Evolving Spatiotemporal Coordination in a Modular
Robotic System
M. Prokopenko, V. Gerasimov, и I. Tanev. From Animals to Animats 9: 9th International
Conference on the Simulation of Adaptive Behavior (SAB
2006), том 4095 из Lecture Notes in Computer Science, стр. 558--569. Rome, Italy, Springer, (25-29 September 2006)
DOI: doi:10.1007/11840541_46
Аннотация
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.
%0 Conference Paper
%1 Prokopenko:2006:SAB
%A Prokopenko, Mikhail
%A Gerasimov, Vadim
%A Tanev, Ivan
%B From Animals to Animats 9: 9th International
Conference on the Simulation of Adaptive Behavior (SAB
2006)
%C Rome, Italy
%D 2006
%E Nolfi, Stefano
%E Baldassarre, Gianluca
%E Calabretta, Raffaele
%E Hallam, John C. T.
%E Marocco, Davide
%E Meyer, Jean-Arcady
%E Miglino, Orazio
%E Parisi, Domenico
%I Springer
%K algorithms, coordination, entropy genetic programming, spatiotemporal
%P 558--569
%R doi:10.1007/11840541_46
%T Evolving Spatiotemporal Coordination in a Modular
Robotic System
%U http://www.ict.csiro.au/staff/mikhail.prokopenko/Publications/Agents/snakebot-corrected.pdf
%V 4095
%X 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.
%@ 3-540-38608-4
@inproceedings{Prokopenko:2006:SAB,
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.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Rome, Italy},
author = {Prokopenko, Mikhail and Gerasimov, Vadim and Tanev, Ivan},
bibsource = {DBLP, http://dblp.uni-trier.de},
biburl = {https://www.bibsonomy.org/bibtex/25b138856f355e8a39eea09270caa9ba1/brazovayeye},
booktitle = {From Animals to Animats 9: 9th International
Conference on the Simulation of Adaptive Behavior (SAB
2006)},
doi = {doi:10.1007/11840541_46},
editor = {Nolfi, Stefano and Baldassarre, Gianluca and Calabretta, Raffaele and Hallam, John C. T. and Marocco, Davide and Meyer, Jean-Arcady and Miglino, Orazio and Parisi, Domenico},
interhash = {0099a49b9f2adf1166470aa8e1e826ed},
intrahash = {5b138856f355e8a39eea09270caa9ba1},
isbn = {3-540-38608-4},
keywords = {algorithms, coordination, entropy genetic programming, spatiotemporal},
month = {25-29 September},
notes = {http://www.sab06.org/},
pages = {558--569},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
size = {12 pages},
timestamp = {2008-06-19T17:49:53.000+0200},
title = {Evolving Spatiotemporal Coordination in a Modular
Robotic System},
url = {http://www.ict.csiro.au/staff/mikhail.prokopenko/Publications/Agents/snakebot-corrected.pdf},
volume = 4095,
year = 2006
}