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

Tactile pose estimation and tactile servoing are fundamental capabilities ofrobot touch. Reliable and precise pose estimation can be provided by applyingdeep learning models to high-resolution optical tactile sensors. Given therecent successes of Graph Neural Network (GNN) and the effectiveness of Voronoifeatures, we developed a Tactile Voronoi Graph Neural Network (Tac-VGNN) toachieve reliable pose-based tactile servoing relying on a biomimetic opticaltactile sensor (TacTip). The GNN is well suited to modeling the distributionrelationship between shear motions of the tactile markers, while the Voronoidiagram supplements this with area-based tactile features related to contactdepth. The experiment results showed that the Tac-VGNN model can help enhancedata interpretability during graph generation and model training efficiencysignificantly than CNN-based methods. It also improved pose estimation accuracyalong vertical depth by 28.57% over vanilla GNN without Voronoi features andachieved better performance on the real surface following tasks with smootherrobot control trajectories. For more project details, please view our website:https://sites.google.com/view/tac-vgnn/home

Tac-VGNN: A Voronoi Graph Neural Network for Pose-Based Tactile Servoing