Bridge condition assessment is important to maintain the quality of highwayroads for public transport. Bridge deterioration with time is inevitable due toaging material, environmental wear and in some cases, inadequate maintenance.Non-destructive evaluation (NDE) methods are preferred for condition assessmentfor bridges, concrete buildings, and other civil structures. Some examples ofNDE methods are ground penetrating radar (GPR), acoustic emission, andelectrical resistivity (ER). NDE methods provide the ability to inspect astructure without causing any damage to the structure in the process. Inaddition, NDE methods typically cost less than other methods, since they do notrequire inspection sites to be evacuated prior to inspection, which greatlyreduces the cost of safety related issues during the inspection process. Inthis paper, an autonomous robotic system equipped with three different NDEsensors is presented. The system employs GPR, ER, and a camera for datacollection. The system is capable of performing real-time, cost-effectivebridge deck inspection, and is comprised of a mechanical robot design andmachine learning and pattern recognition methods for automated steel rebarpicking to provide realtime condition maps of the corrosive deck environments.
展开▼