Sciweavers

222 search results - page 17 / 45
» Evolved Controllers for Simulated Locomotion
Sort
View
GECCO
2009
Springer
122views Optimization» more  GECCO 2009»
14 years 2 months ago
Evolving symmetric and modular neural networks for distributed control
Problems such as the design of distributed controllers are characterized by modularity and symmetry. However, the symmetries useful for solving them are often difficult to determ...
Vinod K. Valsalam, Risto Miikkulainen
GECCO
2010
Springer
165views Optimization» more  GECCO 2010»
13 years 9 months ago
Evolving robust controller parameters using covariance matrix adaptation
In this paper, the advantages of introducing an additional amount of tests when evolving parameters for specific purposes is discussed. A set of optimal PID-controller parameters...
Gerulf K. M. Pedersen, Martin V. Butz
IJON
2006
127views more  IJON 2006»
13 years 7 months ago
Evolved neural networks based on cellular automata for sensory-motor controller
Constructing the controller of a mobile robot has several issues to be addressed: how to automate behavior generation procedure, how to insert available domain knowledge effective...
Kyung-Joong Kim, Sung-Bae Cho
CEC
2010
IEEE
13 years 8 months ago
Evolvable mechanics: Hardware tools for evolutionary robotics
Embodying robot morphologies evolved in simulation can present serious problems for an engineer when translating simplified simulated mechanisms into working devices, often drawing...
Bill Bigge Inman, R. Harvey
IROS
2006
IEEE
137views Robotics» more  IROS 2006»
14 years 1 months ago
Distributed Control of the Center of Mass of a Modular Robot
— We present a distributed controller for the center of mass of a modular robot. This is useful for locomotion of a modular robot over uneven and unknown terrain. By controlling ...
Mark Moll, Peter M. Will, Maks Krivokon, Wei-Min S...