Robotic bridge inspection within strategic flood evacuation planning

Abstract

Bridges are fragile transport infrastructure elements which require special attention in evacuation planning within flood disaster scenarios. In this paper we present work on a bridge inspection procedure with a marine vehicle in which a bridge statics analysis expert assesses the condition of the bridge from a safe operating station. Given bridge construction knowledge beforehand, our work shows how the assessment can benefit from an unmanned marine vehicle which provides information about the current structural condition of the bridge. Due to quality degradation of standard RGB camera readings caused by varying visibility conditions under water, visual information is captured from an imaging sonar. In contrary to conventional approaches, the assessment of bridges gains quality by considering live stream of sonar images which reveal bridge structure information even under rough water conditions. Additionally, an image registration method is applied which creates a map of the live stream and provides a valuable information source for further bridge assessment. We describe the deployment of the system in a real test field.