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

Target-oriented grasping in unstructured scenes with language control isessential for intelligent robot arm grasping. The ability for the robot arm tounderstand the human language and execute corresponding grasping actions is apivotal challenge. In this paper, we propose a combination model calledQwenGrasp which combines a large vision-language model with a 6-DoF graspneural network. QwenGrasp is able to conduct a 6-DoF grasping task on thetarget object with textual language instruction. We design a completeexperiment with six-dimension instructions to test the QwenGrasp when facingwith different cases. The results show that QwenGrasp has a superior ability tocomprehend the human intention. Even in the face of vague instructions withdescriptive words or instructions with direction information, the target objectcan be grasped accurately. When QwenGrasp accepts the instruction which is notfeasible or not relevant to the grasping task, our approach has the ability tosuspend the task execution and provide a proper feedback to humans, improvingthe safety. In conclusion, with the great power of large vision-language model,QwenGrasp can be applied in the open language environment to conduct thetarget-oriented grasping task with freely input instructions.

QwenGrasp: A Usage of Large Vision-Language Model for Target-Oriented Grasping