Dense Force Estimation with an Event-based Optical Tactile Sensor

2026-06-08

AI Summary

Traditional camera-based tactile sensors are limited by frame rate and motion blur, hindering high spatiotemporal resolution in dense 3D force field perception, while existing event-based tactile methods can only estimate net force. This work proposes the first event-based framework for dense 3D tactile force field reconstruction: shear displacements are recovered through event token tracking, normal displacements are predicted using a convolutional neural network, and an inverse finite element method (iFEM) maps these displacements to spatially dense force distributions. For the first time, this approach enables event-driven, spatially dense 3D force estimation, overcoming the limitation of net-force-only prediction. Evaluated over a force range of (4 N, 4 N, 20 N) in the x, y, and z directions, the system achieves mean absolute errors of (0.14 N, 0.10 N, 0.93 N) at approximately 100 Hz, supporting high-speed dexterous manipulation.

Abstract

Humans rely on spatially dense, geometry and force-aware tactile feedback at high temporal resolution for dexterous manipulation. While vision-based tactile sensors enable dense force estimation, they are limited by camera frame rates, motion blur, and data bandwidth. Event-based optical tactile sensors offer an attractive alternative with microsecond temporal resolution and low motion blur, but existing methods are restricted to predicting only net forces. We introduce the first framework for dense 3D force field reconstruction using event-based optical tactile sensors. Our approach estimates 3D surface displacements from event data and maps them to forces via the inverse Finite Elements Method (iFEM). Shear displacements are recovered through the proposed event-based marker tracking algorithm, while normal displacements are predicted by a convolutional neural network trained on a collected dataset of synchronized force-displacement-event data. Experiments demonstrate accurate reconstruction of physically grounded forces, achieving a mean absolute error of (0.14 N, 0.10 N, 0.93 N) over force ranges up to (4 N, 4 N, 20 N), while operating at an average of 100 Hz. This work constitutes a first step toward enabling dense force feedback for high-frequency control in robotic grasping and dexterous manipulation.

Problem

• dense force estimation
• event-based tactile sensor
• 3D force field
• dexterous manipulation
• tactile feedback

Innovation

• event-based tactile sensing
• dense force estimation
• inverse Finite Element Method
• 3D force field reconstruction
• marker tracking