In this paper we introduce the development of dedicated hardware capable of controlling autonomous micro-scale robots for fault detection/repair in complex inaccessible fluidic environments. This work is part of a European Union funded project entitled SOCIAL, (self organized societies of connectionist intelligent agents capable of learning No IST-2001-38911). The project's aim is to produce a swarm of micro-scale (5 cm3) autonomous robots that, through indirect communication, are capable of achieving fault detection and reparation in difficult, challenging and inaccessible environments. An application benchmark for this project is the on-line monitoring and maintenance of underwater pipelines like those found in the oil industry or desalination plants. The robots would move through the fluidic environment, continuously sensing for corrosion and scaling faults in the pipeline.