Effect of animat complexity on the evolution of hierarchical control

ABSTRACT

Animal movements are realized by a combination of high-level control from the nervous system and joint-level movement provided by the musculoskeletal system. The digital muscle model (DMM) emulates the low-level musculoskeletal system and can be combined with a high-level artificial neural network (ANN) controller forming a hybrid control strategy. Previous work has shown that, compared to ANN-only controllers, hybrid ANN/DMM controllers exhibit similar performance with fewer synapses, suggesting that some computation is offloaded to the low-level DMM. An open question is how the complexity of the robot, in terms of the number of joints, affects the evolution of the ANN control structure. We explore this question by evolving both hybrid controllers and ANN-only controllers for worm-like animats of varying complexity. Specifically, the number of joints in the worms ranges from 1 to 12. Consistent with an earlier study, the results demonstrate that, in most cases, hybrid ANN/DMM controllers exhibit equal or better performance than ANN-only controllers. In addition, above a threshold for animat complexity (number of joints), the ANNs for one variant of the hybrid controllers have significantly fewer connections than the ANN-only controllers.

References

1. R. Alexander and Alexandra Vernon. 1975. The mechanics of hopping by kangaroos (Macropodidae). Journal of Zoology 177, 2 (1975), 265--303.
2. Kellar Autumn, Metin Sitti, Yiching A. Liang, Anne M. Peattie, Wendy R. Hansen, Simon Sponberg, Thomas W. Kenny, Ronald Fearing, Jacob N. Israelachvili, and Robert J. Full. 2002. Evidence for van der Waals adhesion in gecko setae. Proceedings of the National Academy of Sciences 99, 19 (2002), 12252--12256.
3. Josh C. Bongard, Anton Bernatskiy, Ken Livingston, Nicholas Livingston, John Long, and Marc Smith. 2015. Evolving Robot Morphology Facilitates the Evolution of Neural Modularity and Evolvability. In Proceedings of the 2015 Genetic and Evolutionary Computation Conference. ACM, Madrid, Spain, 129--136.
4. Jeff Clune, Benjamin E. Beckmann, Charles Ofria, and Robert T. Pennock. 2009. Evolving coordinated quadruped gaits with the HyperNEAT generative encoding. In Proceedings of the IEEE Congress on Evolutionary Computation. Trondheim, Norway, 2764--2771.
5. S. Doncieux and J.-A. Meyer. 2004. Evolving Modular Neural Networks to Solve Challenging Control Problems. In Proceedings of the Fourth International ICSC Symposium on Engineering of Intelligent Systems (EIS 2004). Madeira, Portugal, 1--7.
6. Dario Floreano, Phil Husbands, and Stefano Nolfi. 2008. Evolutionary Robotics. In Handbook of Robotics. Springer Verlag, Berlin.
7. Rudolf M. Füchslin, Andrej Dzyakanchuk, Dandolo Flumini, Helmut Hauser, Kenneth J. Hunt, Rolf H. Luchsinger, Benedikt Reller, Stephan Scheidegger, and Richard Walker. 2013. Morphological Computation and Morphological Control: Steps Toward a Formal Theory and Applications. Artificial Life 19, 1 (2013), 9--34.
8. Thomas Geijtenbeek, Michiel van de Panne, and A. Frank van der Stappen. 2013. Flexible Muscle-based Locomotion for Bipedal Creatures. ACM Transactions on Graphics 32, 6 (2013), 1--11.
9. Simon F. Giszter, A. Mussa-lvaldi, and Emilio Bizzi. 1993. Convergent force fields organized in the frog's spinal cord. Journal of Neuroscience 13, 2 (1993), 467--491.
10. Faustino Gomez and Risto Miikkulainen. 2003. Active Guidance for a Finless Rocket Using Neuroevolution. In Proceedings of the 2003 Genetic and Evolutionary Computation Conference. Chicago, Illinois, USA, 2084--2095.
11. J.D. Hiller and H. Lipson. 2010. Evolving Amorphous Robots. In Proceedings of the Twelfth International Conference on Artificial Life. Odense, Denmark, 717--724.
12. Gregory S. Hornby and Jordan B. Pollack. 2001. Body-Brain Co-evolution Using L-systems as a Generative Encoding. In Proceedings of the 2001 ACM Genetic and Evolutionary Computation Conference. Morgan Kaufmann, San Francisco, California, USA, 868--875.
13. Dan Lessin, Don Fussell, and Risto Miikkulainen. 2013. Open-Ended Behavioral Complexity for Evolved Virtual Creatures. In Proceedings of the 2013 ACM Genetic and Evolutionary Computing Conference. ACM, Amsterdam, Netherlands, 335--342.
14. Dan Lessin, Don Fussell, and Risto Miikkulainen. 2014. Trading Control Intelligence for Physical Intelligence: Muscle Drives in Evolved Virtual Creatures. In Proceedings of the 2014 Conference on Genetic and Evolutionary Computation. ACM, Vancouver, BC, Canada, 705--712.
15. Jared M. Moore and Philip K. McKinley. 2014. Evolving Joint-Level Control with Digital Muscles. In Proceedings of the 2014 ACM Genetic and Evolutionary Computing Conference. ACM, Vancouver, BC, Canada, 209--216.
16. Jared M. Moore and Philip K. McKinley. 2014. Investigating Modular Coupling of Morphology and Control with Digital Muscles. In Proceedings of the 14th International Conference on the Simulation and Synthesis of Living Systems. ACM, New York, NY, USA, 148--155.
17. Stefano Nolfi and Dario Floreano. 2000. Evolutionary Robotics: The Biology, Intelligence and Technology of Self-Organizing Machines. The MIT Press.
18. Frank Pasemann, Uli Steinmetz, Martin Hulse, and Bruno Lara. 2001. Robot control and the evolution of modular neurodynamics. Theory in Biosciences 120, 3--4 (2001), 311--326.
19. Chandana Paul. 2006. Morphological computation: A basis for the analysis of morphology and control requirements. Robotics and Autonomous Systems 54, 8 (2006), 619--630.
20. John A. Rieffel, Francisco J. Valero-Cuevas, and Hod Lipson. 2010. Morphological communication: Exploiting coupled dynamics in a complex mechanical structure to achieve locomotion. Journal of The Royal Society Interface 7, 45 (April 2010), 613--621.
21. M. Rommerman, D. Kuhn, and F. Kirchner. 2009. Robot design for space missions using evolutionary computation. In IEEE Congress on Evolutionary Computation. Trondheim, Norway, 2098--2105.
22. Jacob Schrum and Risto Miikkulainen. 2014. Evolving Multimodal Behavior with Modular Neural Networks in Ms. Pac-Man. In Proceedings of the 2014 Conference on Genetic and Evolutionary Computation (GECCO '14). ACM, Vancouver, BC, Canada, 325--332.
23. Karl Sims. 1994. Evolving 3D morphology and behavior by competition. Artificial Life 1, 4 (1994), 353--372.
24. Russell Smith. 2013. Open Dynamics Engine, http://www.ode.org/. (2013). http://www.ode.org/
25. J C Spagna, D I Goldman, P-C Lin, D E Koditschek, and R J Full. 2007. Distributed mechanical feedback in arthropods and robots simplifies control of rapid running on challenging terrain. Bioinspiration & Biomimetics 2, 1 (2007), 9--18.
26. Kenneth O. Stanley and Risto Miikkulainen. 2002. Evolving Neural Networks through Augmenting Topologies. Evolutionary Computation 10, 2 (June 2002), 99--127.
27. Adam Stanton and Alastair Channon. 2013. Incremental Neuroevolution of Reactive and Deliberative 3D Agents. In Proceedings of the 13th European Conference on Artificial Life. York, UK, 341--348.
28. F.J. Valero-Cuevas, Jae-Woong Yi, D. Brown, R.V. McNamara, C. Paul, and H. Lipson. 2007. The Tendon Network of the Fingers Performs Anatomical Computation at a Macroscopic Scale. IEEE Transactions on Biomedical Engineering 54, 6 (June 2007), 1161--1166.
29. Vinod K. Valsalam and Risto Miikkulainen. 2008. Modular neuroevolution for multilegged locomotion. In Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation. ACM, Atlanta, GA, USA, 265--272.
30. Barthelemy von Haller, Auke Ijspeert, and Dario Floreano. 2005. Co-evolution of Structures and Controllers for Neubot Underwater Modular Robots. In Advances in Artificial Life, Mathieu S. Capcarrere, Alex A. Freitas, Peter J. Bentley, Colin G. Johnson, and Jon Timmis (Eds.). Lecture Notes in Computer Science, Vol. 3630. Springer Berlin Heidelberg, 189--199.
31. Jack M. Wang, Samuel R. Hamner, Scott L. Delp, and Vladlen Koltun. 2012. Optimizing Locomotion Controllers Using Biologically-based Actuators and Objectives. ACM Trans. Graph. 31, 4, Article 25 (July 2012), 25:1--25:11 pages.
32. X. Yao. 1999. Evolving artificial neural networks. Proc. IEEE 87, 9 (1999), 1423--1447.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Planning and scheduling

      • Robotic planning

        • Evolutionary robotics