ROBust VIsion for Sensing in Industrial Operations and Needs project develops a vision system that finds and measures the location of 3D structures with respect to a CAD-model. Industries using a CAD-system to design parts or working areas need a means of feedback to enable a comparison of designed and manufactured structures. The autonomy of a robotic vehicle is needed in several applications in building and inspecting of large structures, such as ship bodies.

The application of a walking robot and a vision tool can be used for the task of dimensional measurements of parts. The integration of a CAD-model to visual measurement and direct feedback of measurement results is a key aspect. The objective is to render visual processing robust to deviations in parts and environmental conditions. To achieve this goal a technique is developed that integrates different cues of images to obtain confidence of the measurement result.

The benefit for the ship producer is large savings in production cost, as manual measurement and inspection tasks can be executed in a fraction of the time needed before. The measurement of structures using the link to the CAD-model offers a large number of potential applications. The key advantage of this methodology of vision-based measurement is the possibility of directly up-dating the dimensions of a part in the CAD-model automatically.

The project will focus on using the vision system for guiding a robotic vehicle to enable it to navigate and position itself in order to deliver work packages for inspection, welding and other tasks for the structure/body of a large vessel during production. The final demonstration will see the walking robot enter and climb the vessel structure.

The main innovation is to tackle the issue of robustness in visual processing utilising the redundancy of image cues. Setting up a generic cue integration scheme could move vision as viable sensor from the laboratory onto the production floor. The idea is to obtain the first generation of fully autonomous, articulated limbed, walking/climbing mobile robots capable of performing a variety of tasks within confined and hazardous environments.