A comparative analysis on genome pleiotropy for evolved soft robots
- Author
- Dries Marzougui (UGent) , Matthijs Biondina (UGent) and Francis wyffels (UGent)
- Organization
- Abstract
- Biological evolution shapes the body and brain of living creatures together over time. By contrast, in evolutionary robotics, the co-optimization of these subsystems remains challenging. Conflicting mutations cause dissociation between morphology and control, which leads to premature convergence. Recent works have proposed algorithmic modifications to mitigate the impact of conflicting mutations. However, the importance of genetic design remains underexposed. Current approaches are divided between a single, pleiotropic genetic encoding and two isolated encodings representing morphology and control. This design choice is commonly made ad hoc, causing a lack of consistency for practitioners. To standardize this design, we performed a comparative analysis between these two configurations on a soft robot locomotion task. Additionally, we incorporated two currently unexplored alternatives that drive these configurations to their logical extremes. Our results demonstrate that pleiotropic representations yield superior performance in fitness and robustness towards premature convergence. Moreover, we showcase the importance of shared structure in the pleiotropic representation of robot morphology and control to achieve this performance gain. These findings provide valuable insights into genetic encoding design, which supply practitioners with a theoretical foundation to pursue efficient brain-body co-optimization.
- Keywords
- Brain-body co-optimization, CPPN, Genetic encodings, Soft Robotics, Representation, Evolutionary Robotics
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 506.85 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8761994
- MLA
- Marzougui, Dries, et al. “A Comparative Analysis on Genome Pleiotropy for Evolved Soft Robots.” PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, edited by Jonathan E. Fieldsend, Association for Computing Machinery (ACM), 2022, pp. 136–39, doi:10.1145/3520304.3528977.
- APA
- Marzougui, D., Biondina, M., & wyffels, F. (2022). A comparative analysis on genome pleiotropy for evolved soft robots. In J. E. Fieldsend (Ed.), PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022 (pp. 136–139). https://doi.org/10.1145/3520304.3528977
- Chicago author-date
- Marzougui, Dries, Matthijs Biondina, and Francis wyffels. 2022. “A Comparative Analysis on Genome Pleiotropy for Evolved Soft Robots.” In PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, edited by Jonathan E. Fieldsend, 136–39. Association for Computing Machinery (ACM). https://doi.org/10.1145/3520304.3528977.
- Chicago author-date (all authors)
- Marzougui, Dries, Matthijs Biondina, and Francis wyffels. 2022. “A Comparative Analysis on Genome Pleiotropy for Evolved Soft Robots.” In PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, ed by. Jonathan E. Fieldsend, 136–139. Association for Computing Machinery (ACM). doi:10.1145/3520304.3528977.
- Vancouver
- 1.Marzougui D, Biondina M, wyffels F. A comparative analysis on genome pleiotropy for evolved soft robots. In: Fieldsend JE, editor. PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022. Association for Computing Machinery (ACM); 2022. p. 136–9.
- IEEE
- [1]D. Marzougui, M. Biondina, and F. wyffels, “A comparative analysis on genome pleiotropy for evolved soft robots,” in PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022, Boston, Massachusetts, 2022, pp. 136–139.
@inproceedings{8761994,
abstract = {{Biological evolution shapes the body and brain of living creatures together over time. By contrast, in evolutionary robotics, the co-optimization of these subsystems remains challenging. Conflicting mutations cause dissociation between morphology and control, which leads to premature convergence. Recent works have proposed algorithmic modifications to mitigate the impact of conflicting mutations. However, the importance of genetic design remains underexposed. Current approaches are divided between a single, pleiotropic genetic encoding and two isolated encodings representing morphology and control. This design choice is commonly made ad hoc, causing a lack of consistency for practitioners. To standardize this design, we performed a comparative analysis between these two configurations on a soft robot locomotion task. Additionally, we incorporated two currently unexplored alternatives that drive these configurations to their logical extremes. Our results demonstrate that pleiotropic representations yield superior performance in fitness and robustness towards premature convergence. Moreover, we showcase the importance of shared structure in the pleiotropic representation of robot morphology and control to achieve this performance gain. These findings provide valuable insights into genetic encoding design, which supply practitioners with a theoretical foundation to pursue efficient brain-body co-optimization.}},
author = {{Marzougui, Dries and Biondina, Matthijs and wyffels, Francis}},
booktitle = {{PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2022}},
editor = {{Fieldsend, Jonathan E.}},
isbn = {{9781450392686}},
keywords = {{Brain-body co-optimization,CPPN,Genetic encodings,Soft Robotics,Representation,Evolutionary Robotics}},
language = {{eng}},
location = {{Boston, Massachusetts}},
pages = {{136--139}},
publisher = {{Association for Computing Machinery (ACM)}},
title = {{A comparative analysis on genome pleiotropy for evolved soft robots}},
url = {{http://doi.org/10.1145/3520304.3528977}},
year = {{2022}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: