Sciweavers

Share
GECCO
2005
Springer

Evolution of multi-loop controllers for fixed morphology with a cyclic genetic algorithm

9 years 8 months ago
Evolution of multi-loop controllers for fixed morphology with a cyclic genetic algorithm
Cyclic genetic algorithms can be used to generate single loop control programs for robots. While successful in generating controllers for individual leg movement, gait generation, and area search path finding, cyclic genetic algorithms have had limited use when dealing with control problems that require different behaviors in response to sensor inputs. For such behaviors, there is a need for modifications that will allow the generation of multiloop control programs, which can properly react to sensor input. In this work, we present modifications to the standard cyclic genetic algorithm that enables it to learn multi-loop control programs with branching that allows the control to jump from one loop to another. Preliminary tests show the success of our modification. Categories and Subject Descriptors I.2.9 [Artificial Intelligence]: Robotics – autonomous vehicles. General Terms Algorithms, experimentation. Keywords Evolutionary robotics, learning, control, code generation
Gary B. Parker, Ramona Georgescu
Added 27 Jun 2010
Updated 27 Jun 2010
Type Conference
Year 2005
Where GECCO
Authors Gary B. Parker, Ramona Georgescu
Comments (0)
books