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

In this paper, we address the problem of using visuo-tactile feedback for6-DoF localization and 3D reconstruction of unknown in-hand objects. We proposeFingerSLAM, a closed-loop factor graph-based pose estimator that combines localtactile sensing at finger-tip and global vision sensing from a wrist-mountcamera. FingerSLAM is constructed with two constituent pose estimators: amulti-pass refined tactile-based pose estimator that captures movements fromdetailed local textures, and a single-pass vision-based pose estimator thatpredicts from a global view of the object. We also design a loop closuremechanism that actively matches current vision and tactile images to previouslystored key-frames to reduce accumulated error. FingerSLAM incorporates the twosensing modalities of tactile and vision, as well as the loop closure mechanismwith a factor graph-based optimization framework. Such a framework produces anoptimized pose estimation solution that is more accurate than the standaloneestimators. The estimated poses are then used to reconstruct the shape of theunknown object incrementally by stitching the local point clouds recovered fromtactile images. We train our system on real-world data collected with 20objects. We demonstrate reliable visuo-tactile pose estimation and shapereconstruction through quantitative and qualitative real-world evaluations on 6objects that are unseen during training.

FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback