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

Aiming at the traditional grasping method for manipulators based on 2Dcamera, when faced with the scene of gathering or covering, it can hardlyperform well in unstructured scenes that appear as gathering and covering, forthe reason that can't recognize objects accurately in cluster scenes from asingle perspective and the manipulators can't make the environment better forgrasping. In this case, a novel method of pushing-grasping collaborative basedon the deep Q-network in dual perspectives is proposed in this paper. Thismethod adopts an improved deep Q network algorithm, with an RGB-D camera toobtain the information of objects' RGB images and point clouds from twoperspectives, and combines the pushing and grasping actions so that the trainedmanipulator can make the scenes better for grasping so that it can perform wellin more complicated grasping scenes. What's more, we improved the rewardfunction of the deep Q-network and propose the piecewise reward function tospeed up the convergence of the deep Q-network. We trained different models andtried different methods in the V-REP simulation environment, and it concludedthat the method proposed in this paper converges quickly and the success rateof grasping objects in unstructured scenes raises up to 83.5%. Besides, itshows the generalization ability and well performance when novel objects appearin the scenes that the manipulator has never grasped before.

A Pushing-Grasping Collaborative Method Based on Deep Q-Network Algorithm in Dual Perspectives