Learning Latent Space Dynamics for Tactile Servoing
This addresses the problem of enabling robots to use tactile feedback for precise manipulation, though it is incremental as it builds on existing tactile servoing methods with a new manifold-based approach.
The paper tackles tactile servoing for robotic manipulation by learning a dynamics model from demonstration, representing tactile sensing on a 2D manifold to handle various skin geometries, and achieves successful contact point tracking on a robot with a tactile finger.
To achieve a dexterous robotic manipulation, we need to endow our robot with tactile feedback capability, i.e. the ability to drive action based on tactile sensing. In this paper, we specifically address the challenge of tactile servoing, i.e. given the current tactile sensing and a target/goal tactile sensing --memorized from a successful task execution in the past-- what is the action that will bring the current tactile sensing to move closer towards the target tactile sensing at the next time step. We develop a data-driven approach to acquire a dynamics model for tactile servoing by learning from demonstration. Moreover, our method represents the tactile sensing information as to lie on a surface --or a 2D manifold-- and perform a manifold learning, making it applicable to any tactile skin geometry. We evaluate our method on a contact point tracking task using a robot equipped with a tactile finger. A video demonstrating our approach can be seen in https://youtu.be/0QK0-Vx7WkI