UniTac-NV: A Unified Tactile Representation For Non-Vision-Based Tactile Sensors

TL;DR

This paper introduces UniTac-NV, a unified encoder-decoder framework that creates a sensor-agnostic latent space for non-vision tactile sensors, enabling cross-sensor data transfer and application in robotic manipulation tasks.

Contribution

It proposes a novel architecture that unifies tactile data from different non-vision sensors into a common latent space, facilitating transfer and generalization across sensors.

Findings

Low error cross-sensor data transfer achieved.

Effective contact geometry estimation across sensors.

Model generalizes to unseen objects.

Abstract

Generalizable algorithms for tactile sensing remain underexplored, primarily due to the diversity of sensor modalities. Recently, many methods for cross-sensor transfer between optical (vision-based) tactile sensors have been investigated, yet little work focus on non-optical tactile sensors. To address this gap, we propose an encoder-decoder architecture to unify tactile data across non-vision-based sensors. By leveraging sensor-specific encoders, the framework creates a latent space that is sensor-agnostic, enabling cross-sensor data transfer with low errors and direct use in downstream applications. We leverage this network to unify tactile data from two commercial tactile sensors: the Xela uSkin uSPa 46 and the Contactile PapillArray. Both were mounted on a UR5e robotic arm, performing force-controlled pressing sequences against distinct object shapes (circular, square, and hexagonal prisms) and two materials (rigid PLA and flexible TPU). Another more complex unseen object was also included to investigate the model's generalization capabilities. We show that alignment in latent space can be implicitly learned from joint autoencoder training with matching contacts collected via different sensors. We further demonstrate the practical utility of our approach through contact geometry estimation, where downstream models trained on one sensor's latent representation can be directly applied to another without retraining.