Incremental Evolution of Target-Following Neuro-controllers for Flapping-Wing Animats

Jean-Baptiste Mouret 1 Stéphane Doncieux 1 Jean-Arcady Meyer 1
1 Animatlab
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Using an incremental multi-objective evolutionary algorithm and the ModNet encoding, we generated working neuro-controllers for target-following behavior in a simulated flapping-wing animat. To this end, we evolved tail con- trollers that were combined with two closed-loop wing-beat controllers previously generated, and able to secure straight flight at constant altitude and speed. The corresponding results demonstrate that a wing-beat strategy that consists in continuously adapting the twist of the external wing panel leads to better maneuvering capabilities than another strategy that adapts the beating amplitude. Such differences suggest that further improvements in flying control should bet- ter rely on some sort of automatic incremental evolution procedure than on any hand-designed decomposition of the problem.
Document type :
Conference papers
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01300724
Contributor : Jean-Baptiste Mouret <>
Submitted on : Monday, April 11, 2016 - 10:02:53 PM
Last modification on : Thursday, March 21, 2019 - 1:00:17 PM
Long-term archiving on : Tuesday, July 12, 2016 - 11:44:44 AM

File

2006ACTI462.pdf
Files produced by the author(s)

Identifiers

Citation

Jean-Baptiste Mouret, Stéphane Doncieux, Jean-Arcady Meyer. Incremental Evolution of Target-Following Neuro-controllers for Flapping-Wing Animats. SAB 2006 - 9th International Conference on the Simulation of Adaptive Behavior, Sep 2006, Rome, Italy. pp.606--618, ⟨10.1007/11840541_50⟩. ⟨hal-01300724⟩

Share

Metrics

Record views

123

Files downloads

169