Shape modeling using visual ID-tags for robotic applications

A new method of shape modeling for robotic applications is proposed. We utilize visual ID-tags to acquire local tangent planes of objects, and generate approximate polyhedral models of the environment. We developed an optimization algorithm for estimating tag configurations and a method of forming polyhedral models of objects. Our approach enables easy modeling using a single camera without pose information. The shape models are superimposed on the real environment, and they are used in many robotic tasks. We examined the performance of the modeling method, and demonstrated the effectiveness of the models in robotic applications.