aiqbench analysis
This research introduces Tactile-JEPA, a self-supervised learning framework that leverages the spatial topology of distributed electronic skins to improve robot manipulation under visual occlusion. By utilizing sensor connectivity graphs for masking strategies, the method significantly reduces force and orientation estimation errors across diverse magnetic and piezoresistive datasets without requiring labeled data. The work highlights a critical advancement in encoder pre-training quality, directly addressing the gap between vision-based SSL methods and the unique constraints of irregular tactile arrays.
Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors
arXiv:2609.24385v1 Announce Type: cross Abstract: Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trained image encoders are standard in robot learning pipelines, tactile encoders are still commonly trained from scratch from raw, noisy signals, which might limit their expressivity. Existing self-supervised learning (SSL) approaches focus predominantly on vision-based tactile sensors, leaving distributed electronic skins largely unaddressed. These sensors, however, have a distinctive property: their sensing elements are sparse and irregularly arranged over the surface they cover, which makes direct reuse of visual SSL methods suboptimal. We present Tactile-JEPA, an efficient self-supervised pre-training method that uses the spatial arrangement of tactile sensors to learn topology-aware representations. Specifically, it is trained to predict the embeddings of masked sensing elements from the unmasked remainder, using the sensor connectivity graph to guide spatial masking. Our analysis shows that effective tactile representations require capturing both local contact details and the global state of the tactile surface, which we achieve through dual-scale masking. Across three diverse datasets spanning magnetic and piezoresistive sensors, different robot embodiments, and single- and paired-sensor configurations, Tactile-JEPA reduces force estimation error by 6.3% and in-hand orientation error by 20.8% over the prior state-of-the-art, with consistent gains in other downstream applications, including policy learning. Overall, our results demonstrate that the benefit of tactile sensing depends critically on the quality of encoder pre-training, a problem which Tactile-JEPA addresses directly. Code is available at https://github.com/E-Kovtun/tactile.
Abstract:Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trained image encoders are standard in robot learning pipelines, tactile encoders are still commonly trained from scratch from raw, noisy signals, which might limit their expressivity. Existing self-supervised learning (SSL) approaches focus predominantly on vision-based tactile sensors, leaving distributed electronic skins largely unaddressed. These sensors, however, have a distinctive property: their sensing elements are sparse and irregularly arranged over the surface they cover, which makes direct reuse of visual SSL methods suboptimal. We present Tactile-JEPA, an efficient self-supervised pre-training method that uses the spatial arrangement of tactile sensors to learn topology-aware representations. Specifically, it is trained to predict the embeddings of masked sensing elements from the unmasked remainder, using the sensor connectivity graph to guide spatial masking. Our analysis shows that effective tactile representations require capturing both local contact details and the global state of the tactile surface, which we achieve through dual-scale masking. Across three diverse datasets spanning magnetic and piezoresistive sensors, different robot embodiments, and single- and paired-sensor configurations, Tactile-JEPA reduces force estimation error by 6.3% and in-hand orientation error by 20.8% over the prior state-of-the-art, with consistent gains in other downstream applications, including policy learning. Overall, our results demonstrate that the benefit of tactile sensing depends critically on the quality of encoder pre-training, a problem which Tactile-JEPA addresses directly. Code is available at this https URL.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2609.24385 [cs.RO]
(or arXiv:2609.24385v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.24385 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 332 words
Related coverage
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · Jul 15, 2026
A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning
arXiv · Jul 21, 2026
NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning
arXiv · Aug 6, 2026
CI-JEPA: A Counterfactual Analysis of Latent Representations in Joint-Embedding Predictive Architectures for Self-Supervised Learning
arXiv · Oct 7, 2026