Tactile sensing plays a key role in robotic manipulation, particularly in tasks like surface inspection. Successful execution requires maintaining contact while accurately tracking object contours. In this work, we propose a Vision-Based Tactile Model Predictive Control (VBT-MPC) framework for robotic contour following using a Vision-Based Tactile Sensor (VBTS) mounted in an eye-in-hand configuration. The proposed controller operates directly in contour features space, thereby avoiding the need for separate pose-estimation modules or complex force-control architectures. We further compare our VBT-MPC with visual-servoing strategies adapted to tactile features, and evaluate contour tracking on objects with diverse geometries and materials in both simulation and real-world experiments.
@article{arxiv.2605.20392,
title = {VBT-MPC: Vision-Based Tactile MPC for Contour Following},
author = {Edison Velasco-Sanchez and Luis F. Recalde and Guanrui Li and Pablo Gil},
journal= {arXiv preprint arXiv:2605.20392},
year = {2026}
}
Comments
This article has been accepted for publication in IEEE Robotics and Automation Letters. This is a preprint version. This work was supported by the Interreg-VI Sudoe and European Regional Development Funds through the REMAIN Project under Grant S1/1.1/E0111