Abstract
Creating gaits for physical robots is a longstanding and open challenge. Recently, the HyperNEAT generative encoding was shown to automatically discover a variety of gait regularities, producing fast, coordinated gaits, but only for simulated robots. A follow-up study found that HyperNEAT did not produce impressive gaits when they were evolved directly on a physical robot. A simpler encoding hand-tuned to produce regular gaits was tried on the same robot, and outperformed HyperNEAT, but these gaits were first evolved in simulation before being transferred to the robot. In this paper, we tested the hypothesis that the beneficial properties of HyperNEAT would outperform the simpler encoding if HyperNEAT gaits are first evolved in simulation before being transferred to reality. That hypothesis was confirmed, resulting in the fastest gaits yet observed for this robot, including those produced by nine different algorithms from three previous papers describing gaitgenerating techniques for this robot. This result is important because it confirms that the early promise shown by generative encodings, specifically HyperNEAT, are not limited to simulation, but work on challenging real-world engineering challenges such as evolving gaits for real robots.
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
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Beer, R., Gallagher, J.: Evolving dynamical neural networks for adaptive behavior. Adaptive Behavior 1(1), 91–122 (1992)
Bongard, J.C.: Synthesizing Physically-Realistic Environmental Models from Robot Exploration. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds.) ECAL 2007. LNCS (LNAI), vol. 4648, pp. 806–815. Springer, Heidelberg (2007)
Carroll, S.: Endless Forms Most Beautiful: The New Science of Evo Devo and the Making of the Animal Kingdom. Norton, New York (2005)
Clune, J., Beckmann, B., Ofria, C., Pennock, R.: Evolving coordinated quadruped gaits with the HyperNEAT generative encoding. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 2764–2771 (2009)
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. 144–148 (2011)
Clune, J., Ofria, C., Pennock, R.: The sensitivity of HyperNEAT to different geoemtric representations of a problem. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 2764–2771 (2009)
Clune, J., Stanley, K.O., Pennock, R., Ofria, C.: On the performance of indirect encoding across the contiuum of regularity. IEEE Transactions on Evolutioanry Computation 15, 346–367 (2011)
Gauci, J., Stanley, K.: Generating large-scale neural networks through discovering geometric regularities. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 997–1004. ACM (2007)
Glette, K., Klaus, G., Zagal, J., Torresen, J.: Evolution of locomotion in a simulated quadruped robot and transferral to reality. In: Proceedings of the Seventeenth International Symposium on Artificial Life and Robotics (2012)
Hornby, G., Lipson, H., Pollack, J.B.: Generative representations for the automated design of modular physical robots. IEEE Transactions on Robotics and Automation 19, 703–719 (2003)
Hornby, G., Takamura, S., Tamamoto, T., Fujita, M.: Autonomous evolution of dynamic gaits with two quadruped robots. IEEE Transactions on Robotics 21(3), 402–410 (2005)
Kohl, N., Stone, P.: Machine learning for fast quadrupedal motion. In: The Nineteenth National Conference on Articifial Intelligence (AAAI), pp. 611–616 (2004)
Koos, S., Mouret, J., Doncieux, S.: The transferability approach: Crossing the reality gap in evolutionary robotics. IEEE Trans. Evolutionary Computation 1, 1–25 (2012)
Lohmann, S., Yosinksi, J., Gold, E., Clune, J., Blum, J., Lipson, H.: Aracna: An open-source quadruped platform for evolutionary robotics. In: Proceedings of the 13th International Conference on the Synthesis and Simulation of Living Systems, pp. 387–392 (2012)
Raibert, M., Chepponis, M., Brown Jr., H.: Running on four legs as though they were one. IEEE Journal of Robotics and Automation 2(2), 70–82 (1986)
Ridderstrom, C.: Legged locomotion control–a literature survey. In: Tech Report: Royal Institute of Technology. pp. 1400–1179. No. TRITA-MMK, Stockholm, Sweden (1999)
Secretan, J., Beato, N., D’Ambrosio, D., Rodriguez, A., Campbell, A., Folsom-Kovarik, J., Stanley, K.: Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space. Evolutionary Computation 19(3), 373–403 (2011)
Shen, H., Yosinski, J., Kormushev, P., Caldwell, D.G., Lipson, H.: Learning fast quadruped robot gaits with the RL power spline parameterization. In: AIMSA Workshop on Advances in Robot Learning and Human-Robot Interaction (2012)
Stanley, K.O.: Compositional pattern producing networks: A novel abstraction of development. Genetic Programming and Evolvable Matter 8(2), 131–152 (2007)
Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artificial Life 15(2), 185–212 (2009)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)
Téllez, R.A., Angulo, C., Pardo, D.E.: Evolving the Walking Behaviour of a 12 DOF Quadruped Using a Distributed Neural Architecture. In: Ijspeert, A.J., Masuzawa, T., Kusumoto, S. (eds.) BioADIT 2006. LNCS, vol. 3853, pp. 5–19. Springer, Heidelberg (2006)
Valsalam, V., Miikkulainen, R.: Modular neuroevolution for multilegged locomotion. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 265–272 (2008)
Wettergreen, D., Thorpe, C.: Gait generation for legged robots. In: IEEE International Conference on Intelligent Robots and Systems, pp. 1413–1420 (1992)
Yosinski, J., Clune, J., Hidalgo, D., Nguyen, S., Zagal, J., Lipson, H.: Evolving robot gaits in hardware: the HyperNEAT generative encoding vs. parameter optimization. In: Proceedings of the 20th European Conference on Artificial Life, pp. 11–18 (2011)
Zagal, J., Ruiz-del-Solar, J., Vallejos, P.: Back to reality: Crossing the reality gap in evolutionary robotics. In: Proceedings of IAV 2004, the 5th IFAC Symposium on Intelligent Autonomous Vehicles (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, S., Yosinski, J., Glette, K., Lipson, H., Clune, J. (2013). Evolving Gaits for Physical Robots with the HyperNEAT Generative Encoding: The Benefits of Simulation. In: Esparcia-Alcázar, A.I. (eds) Applications of Evolutionary Computation. EvoApplications 2013. Lecture Notes in Computer Science, vol 7835. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37192-9_54
Download citation
DOI: https://doi.org/10.1007/978-3-642-37192-9_54
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37191-2
Online ISBN: 978-3-642-37192-9
eBook Packages: Computer ScienceComputer Science (R0)