Towards an Evolutionary Design of Modular Robots for Industry - Foundations on Natural and Artificial Computation - page 50

Towards an Evolutionary Design of Modular
Robots for Industry

Andres Fa ına, Francisco Bellas, Daniel Souto, and Richard J. Duro

Integrated Group for Engineering Research,
Universidade da Coruna, 15403, Ferrol, Spain
{afaina,fran,dsouto,richard}@udc.es
http://www.gii.udc.es

Abstract. We are interested in the next generation of industrial robots,
those that are able to operate in dynamic and unstructured environ-
ments and, consequently, that are able to adapt to changing circum-
stances or to work on different tasks in an autonomous way. In this
sense, multirobot systems and, in particular, modular systems present
several features like scalability, fault tolerance, low maintenance or re-
configuration capabilities that make them highly suitable for this kind of
environments. The work presented here is concerned with the problem
of automatically obtaining the morphology and control structure for this
type of modular systems. In this line, we present the first results pro-
duced using a newly designed constructive evolutionary approach that
takes into account the extreme diculty of the tremendously deceptive
and uninformative search space this type of applications are faced with.
As an example, the algorithm is used to design the morphology and the
distributed control parameters for a typical benchmark problem, that of
moving as far as possible in a straight line, for a heterogeneous modular
robotic system developed by our group.

Keywords: Multi-robot Systems, Modular Robots, Evolutionary Algo-
rithms, Industrial Automation.

1 Introduction

The typical production lines found in industry are highly automated using dedi-
cated robots that perform their tasks in a very accurate and fast manner. These
environments are static and structured. Consequently, the robots are always in
a controlled position and their sensors and actuators can be adjusted assuming
predictable conditions. In order to extend the advantages of robotic automation
to other types of industries, new robots are required that can deal with dynamic
and unstructured environments, such as those found in shipyards or civil engi-
neering projects and that can easily reconfigure to perform different tasks. Some,
albeit few, robots have been designed and tested for use in these types of envi-
ronments. The first example that can be found in civil engineering is the SSR-1,
which was used for the application of a fire protection layer to beams. Additional