, 53–70 (2019). ISSN 0304-3975
Packard, N., et al.: An overview of open-ended evolution: Editorial introduction to the open-ended evolution ii special issue. Artif. Life 25(2), 93–103 (2019). ISSN 1064–5462
Sims, K.: Evolving virtual creatures. In: Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1994, pp. 15–22. ACM (1994). ISBN 0897916670
Trujillo, L., Olague, G., Lutton, E., de Vega, F.F., Dozal, L., Clemente, E.: Speciation in behavioral space for evolutionary robotics. J. Intell. Robot. Syst. 64(3–4), 323–351 (2011). ISSN 0921–0296
Wang, R., Lehman, J., Clune, J., Stanley, K.O.: Poet: open-ended coevolution of environments and their optimized solutions. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2019, pp. 142–151. Association for Computing Machinery (2019). ISBN 9781450361118, https://doi.org/10.1145/3321707.3321799
Acknowledgments
This work was partially supported by the Research Council of Norway through its Centres of Excellence scheme, project number 262762. The simulations were performed on resources provided by UNINETT Sigma2 - the National Infrastructure for High Performance Computing and Data Storage in Norway.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Stensby, E.H., Ellefsen, K.O., Glette, K. (2021). Co-optimising Robot Morphology and Controller in a Simulated Open-Ended Environment. In: Castillo, P.A., Jiménez Laredo, J.L. (eds) Applications of Evolutionary Computation. EvoApplications 2021. Lecture Notes in Computer Science(), vol 12694. Springer, Cham. https://doi.org/10.1007/978-3-030-72699-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-72699-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72698-0
Online ISBN: 978-3-030-72699-7
eBook Packages: Computer ScienceComputer Science (R0)