| Authors: |
Mikhail Prokopenko
and Vadim Gerasimov
and Ivan Tanev
|
| Editors: |
Stefano Nolfi
and Gianluca Baldassarre
and Raffaele Calabretta
and John C. T. Hallam
and Davide Marocco
and Jean-Arcady Meyer
and Orazio Miglino
and Domenico Parisi
|
| URL: |
http://www.ict.csiro.au/staff/mikhail.prokopenko/Publications/Agents/snakebot-corrected.pdf |
| Tags: |
algorithms,
coordination,
entropy
genetic
programming,
spatiotemporal
|
| Abstract: |
In this paper we present a novel information-theoretic
measure of spatiotemporal coordination in a modular
robotic system, and use it as a fitness function in
evolving the system. This approach exemplifies a new
methodology formalising co-evolution in multi-agent
adaptive systems: information-driven evolutionary
design. The methodology attempts to link together
different aspects of information transfer involved in
adaptive systems, and suggests to approximate direct
task-specific fitness functions with intrinsic
selection pressures. In particular, the
information-theoretic measure of coordination employed
in this work estimates the generalised correlation
entropy K2 and the generalized excess entropy E2
computed over a multivariate time series of actuators'
states. The simulated modular robotic system evolved
according to the new measure exhibits regular
locomotion and performs well in challenging terrains. |
@inproceedings{Prokopenko:2006:SAB,
title = {Evolving Spatiotemporal Coordination in a Modular
Robotic System},
address = {Rome, Italy},
author = {Mikhail Prokopenko and Vadim Gerasimov and Ivan Tanev},
booktitle = {From Animals to Animats 9: 9th International
Conference on the Simulation of Adaptive Behavior (SAB
2006)},
editor = {Stefano Nolfi and Gianluca Baldassarre and Raffaele Calabretta and John C. T. Hallam and Davide Marocco and Jean-Arcady Meyer and Orazio Miglino and Domenico Parisi},
month = {25-29 September},
pages = {558--569},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
url = {http://www.ict.csiro.au/staff/mikhail.prokopenko/Publications/Agents/snakebot-corrected.pdf},
volume = {4095},
year = {2006},
abstract = {In this paper we present a novel information-theoretic
measure of spatiotemporal coordination in a modular
robotic system, and use it as a fitness function in
evolving the system. This approach exemplifies a new
methodology formalising co-evolution in multi-agent
adaptive systems: information-driven evolutionary
design. The methodology attempts to link together
different aspects of information transfer involved in
adaptive systems, and suggests to approximate direct
task-specific fitness functions with intrinsic
selection pressures. In particular, the
information-theoretic measure of coordination employed
in this work estimates the generalised correlation
entropy K2 and the generalized excess entropy E2
computed over a multivariate time series of actuators'
states. The simulated modular robotic system evolved
according to the new measure exhibits regular
locomotion and performs well in challenging terrains.},
bibsource = {DBLP, http://dblp.uni-trier.de}, size = {12 pages}, isbn = {3-540-38608-4}, notes = {http://www.sab06.org/}, doi = {doi:10.1007/11840541_46},
keywords = {algorithms, coordination, entropy genetic programming, spatiotemporal }
}
::