Upload any object and evolve it: injecting complex geometric patterns into CPPNs for further evolution

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Reference

Clune, J., Chen, A., Lipson, H.: Upload any object and evolve it: injecting complex geometric patterns into CPPNs for further evolution. In: Proceedings of the IEEE Congress on Evolutionary Computation (2013)

DOI

http://dx.doi.org/10.1109/CEC.2013.6557986

Abstract

Ongoing, rapid advances in three-dimensional (3D) printing technology are making it inexpensive for lay people to manufacture 3D objects. However, the lack of tools to help nontechnical users design interesting, complex objects represents a significant barrier preventing the public from benefitting from 3D printers. Previous work has shown that an evolutionary algorithm with a generative encoding based on developmental biology-a compositional pattern-producing network (CPPN)-can automate the design of interesting 3D shapes, but users collectively had to start each act of creation from a random object, making it difficult to evolve preconceived target shapes. In this paper, we describe how to modify that algorithm to allow the further evolution of any uploaded shape. The technical insight is to inject the distance to the surface of the object as an input to the CPPN. We show that this seeded-CPPN technique reproduces the original shape to an arbitrary resolution, yet enables morphing the shape in interesting, complex ways. This technology also raises the possibility of two new, important types of science: (1) It could work equally well for CPPN-encoded neural networks, meaning neural wiring diagrams from nature, such as the mouse or human connectome, could be injected into a neural network and further evolved via the CPPN encoding. (2) The technique could be generalized to recreate any CPPN phenotype, but substituting a flat CPPN representation for the rich, originally evolved one. Any evolvability extant in the original CPPN genome can be assessed by comparing the two, a project we take first steps toward in this paper. Overall, this paper introduces a method that will enable non-technical users to modify complex, existing 3D shapes and opens new types of scientific inquiry that can catalyze research on bio-inspired artificial intelligence and the evolvability benefits of generative encodings.

Extended Abstract

Bibtex

@INPROCEEDINGS{6557986,
author={Clune, J. and Chen, A. and Lipson, H.},
booktitle={Evolutionary Computation (CEC), 2013 IEEE Congress on},
title={Upload any object and evolve it: Injecting complex geometric patterns into CPPNS for further evolution},
year={2013},
pages={3395-3402},
keywords={artificial intelligence;computational geometry;evolutionary computation;neural nets;solid modelling;three-dimensional printing;3D object;3D printing technology;3D shape;CPPN encoding;CPPN-encoded neural network;bio-inspired artificial intelligence;complex geometric pattern;compositional pattern-producing network;developmental biology;evolutionary algorithm;generative encoding;neural wiring diagram;seeded-CPPN technique;three-dimensional printing technology;Abstracts;Bioinformatics;Encoding;Evolution (biology);Genomics;Neural networks;Shape},
doi={10.1109/CEC.2013.6557986},
url={http://dx.doi.org/10.1109/CEC.2013.6557986, http://de.evo-art.org/index.php?title=Upload_any_object_and_evolve_it:_injecting_complex_geometric_patterns_into_CPPNs_for_further_evolution },
month={June},
}

Used References

J. Auerbach,J. Bongard. Dynamic resolution in the co-evolution of morphology and control. In Proceedings of Artificial Life, 12,2010.

J. Auerbach and J. Bongard. Evolving CPPNs to grow threedimensional physical structures. In Proceedings of the genetic and evolutionary computation conference, pages 627-634. ACM, 2010.

   Full Text: Access at ACM 

P. J. Bentley. Generic Evolutionary Design of Solid O bjects using a Genetic Algorithm. PhD thesis, University of Huddersfield, 1996.

S. Carroll. Endless forms most beautiful: The new science of evo devo and the making of the animal kingdom. Norton, 2005.

N. Cheney, R. MacCurdy, J. Clune, and H. Lipson. Unshack ling evolution: Evolving soft robots with multiple materials and a powerful generative encoding. In Proceedings of the Genetic and Evolutionary Computation Conference, 2013.

J. Clune, B. Beckmann, C. Ofria, and R. Pennock. Evolving coordinated quadruped gaits with the HyperNEAT generative encoding. In Proceedings of the IEEE Congress on Evolutionary Computation, pages 2764-2771, 2009. http://dx.doi.org/10.1109/CEC.2009.4983289

J. Clune and H. L ipson. Evolving three-dimensional objects with a generative encoding inspired by developmental biology. In Proceedings of the European Conference on Artificial Life, pages 144-148, 2011.

J. Clune, C. Ofria, and R. Pennock. The sensitivity of HyperNEAT to different geometric representations of a problem. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 675-682, 2009.

   Full Text: Access at ACM 

J. Clune, K. Stanley, R. Pennock, and C. Ofria. On the performance of indirect encoding across the continuum of regularity. IEEE Transactions on Evolutionary Computation, 15(4):346-367, 2011. http://dx.doi.org/10.1109/TEVC.2010.2104157

P. Dahlstedt. Autonomous evolution of complete piano pieces and performances. In Proceedings of Music AL Workshop. Citeseer, 2007.

D. D'Ambrosio, J. Lehman, S. Risi, and K. Stanley. Evolving po licy geometry for scalable multiagent learning. In Proc. of the Conference on Autonomous Agents and Multiagent Systems, pages 731-738, 2010.

D. D'Ambrosio and K. Stanley. Generative encoding for multiag ent learning. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 819-826. ACM, 2008.

C. Ericson. Real-time collision detection. Morgan Kaufmann, 2004.

J. Gauci,K. Stanley.Generating large-scale neural networks through discovering geometric regularities. In Proceedings of the Genetic and Evolutionary Computation Conference pages 997-1004. ACM 2007. http://dx.doi.org/10.1145/1276958.1277158

J. Gauci,K. Stanley. A case study on the critical role of geometric regularity in machine learning. In Proceedings of the AAAI Conference on Artificial Intelligence pages 628-633. AAAI Press

J. Gauci,K. Stanley. Autonomous evolution of topographic regularities in artificial neural networks. Neural Computation 22(7): 1860-1898, 2010 http://dx.doi.org/10.1162/neco.2010.06-09-1042

A. K. Hoover, P. A. Szerlip, M. E. Norton, T. A. Brindle, Z. Merritt, and K. O. Stanley. Generating a complete multipart musical composition from a single monophonic melody with functional scaffolding. In International Conference on Computational Creativit y, page 111, 2012.

G. Hornby, H. Lipson, and J. Pollack. Generative representations for the automated design of modular physical robots. IEEE Transactions on Robotics and Automation, 19(4):703-719, 2003. http://dx.doi.org/10.1109/TRA.2003.814502

S. Lee, J. Yosinski, K. Glette, H. Lipson, and J. Clune. Evolving gaits for physical robots with the hyperneat generative encoding: the benefits of simulation. In Applications of Evolutionary Computing. Springer, 2013. http://dx.doi.org/10.1007/978-3-642-37192-9_54

J. Lehman and K. Stanley. Exploiting open-endedness to solve problems through the search for novelty. Artificial Life, 11:329, 2008.

A. Lindenmayer. Mathematical models for cellular interactions in development I. Filaments with one-sided inputs. Journal of Theoretical Biology, 18(3):280-299, 1968. http://dx.doi.org/10.1016/0022-5193(68)90079-9

H. Lipson and M. Kurman. Fabricated: The New World of 3D Printing. Wiley, 2013.

W. Lorensen and H. Cline. Marching cubes: A high resolution 3D surface construction algorithm. In Proc. of the 14th annual conference on Computer graphics and interactive techniques, pages 163-169, 1987. http://dx.doi.org/10.1145/37401.37422

M. Pigliucci. Is evolvability evolvable Nature Reviews Genetics, 9(1):75-82, 2008. http://dx.doi.org/10.1038/nrg2278

J. Secretan, N. Beato, D. D'Ambrosio, A. Rodriguez, A. Campbell, J. Folsom-Kovarik, and K. Stanley. Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space. Evolutionary Computation, 19(3):373-403, 2011. http://dx.doi.org/10.1162/EVCO_a_00030

K. Stanley. Composition al pattern producing networks: A novel abstraction of development. Genetic Programming and Evolvable Machines, 8(2):131-162, 2007. http://dx.doi.org/10.1007/s10710-007-9028-8

K. Stanley, D. D'Ambrosio, and J. Gauci. A hypercube-based encoding for evolving large-scale neural networks. Artif. Life, 15(2):185-212, 2009. http://dx.doi.org/10.1162/artl.2009.15.2.15202

K. Stanley and R. Miikkulainen. Evolving neural networks through augmenting topologies. Evolutionary Comput ation, 10(2):99-127, 2002. http://dx.doi.org/10.1162/106365602320169811

K. Stanley and R. Miikkulainen. A taxonomy for artificial embryogeny. Artificial Life, 9(2):93-130, 2003. http://dx.doi.org/10.1162/106454603322221487

G. Wagner. Homologues, natural kinds and the evolution of modularity. Integrative and Comparative Biology, 36(1):36, 1996. http://dx.doi.org/10.1093/icb/36.1.36

G. Wagner and L. Altenberg. Complex adaptations and the evolution of evolvability. Evolution, 50(3):967-976, 1996. http://dx.doi.org/10.2307/2410639

L. Wolpert and C. Tickle. Principles of Development. Oxford University Press, 4th edition, 2010.

B. Woolley and K. Stanley. On the deleterious effects of a priori objectives on evolution and representation. In Proc. of the Genetic and Evolutionary Computation Conference, pages 957-964, 2011. http://dx.doi.org/10.1145/2001576.2001707


Links

Full Text

intern file

Sonstige Links