Evolutionary fabrication: the emergence of novel assembly methods in artificial ontogenies

Evolutionary Design Systems (EDSs) have demonstrated the ability to generate a wide array of novel objects, including robots, tables, and antennas. Often, the novelty of these evolved designs is due to their ability to discover and exploit important principles of the design space, such as the truss and the ratchet. One current obstacle to the real-world application of such EDSs is that they often create purely descriptive representations, and are therefore capable of generating designs whose specific assembly is difficult, if not impossible, to infer. One solution that we offer is to evolve how to build, rather than what to build. When evolution occurs in assembly space rather than design space, only buildable objects are produced. Furthermore, as we demonstrate in this paper, doing so allows for the emergence not just of novel designs, but of novel means of assembly.

[1]  Shigeyoshi Tsutsui,et al.  Advances in evolutionary computing: theory and applications , 2003 .

[2]  Gregory S. Hornby,et al.  The advantages of generative grammatical encodings for physical design , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[3]  Lydia E. Kavraki,et al.  On the Complexity of Assembly Partitioning , 1993, CCCG.

[4]  Gregory S. Hornby,et al.  An Evolved Antenna for Deployment on NASA's Space Technology 5 Mission , 2004 .

[5]  Jordan B. Pollack,et al.  Evolution of complexity in real-world domains , 2001 .

[6]  Fumio Hara,et al.  Morpho-functional Machines: The New Species , 2012, Springer Japan.

[7]  Carlos A. Coello Coello,et al.  An updated survey of evolutionary multiobjective optimization techniques: state of the art and future trends , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[8]  Jordan B. Pollack,et al.  Artificial Ontogenies for Real World Design and Assembly , 2004 .

[9]  Rajeev Motwani,et al.  Complexity Measures for Assembly Sequences , 1999, Int. J. Comput. Geom. Appl..

[10]  Jordan B. Pollack,et al.  Coevolutionary robotics , 1999, Proceedings of the First NASA/DoD Workshop on Evolvable Hardware.

[11]  Jordan B. Pollack,et al.  The Emergence of Ontogenic Scaffolding in a Stochastic Development Environment , 2004, GECCO.

[12]  Edwin D. de Jong,et al.  Reducing bloat and promoting diversity using multi-objective methods , 2001 .

[13]  Jordan B. Pollack,et al.  Automated assembly as situated development: using artificial ontogenies to evolve buildable 3-D objects , 2005, GECCO '05.