DA2 Dataset: Toward Dexterity-Aware Dual-Arm Grasping

被引：8

作者：

Zhai, Guangyao ^{[1
]}

Zheng, Yu ^{[2
]}

Xu, Ziwei ^{[2
]}

Kong, Xin ^{[3
]}

Liu, Yong ^{[4
]}

Busam, Benjamin ^{[1
]}

Ren, Yi ^{[2
]}

Navab, Nassir ^{[1
,5
]}

Zhang, Zhengyou ^{[2
]}

机构：

[1] Tech Univ Munich, Chair Comp Aided Med Procedures & Augmented Real, D-80333 Munich, Germany

[2] Tencent, Tencent Robot X, Shenzhen 518000, Peoples R China

[3] Imperial Coll London, Dept Comp, London SW7 2BX, England

[4] Zhejiang Univ, Inst Cyber Syst & Control, Hangzhou 310027, Peoples R China

[5] Johns Hopkins Univ, Lab Computat Sensing & Robot, Baltimore, MD 21218 USA

来源：

IEEE ROBOTICS AND AUTOMATION LETTERS | 2022年 / 7卷 / 04期

关键词：

Perception for grasping and manipulation; dual-arm manipulation; deep learning in grasping and manipulation;

D O I：

10.1109/LRA.2022.3189959

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

In this paper, we introduce DA(2), the first large-scale dual-arm dexterity-aware dataset for the generation of optimal bimanual grasping pairs for arbitrary large objects. The dataset contains about 9 M pairs of parallel jaw grasps, generated from more than 6000 objects and each labeled with various grasp dexterity measures. In addition, we propose an end-to-end dual-arm grasp evaluation model trained on the rendered scenes from this dataset. We utilize the evaluation model as our baseline to show the value of this novel and nontrivial dataset by both online analysis and real robot experiments.

引用

页码：8941 / 8948

页数：8

共 43 条

[1] RGB-D Object Recognition and Grasp Detection Using Hierarchical Cascaded Forests [J].

Asif, Umar ;

Bennamoun, Mohammed ;

Sohel, Ferdous A. .

IEEE TRANSACTIONS ON ROBOTICS, 2017, 33 (03) :547-564

[2]

Asir U, 2018, PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P4875

[3]

Calli B, 2015, PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS (ICAR), P510, DOI 10.1109/ICAR.2015.7251504

[4] Real-World Multiobject, Multigrasp Detection [J].

Chu, Fu-Jen ;

Xu, Ruinian ;

Vela, Patricio A. .

IEEE ROBOTICS AND AUTOMATION LETTERS, 2018, 3 (04) :3355-3362

[5] Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis [J].

Dai, Angela ;

Qi, Charles Ruizhongtai ;

Niessner, Matthias .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :6545-6554

[6]

Depierre A, 2018, IEEE INT C INT ROBOT, P3511, DOI 10.1109/IROS.2018.8593950

[7]

Di Guo, 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA), P1609, DOI 10.1109/ICRA.2017.7989191

[8]

Eppner C., 2019, INT S ROBOT RES, P890

[9] ACRONYM: A Large-Scale Grasp Dataset Based on Simulation [J].

Eppner, Clemens ;

Mousavian, Arsalan ;

Fox, Dieter .

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, :6222-6227

[10] GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping [J].

Fang, Hao-Shu ;

Wang, Chenxi ;

Gou, Minghao ;

Lu, Cewu .

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :11441-11450

← 1 2 3 4 5 →