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

As robots become more widely available outside industrial settings, the needfor reliable object grasping and manipulation is increasing. In suchenvironments, robots must be able to grasp and manipulate novel objects invarious situations. This paper presents GraspCaps, a novel architecture basedon Capsule Networks for generating per-point 6D grasp configurations forfamiliar objects. GraspCaps extracts a rich feature vector of the objectspresent in the point cloud input, which is then used to generate per-pointgrasp vectors. This approach allows the network to learn specific graspingstrategies for each object category. In addition to GraspCaps, the paper alsopresents a method for generating a large object-grasping dataset usingsimulated annealing. The obtained dataset is then used to train the GraspCapsnetwork. Through extensive experiments, we evaluate the performance of theproposed approach, particularly in terms of the success rate of graspingfamiliar objects in challenging real and simulated scenarios. The experimentalresults showed that the overall object-grasping performance of the proposedapproach is significantly better than the selected baseline. This superiorperformance highlights the effectiveness of the GraspCaps in achievingsuccessful object grasping across various scenarios.

GraspCaps: A Capsule Network Approach for Familiar 6DoF Object Grasping