Learning Bayes Filter Models for Tactile Localization
This work addresses a key challenge in robotics manipulation for low-cost or poorly calibrated systems, offering a practical solution for tactile-based localization.
The paper tackles the problem of localizing robotic grippers with imprecise kinematics or unknown world coordinates by introducing learnable Bayes filter models that use tactile feedback, achieving successful localization in both simulation and real-world tabletop tasks with generalization across various object sizes, shapes, and configurations.
Localizing and tracking the pose of robotic grippers are necessary skills for manipulation tasks. However, the manipulators with imprecise kinematic models (e.g. low-cost arms) or manipulators with unknown world coordinates (e.g. poor camera-arm calibration) cannot locate the gripper with respect to the world. In these circumstances, we can leverage tactile feedback between the gripper and the environment. In this paper, we present learnable Bayes filter models that can localize robotic grippers using tactile feedback. We propose a novel observation model that conditions the tactile feedback on visual maps of the environment along with a motion model to recursively estimate the gripper's location. Our models are trained in simulation with self-supervision and transferred to the real world. Our method is evaluated on a tabletop localization task in which the gripper interacts with objects. We report results in simulation and on a real robot, generalizing over different sizes, shapes, and configurations of the objects.