Online in-hand object localization

Robotic hands are a key component of humanoids. Initially more fragile and larger than their human counterparts, the technology has evolved and the latest generation is close to the human hand in size and robustness. However, it is still disappointing to see how little robotic hands are able to do once the grasp is acquired due to the difficulty to obtain a reliable pose of the object within the palm. This paper presents a novel method based on a particle filter used to estimate online the object pose. It is shown that the method is robust, accurate and handles many realistic scenario without hand crafted rules. It combines an efficient collision checker with a few very simple ideas, that require only a basic knowledge of the geometry of the objects. It is shown, by experiments and simulations, that the algorithm is able to deal with inaccurate finger position measurements and can integrate tactile measurements. The method greatly enhances the performance of common manipulation operations, such as a pick and place tasks, and boosts the sensing capabilities of the robot.