AUTOTRACKER : REAL-TIME ARCHITECTURE FOR PIPELINE AN D CABLE TRACKING ON AUVs

As the underlying vehicle technologies for AUVs mature, increasing attention is being paid to the development of “smarts”, onboard systems used to enhance and extend the range of autonomous operatio ns that can be undertaken. These include advanced navigation, onboard CAD / CAC techniques (Computer Aided Detection / Computer Aided Classification), mission self-reconfiguration, and detection / recov ery from onboard system failures. This paper concentrates on one of the fastest matur ing, and probably most immediately significant, commercially: Cable and Pipeline Tracking. A modula r approach to this problem has been adopted for the technologies developed as part of the autonomous pipeline and cable tracking system. The AUTOTRACKER project is partially funded by the European Union and companies within the offshore industry. The system will be demonstrated and evaluated on real pipelines and cables using a commercial Survey-AUV. This paper describes AUTOTRACKER’s modular, distributed software architecture. It then outlines the sensor and processing techniques used for real-time control of the AUV to perform tracking and obstacle avoidance. In addition, details of the system tests and practical trials used in the development process ar e outlined.