English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Humans make extensive use of vision and touch as complementary senses, withvision providing global information about the scene and touch measuring localinformation during manipulation without suffering from occlusions. While priorwork demonstrates the efficacy of tactile sensing for precise manipulation ofdeformables, they typically rely on supervised, human-labeled datasets. Wepropose Self-Supervised Visuo-Tactile Pretraining (SSVTP), a framework forlearning multi-task visuo-tactile representations in a self-supervised mannerthrough cross-modal supervision. We design a mechanism that enables a robot toautonomously collect precisely spatially-aligned visual and tactile imagepairs, then train visual and tactile encoders to embed these pairs into ashared latent space using cross-modal contrastive loss. We apply this latentspace to downstream perception and control of deformable garments on flatsurfaces, and evaluate the flexibility of the learned representations withoutfine-tuning on 5 tasks: feature classification, contact localization, anomalydetection, feature search from a visual query (e.g., garment featurelocalization under occlusion), and edge following along cloth edges. Thepretrained representations achieve a 73-100% success rate on these 5 tasks.

Self-Supervised Visuo-Tactile Pretraining to Locate and Follow Garment Features