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

Manipulation relationship detection (MRD) aims to guide the robot to graspobjects in the right order, which is important to ensure the safety andreliability of grasping in object stacked scenes. Previous works infermanipulation relationship by deep neural network trained with data collectedfrom a predefined view, which has limitation in visual dislocation inunstructured environments. Multi-view data provide more comprehensiveinformation in space, while a challenge of multi-view MRD is domain shift. Inthis paper, we propose a novel multi-view fusion framework, namely multi-viewMRD network (MMRDN), which is trained by 2D and 3D multi-view data. We projectthe 2D data from different views into a common hidden space and fit theembeddings with a set of Von-Mises-Fisher distributions to learn the consistentrepresentations. Besides, taking advantage of position information within the3D data, we select a set of $K$ Maximum Vertical Neighbors (KMVN) points fromthe point cloud of each object pair, which encodes the relative position ofthese two objects. Finally, the features of multi-view 2D and 3D data areconcatenated to predict the pairwise relationship of objects. Experimentalresults on the challenging REGRAD dataset show that MMRDN outperforms thestate-of-the-art methods in multi-view MRD tasks. The results also demonstratethat our model trained by synthetic data is capable to transfer to real-worldscenarios.

MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes