Probabilistic Surface Friction Estimation Based on Visual and Haptic Measurements
This work addresses the challenge of accurately modeling surface properties like friction for robotics, such as grasping and material recognition, by integrating visual and haptic information, though it is incremental as it builds on existing methods for sensor fusion.
The paper tackles the problem of estimating surface friction coefficients for robotic applications by proposing a joint visuo-haptic model that combines visual and haptic data with limited exploration, demonstrating its ability to estimate varying friction on real multi-material objects and improve grasping success rates by guiding planners to high-friction areas.
Accurately modeling local surface properties of objects is crucial to many robotic applications, from grasping to material recognition. Surface properties like friction are however difficult to estimate, as visual observation of the object does not convey enough information over these properties. In contrast, haptic exploration is time consuming as it only provides information relevant to the explored parts of the object. In this work, we propose a joint visuo-haptic object model that enables the estimation of surface friction coefficient over an entire object by exploiting the correlation of visual and haptic information, together with a limited haptic exploration by a robotic arm. We demonstrate the validity of the proposed method by showing its ability to estimate varying friction coefficients on a range of real multi-material objects. Furthermore, we illustrate how the estimated friction coefficients can improve grasping success rate by guiding a grasp planner toward high friction areas.