Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking Tasks

被引:0
|
作者
Alterani, Alessio Benito [1 ]
Costanzo, Marco [1 ]
De Simone, Marco [1 ]
Federico, Sara [1 ]
Natale, Ciro [1 ]
机构
[1] Univ Campania Luigi Vanvitelli, Dipartimento Ingn, Via Roma 29, I-81031 Aversa, CE, Italy
关键词
pose estimation; robotic grasping; deep learning;
D O I
10.3390/robotics13090127
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
This paper presents an experimental comparison between two existing methods representative of two categories of 6D pose estimation algorithms nowadays commonly used in the robotics community. The first category includes purely deep learning methods, while the second one includes hybrid approaches combining learning pipelines and geometric reasoning. The hybrid method considered in this paper is a pipeline of an instance-level deep neural network based on RGB data only and a geometric pose refinement algorithm based on the availability of the depth map and the CAD model of the target object. Such a method can handle objects whose dimensions differ from those of the CAD. The pure learning method considered in this comparison is DenseFusion, a consolidated state-of-the-art pose estimation algorithm selected because it uses the same input data, namely, RGB image and depth map. The comparison is carried out by testing the success rate of fresh food pick-and-place operations. The fruit-picking scenario has been selected for the comparison because it is challenging due to the high variability of object instances in appearance and dimensions. The experiments carried out with apples and limes show that the hybrid method outperforms the pure learning one in terms of accuracy, thus allowing the pick-and-place operation of fruits with a higher success rate. An extensive discussion is also presented to help the robotics community select the category of 6D pose estimation algorithms most suitable to the specific application.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] A novel metric for 6D pose estimation
    Niedermaier, Tobias
    Berens, Felix
    Reischl, Markus
    Elser, Stefan
    AT-AUTOMATISIERUNGSTECHNIK, 2025, 73 (02) : 125 - 135
  • [22] 6D Robotic Assembly Based on RGB-only Object Pose Estimation
    Fu, Bowen
    Leong, Sek Kun
    Lian, Xiaocong
    Ji, Xiangyang
    2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2022, : 4736 - 4742
  • [23] Object Detection and 6D Pose Estimation for Precise Robotic Manipulation in Unstructured Environments
    di Castro, Mario
    Camarero Vera, Jorge
    Ferre, Manuel
    Masi, Alessandro
    INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, ICINCO 2017, 2020, 495 : 392 - 403
  • [24] Large-scale 6D Object Pose Estimation Dataset for Industrial Bin-Picking
    Kleeberger, Kilian
    Landgraf, Christian
    Huber, Marco F.
    2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 2573 - 2578
  • [25] OBJECT DETECTION AND AUTOENCODER-BASED 6D POSE ESTIMATION FOR HIGHLY CLUTTERED BIN PICKING
    Hoefer, Timon
    Shamsafar, Faranak
    Benbarka, Nuri
    Zell, Andreas
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 704 - 708
  • [26] 6D pose estimation of textureless shiny objects using random ferns for bin-picking
    Rodrigues, Jose Jeronimo
    Kim, Jun-Sik
    Furukawa, Makoto
    Xavier, Joao
    Aguiar, Pedro
    Kanade, Takeo
    2012 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2012, : 3334 - 3341
  • [27] Single Shot 6D Object Pose Estimation
    Kleeberger, Kilian
    Huber, Marco F.
    2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2020, : 6239 - 6245
  • [28] BOP: Benchmark for 6D Object Pose Estimation
    Hodan, Tomas
    Michel, Frank
    Brachmann, Eric
    Kehl, Wadim
    Buch, Anders Glent
    Kraft, Dirk
    Drost, Bertram
    Vidal, Joel
    Ihrke, Stephan
    Zabulis, Xenophon
    Sahin, Caner
    Manhardt, Fabian
    Tombari, Federico
    Kim, Tae-Kyun
    Matas, Jiri
    Rother, Carsten
    COMPUTER VISION - ECCV 2018, PT X, 2018, 11214 : 19 - 35
  • [29] dVPose: Automated Data Collection and Dataset for 6D Pose Estimation of Robotic Surgical Instruments
    Greene, Nicholas
    Luo, Wenkai
    Kazanzides, Peter
    2023 INTERNATIONAL SYMPOSIUM ON MEDICAL ROBOTICS, ISMR, 2023,
  • [30] 6D Pose Estimation of Transparent Object From Single RGB Image for Robotic Manipulation
    Byambaa, Munkhtulga
    Koutaki, Gou
    Choimaa, Lodoiravsal
    IEEE ACCESS, 2022, 10 : 114897 - 114906