Abstract
To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings-a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.
| Original language | English |
|---|---|
| Title of host publication | GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 127-128 |
| Number of pages | 2 |
| ISBN (Electronic) | 9781450367486 |
| DOIs | |
| Publication status | Published - 13 Jul 2019 |
| Event | 2019 Genetic and Evolutionary Computation Conference, GECCO 2019 - Prague, Czech Republic Duration: 13 Jul 2019 → 17 Jul 2019 |
Publication series
| Name | GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion |
|---|
Conference
| Conference | 2019 Genetic and Evolutionary Computation Conference, GECCO 2019 |
|---|---|
| Country | Czech Republic |
| City | Prague |
| Period | 13/07/19 → 17/07/19 |
Fingerprint
Keywords
- Encodings
- Evolutionary Robotics
Cite this
}
Comparing encodings for performance and phenotypic exploration in evolving modular robots. / Veenstra, Frank; Hart, Emma; Buchanan, Edgar; Li, Wei; De Carlo, Matteo; Eiben, Agoston E.
GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, 2019. p. 127-128 (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion).Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - Comparing encodings for performance and phenotypic exploration in evolving modular robots
AU - Veenstra, Frank
AU - Hart, Emma
AU - Buchanan, Edgar
AU - Li, Wei
AU - De Carlo, Matteo
AU - Eiben, Agoston E.
PY - 2019/7/13
Y1 - 2019/7/13
N2 - To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings-a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.
AB - To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings-a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.
KW - Encodings
KW - Evolutionary Robotics
UR - http://www.scopus.com/inward/record.url?scp=85070649159&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85070649159&partnerID=8YFLogxK
U2 - 10.1145/3319619.3322054
DO - 10.1145/3319619.3322054
M3 - Conference contribution
T3 - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion
SP - 127
EP - 128
BT - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion
PB - Association for Computing Machinery, Inc
ER -