Sensor Guided Robot Path Generation for Surface Repair Tasks on a Large-Scale Buoyancy Module

Abstract

In the offshore oil and gas industry, the repair of damaged drilling riser buoyancy modules (DRBMs) currently involves the removal of defective regions using hand-held abrasive tools. This operation is not only time consuming, but also exposes the worker to hazardous materials generated by the grinding process. In order to increase productivity and minimize occupational health hazards, an automated robotic repair system is developed. The DRBM has a large and almost featureless surface making it particularly challenging to accurately and efficiently detect and localize all the defective regions on the surface. To address these challenges, an eye-in-hand monocular vision system is used to generate the DRBM's global surface map. The defective regions can then be identified from the map using ellipse detection algorithms, and subsequently removed with a robotic manipulator. Experimental results have shown that the proposed solution is able to accurately and efficiently remove defective regions on the surface of DRBMs.