NormalFlow: Fast, Robust, and Accurate Contact-based Object 6DoF Pose Tracking with Vision-based Tactile Sensors

“NormalFlow: Fast, Robust, and Accurate Contact-based Object 6DoF Pose Tracking with Vision-based Tactile Sensors” by H.-J. Huang, M. Kaess, and W. Yuan. IEEE Robotics and Automation Letters, RA-L, vol. 10, no. 1, Jan. 2025, pp. 452-459.

Abstract

Tactile sensing is crucial for robots aiming to achieve human-level dexterity. Among tactile-dependent skills, tactile-based object tracking serves as the cornerstone for many tasks, including manipulation, in-hand manipulation, and 3D reconstruction. In this work, we introduce NormalFlow, a fast, robust, and real-time tactile-based 6DoF tracking algorithm. Leveraging the precise surface normal estimation of vision-based tactile sensors, NormalFlow determines object movements by minimizing discrepancies between the tactile-derived surface normals. Our results show that NormalFlow consistently outperforms competitive baselines and can track low-texture objects like table surfaces. For long-horizon tracking, we demonstrate when rolling the sensor around a bead for 360 degrees, NormalFlow maintains a rotational tracking error of 2.5 degrees. Additionally, we present state-of-the-art tactile-based 3D reconstruction results, showcasing the high accuracy of NormalFlow. We believe NormalFlow unlocks new possibilities for high-precision perception and manipulation tasks that involve interacting with objects using hands.

BibTeX entry:

@article{Huang25ral,
   author = {H.-J. Huang and M. Kaess and W. Yuan},
   title = {Normal{F}low: Fast, Robust, and Accurate Contact-based Object
	{6DoF} Pose Tracking with Vision-based Tactile Sensors},
   journal = {IEEE Robotics and Automation Letters, RA-L},
   volume = {10},
   number = {1},
   pages = {452-459},
   month = jan,
   year = {2025}
}
Last updated: April 20, 2026