Article: Constrained by Design: Influence of Genetic Encodings on Evolved Traits of Robots

Genetic encodings and their particular properties are known to have a strong influence on the success of evolutionary systems. However, the literature has widely focused on studying the effects that encodings have on performance, i.e., fitness-oriented studies. Notably, this anchoring of the literature to performance is limiting, considering that performance provides bounded information about the behavior of a robot system. In this paper, we investigate how genetic encodings constrain the space of robot phenotypes and robot behavior. In summary, we demonstrate how two generative encodings of different nature lead to very different robots and discuss these differences. Our principal contributions are creating awareness about robot encoding biases, demonstrating how such biases affect evolved morphological, control, and behavioral traits, and finally scrutinizing the trade-offs among different biases.

Citing Articles

Morphological Evolution: Bioinspired Methods for Analyzing Bioinspired Robots.

Aaron E, Hawthorne-Madell J, Livingston K, Long Jr J Front Robot AI. 2022; 8:717214.

PMID: 35096977 PMC: 8795882. DOI: 10.3389/frobt.2021.717214.

References

1.

Jelisavcic M, De Carlo M, Hupkes E, Eustratiadis P, Orlowski J, Haasdijk E . Real-World Evolution of Robot Morphologies: A Proof of Concept. Artif Life. 2017; 23(2):206-235. DOI: 10.1162/ARTL_a_00231. View

2.

Komosinski M . Comparison of different genotype encodings for simulated three-dimensional agents. Artif Life. 2002; 7(4):395-418. DOI: 10.1162/106454601317297022. View

3.

Miras K, Ferrante E, Eiben A . Environmental influences on evolvable robots. PLoS One. 2020; 15(5):e0233848. PMC: 7259730. DOI: 10.1371/journal.pone.0233848. View

4.

Kriegman S, Blackiston D, Levin M, Bongard J . A scalable pipeline for designing reconfigurable organisms. Proc Natl Acad Sci U S A. 2020; 117(4):1853-1859. PMC: 6994979. DOI: 10.1073/pnas.1910837117. View

5.

Auerbach J, Bongard J . Environmental influence on the evolution of morphological complexity in machines. PLoS Comput Biol. 2014; 10(1):e1003399. PMC: 3879106. DOI: 10.1371/journal.pcbi.1003399. View

6.

Kodjabachian J, Meyer J . Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects. IEEE Trans Neural Netw. 2008; 9(5):796-812. DOI: 10.1109/72.712153. View

7.

Kuratani S . Modularity, comparative embryology and evo-devo: developmental dissection of evolving body plans. Dev Biol. 2009; 332(1):61-9. DOI: 10.1016/j.ydbio.2009.05.564. View

8.

Stanley K, Miikkulainen R . Evolving neural networks through augmenting topologies. Evol Comput. 2002; 10(2):99-127. DOI: 10.1162/106365602320169811. View

9.

Lindenmayer A . Mathematical models for cellular interactions in development. I. Filaments with one-sided inputs. J Theor Biol. 1968; 18(3):280-99. DOI: 10.1016/0022-5193(68)90079-9. View

10.

Stanley K, DAmbrosio D, Gauci J . A hypercube-based encoding for evolving large-scale neural networks. Artif Life. 2009; 15(2):185-212. DOI: 10.1162/artl.2009.15.2.15202. View

11.

Deloukas P, Schuler G, Gyapay G, Beasley E, Soderlund C, Hui L . A physical map of 30,000 human genes. Science. 1998; 282(5389):744-6. DOI: 10.1126/science.282.5389.744. View