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

Object manipulation in cluttered scenes is a difficult and important problemin robotics. To efficiently manipulate objects, it is crucial to understandtheir surroundings, especially in cases where multiple objects are stacked oneon top of the other, preventing effective grasping. We here present DUQIM-Net,a decision-making approach for object manipulation in a setting of stackedobjects. In DUQIM-Net, the hierarchical stacking relationship is assessed usingAdj-Net, a model that leverages existing Transformer Encoder-Decoder objectdetectors by adding an adjacency head. The output of this headprobabilistically infers the underlying hierarchical structure of the objectsin the scene. We utilize the properties of the adjacency matrix in DUQIM-Net toperform decision making and assist with object-grasping tasks. Our experimentalresults show that Adj-Net surpasses the state-of-the-art in object-relationshipinference on the Visual Manipulation Relationship Dataset (VMRD), and thatDUQIM-Net outperforms comparable approaches in bin clearing tasks.

DUQIM-Net: Probabilistic Object Hierarchy Representation for Multi-View Manipulation