neural networks research group
areas
•
people
•
projects
•
demos
•
publications
•
software/data
•
Evolving Symmetric and Modular Neural Network Controllers for Multilegged Robots (2009)
Vinod K. Valsalam
and
Risto Miikkulainen
Controllers for multilegged robots are characterized by modularity and symmetry. However, the controller symmetries necessary for generating appropriate gaits are often difficult to determine analytically. This paper utilizes a nature-inspired approach called Evolution of Network Symmetry and mOdularity (ENSO) to evolve such controllers automatically. It uses group theory to mutate symmetry systematically, making it more effective than mutating symmetry randomly. This approach was evaluated by evolving modular neural network controllers for a quadruped robot in physically realistic simulations. On flat ground, the resulting controllers are as effective as those having hand-designed symmetries. However, they are significantly faster when evolved on inclined ground, where the appropriate symmetries are difficult to determine manually. The group-theoretic symmetry mutations of ENSO are also significantly more effective at evolving such controllers than random symmetry mutations. Thus, ENSO is a promising approach for evolving modular and symmetric controllers for multilegged robots, as well as solutions to distributed control problems in general.
View:
PDF
Citation:
In
xploring New Horizons in Evolutionary Design of Robots: Workshop at the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
, 2009.
Bibtex:
@inproceedings{valsalam:irosws09, title={Evolving Symmetric and Modular Neural Network Controllers for Multilegged Robots}, author={Vinod K. Valsalam and Risto Miikkulainen}, booktitle={xploring New Horizons in Evolutionary Design of Robots: Workshop at the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, url="http://nn.cs.utexas.edu/?valsalam:irosws09", year={2009} }
People
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Vinod Valsalam
Ph.D. Alumni
vkv [at] alumni utexas net
Projects
Learning Strategic Behavior in Sequential Decision Tasks
2009 - 2014
Modular Neuroevolution for Multilegged Locomotion
2007 - 2012
Evolving Locomotion Controllers for Multilegged Robots
2008 - 2010
Utilizing Symmetry in Evolutionary Design
2007 - 2010
Demos
Evolving Controller Symmetry for Multilegged Robots
Vinod Valsalam
2010
Software/Data
ENSO
This package contains software implementing the ENSO approach for evolving symmetric modular neural networks. It also in...
2010
Areas of Interest
Evolutionary Computation
Neuroevolution
Control
Robotics