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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Robotic manipulation of deformable 1D objects such as ropes, cables, andhoses is challenging due to the lack of high-fidelity analytic models and largeconfiguration spaces. Furthermore, learning end-to-end manipulation policiesdirectly from images and physical interaction requires significant time on arobot and can fail to generalize across tasks. We address these challengesusing interpretable deep visual representations for rope, extending recent workon dense object descriptors for robot manipulation. This facilitates the designof interpretable and transferable geometric policies built on top of thelearned representations, decoupling visual reasoning and control. We present anapproach that learns point-pair correspondences between initial and goal ropeconfigurations, which implicitly encodes geometric structure, entirely insimulation from synthetic depth images. We demonstrate that the learnedrepresentation -- dense depth object descriptors (DDODs) -- can be used tomanipulate a real rope into a variety of different arrangements either bylearning from demonstrations or using interpretable geometric policies. In 50trials of a knot-tying task with the ABB YuMi Robot, the system achieves a 66%knot-tying success rate from previously unseen configurations. Seehttps://tinyurl.com/rope-learning for supplementary material and videos.

Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data