Learning accurate and efficient three-finger grasp generation in clutters with an auto-annotated large-scale dataset

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: swepub > Learning accurate a...

Learning accurate and efficient three-finger grasp generation in clutters with an auto-annotated large-scale dataset

Zhou, Zhenning (författare): School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, PR China

Sun, Han (författare): School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, PR China

Wang, Xi Vincent, Dr. 1985- (författare): KTH,Produktionsutveckling

visa fler...

Zhang, Zhinan (författare): School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, PR China; State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, PR China

Cao, Qixin (författare): School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, PR China

visa färre...

(creator_code:org_t)

Elsevier BV, 2025
2025
Engelska.
Ingår i: Robotics and Computer-Integrated Manufacturing. - : Elsevier BV. - 0736-5845 .- 1879-2537. ; 91

Relaterad länk:: https://urn.kb.se/re...; visa fler...; https://doi.org/10.1...; visa färre...

Tidskriftsartikel (refereegranskat)

Abstract Ämnesord

Stäng

With the development of intelligent manufacturing and robotic technologies, the capability of grasping unknown objects in unstructured environments is becoming more prominent for robots with extensive applications. However, current robotic three-finger grasping studies only focus on grasp generation for single objects or scattered scenes, and suffer from high time expenditure to label grasp ground truth, making them incapable of predicting grasp poses for cluttered objects or generating large-scale datasets. To address such limitations, we first introduce a novel three-finger grasp representation with fewer prediction dimensions, which balances the training difficulty and representation accuracy to obtain efficient grasp performance. Based on this representation, we develop an auto-annotation pipeline and contribute a large-scale three-finger grasp dataset (TF-Grasp Dataset). Our dataset contains 222,720 RGB-D images with over 2 billion grasp annotations in cluttered scenes. In addition, we also propose a three-finger grasp pose detection network (TF-GPD), which detects globally while fine-tuning locally to predict high-quality collision-free grasps from a single-view point cloud. In sum, our work addresses the issue of high-quality collision-free three-finger grasp generation in cluttered scenes based on the proposed pipeline. Extensive comparative experiments show that our proposed methodology outperforms previous methods and improves the grasp quality and efficiency in clutters. The superior results in real-world robot grasping experiments not only prove the reliability of our grasp model but also pave the way for practical applications of three-finger grasping. Our dataset and source code will be released.

Ämnesord

TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)
ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)
NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)

Nyckelord

Deep learning and computer vision in grasp detection
Grasp dataset
Grasp representation
Robotic three-finger grasp generation

Publikations- och innehållstyp

ref (ämneskategori)
art (ämneskategori)

Hitta via bibliotek

Robotics and Computer-Integrated Manufacturing (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...: Zhou, Zhenning; Sun, Han; Wang, Xi Vincent ...; Zhang, Zhinan; Cao, Qixin

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Robotteknik och ...

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datorseende och ...

Artiklar i publikationen: Robotics and Com ...

Av lärosätet: Kungliga Tekniska Högskolan

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se