VBT-MPC: Vision-Based Tactile MPC for Contour Following
For robotic manipulation tasks requiring surface inspection, this work provides a direct tactile-MPC approach that simplifies control architecture.
VBT-MPC enables robotic contour following using tactile features directly, avoiding pose estimation or force control, and achieves accurate tracking on diverse objects in simulation and real-world tests.
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.