Combining 3D SLAM and visual tracking to reach and retrieve objects in daily-life indoor environments

In this paper, we draw perspectives to endow a humanoid robot with capabilities to reach known object in an indoor environment by combining continuous monitoring and building using SLAM and visual tracking. We integrates and exploits two key features: object recognition using the toolbox BLORT, and a SLAM (Simultaneous Localization And Mapping) software, that unifies volumetric 3D modeling and image-based key-frame modeling to be used in tracking. Using these two modules, we show that it is possible to reach a given object in the environment providing its model is registered and known. Our integration software is exemplified using a humanoid robot HRP-2, we present experimental results that illustrates the performance of our approach.