DGBench: An Open-Source, Reproducible Benchmark for Dynamic Grasping

被引:4
|
作者
Burgess-Limerick, Ben [1 ]
Lehnert, Chris [1 ]
Leitner, Jurgen [2 ]
Corke, Peter [1 ]
机构
[1] Queensland Univ Technol, Ctr Robot QCR, Brisbane, Qld, Australia
[2] LYRO Robot, Brisbane, Qld, Australia
关键词
Performance Evaluation and Benchmarking; Perception for Grasping and Manipulation; Grasping; OBJECT; VISION;
D O I
10.1109/IROS47612.2022.9981670
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper introduces DGBench, a fully reproducible open-source testing system to enable benchmarking of dynamic grasping in environments with unpredictable relative motion between robot and object. We use the proposed benchmark to compare several visual perception arrangements. Traditional perception systems developed for static grasping are unable to provide feedback during the final phase of a grasp due to sensor minimum range, occlusion, and a limited field of view. A multi-camera eye-in-hand perception system is presented that has advantages over commonly used camera configurations. We quantitatively evaluate the performance on a real robot with an image-based visual servoing grasp controller and show a significantly improved success rate on a dynamic grasping task.
引用
收藏
页码:3218 / 3224
页数:7
相关论文
共 50 条
  • [1] A Benchmark Open-Source Implementation of COSMO-SAC
    Bell, Ian H.
    Mickoleit, Erik
    Hsieh, Chieh-Ming
    Lin, Shiang-Tai
    Vrabec, Jadran
    Breitkopf, Cornelia
    Jaeger, Andreas
    JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2020, 16 (04) : 2635 - 2646
  • [2] μBench: An Open-Source Factory of Benchmark Microservice Applications
    Detti, Andrea
    Funari, Ludovico
    Petrucci, Luca
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 34 (03) : 968 - 980
  • [3] OpenCBS: An Open-Source COBOL Defects Benchmark Suite
    Lee, Dylan
    Henley, Austin Z.
    Hinshaw, Bill
    Pandita, Rahul
    2022 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE AND EVOLUTION (ICSME 2022), 2022, : 246 - 256
  • [4] ParMiBench - An Open-Source Benchmark for Embedded Multiprocessor Systems
    Iqbal, Syed Muhammad Zeeshan
    Liang, Yuchen
    Grahn, Hakan
    IEEE COMPUTER ARCHITECTURE LETTERS, 2010, 9 (02) : 45 - 48
  • [5] WorldCereal: a dynamic open-source system for global-scale, seasonal, and reproducible crop and irrigation mapping
    Van Tricht, Kristof
    Degerickx, Jeroen
    Gilliams, Sven
    Zanaga, Daniele
    Battude, Marjorie
    Grosu, Alex
    Brombacher, Joost
    Lesiv, Myroslava
    Bayas, Juan Carlos Laso
    Karanam, Santosh
    Fritz, Steffen
    Becker-Reshef, Inbal
    Franch, Belen
    Molla-Bononad, Bertran
    Boogaard, Hendrik
    Pratihast, Arun Kumar
    Koetz, Benjamin
    Szantoi, Zoltan
    EARTH SYSTEM SCIENCE DATA, 2023, 15 (12) : 5491 - 5515
  • [6] Open-source Defect Injection Benchmark Testbed for the Evaluation of Testing
    Bures, Miroslav
    Herout, Pavel
    Ahmed, Bestoun S.
    2020 IEEE 13TH INTERNATIONAL CONFERENCE ON SOFTWARE TESTING, VALIDATION AND VERIFICATION (ICST 2020), 2020, : 442 - 447
  • [7] BulletArm: An Open-Source Robotic Manipulation Benchmark and Learning Framework
    Wang, Dian
    Kohler, Colin
    Zhu, Xupeng
    Jia, Mingxi
    Platt, Robert
    ROBOTICS RESEARCH, ISRR 2022, 2023, 27 : 335 - 350
  • [8] Interactive and reproducible data analysis with the open-source KNIME Analytics Platform
    Landrum, Gregory
    ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2018, 255
  • [9] ClinicaDL: An open-source deep learning software for reproducible neuroimaging processing
    Thibeau-Sutre, Elina
    Diaz, Mauricio
    Hassanaly, Ravi
    Routier, Alexandre
    Dormont, Didier
    Colliot, Olivier
    Burgos, Ninon
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2022, 220
  • [10] Validation of kinfitr: An open-source tool for reproducible PET kinetic modelling
    Tjerkaski, Jonathan
    Cervenka, Simon
    Farde, Lars
    Matheson, Granville J.
    JOURNAL OF CEREBRAL BLOOD FLOW AND METABOLISM, 2021, 41 (1_SUPPL): : 258 - 260