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

We develop a real-time state estimation system to recover the pose andcontact formation of an object relative to its environment. In this paper, wefocus on the application of inserting an object picked by a suction cup into atight space, an enabling technology for robotic packaging.  We propose a framework that fuses force and visual sensing for improvedaccuracy and robustness. Visual sensing is versatile and non-intrusive, butsuffers from occlusions and limited accuracy, especially for tasks involvingcontact. Tactile sensing is local, but provides accuracy and robustness toocclusions. The proposed algorithm to fuse them is based on iSAM, an on-lineoptimization technique, which we use to incorporate kinematic measurements fromthe robot, contact geometry of the object and the container, and visualtracking. In this paper, we generalize previous results in planar settings to a3D task with more complex contact interactions. A key challenge in using forcesensing is that we do not observe contact point locations directly. We proposea data-driven method to infer the contact formation, which is then used inreal-time by the state estimator. We demonstrate and evaluate the algorithm ina setup instrumented to provide groundtruth.

Realtime State Estimation with Tactile and Visual Sensing for Inserting a Suction-held Object