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

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 co...

Full description

Saved in:
Bibliographic Details
Main Authors: Alessio Benito Alterani, Marco Costanzo, Marco De Simone, Sara Federico, Ciro Natale
Format: Article
Language:English
Published: MDPI AG 2024-08-01
Series:Robotics
Subjects:
Online Access:https://www.mdpi.com/2218-6581/13/9/127
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259715609591808
author Alessio Benito Alterani
Marco Costanzo
Marco De Simone
Sara Federico
Ciro Natale
author_facet Alessio Benito Alterani
Marco Costanzo
Marco De Simone
Sara Federico
Ciro Natale
author_sort Alessio Benito Alterani
collection DOAJ
description 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.
format Article
id doaj-art-5b36fc0ba5044130a75d8bc45adce3de
institution OA Journals
issn 2218-6581
language English
publishDate 2024-08-01
publisher MDPI AG
record_format Article
series Robotics
spelling doaj-art-5b36fc0ba5044130a75d8bc45adce3de2025-08-20T01:55:49ZengMDPI AGRobotics2218-65812024-08-0113912710.3390/robotics13090127Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking TasksAlessio Benito Alterani0Marco Costanzo1Marco De Simone2Sara Federico3Ciro Natale4Dipartimento di Ingegneria, Università degli Studi della Campania Luigi Vanvitelli, Via Roma, 29, 81031 Aversa, CE, ItalyDipartimento di Ingegneria, Università degli Studi della Campania Luigi Vanvitelli, Via Roma, 29, 81031 Aversa, CE, ItalyDipartimento di Ingegneria, Università degli Studi della Campania Luigi Vanvitelli, Via Roma, 29, 81031 Aversa, CE, ItalyDipartimento di Ingegneria, Università degli Studi della Campania Luigi Vanvitelli, Via Roma, 29, 81031 Aversa, CE, ItalyDipartimento di Ingegneria, Università degli Studi della Campania Luigi Vanvitelli, Via Roma, 29, 81031 Aversa, CE, ItalyThis 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.https://www.mdpi.com/2218-6581/13/9/127pose estimationrobotic graspingdeep learning
spellingShingle Alessio Benito Alterani
Marco Costanzo
Marco De Simone
Sara Federico
Ciro Natale
Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking Tasks
Robotics
pose estimation
robotic grasping
deep learning
title Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking Tasks
title_full Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking Tasks
title_fullStr Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking Tasks
title_full_unstemmed Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking Tasks
title_short Experimental Comparison of Two 6D Pose Estimation Algorithms in Robotic Fruit-Picking Tasks
title_sort experimental comparison of two 6d pose estimation algorithms in robotic fruit picking tasks
topic pose estimation
robotic grasping
deep learning
url https://www.mdpi.com/2218-6581/13/9/127
work_keys_str_mv AT alessiobenitoalterani experimentalcomparisonoftwo6dposeestimationalgorithmsinroboticfruitpickingtasks
AT marcocostanzo experimentalcomparisonoftwo6dposeestimationalgorithmsinroboticfruitpickingtasks
AT marcodesimone experimentalcomparisonoftwo6dposeestimationalgorithmsinroboticfruitpickingtasks
AT sarafederico experimentalcomparisonoftwo6dposeestimationalgorithmsinroboticfruitpickingtasks
AT cironatale experimentalcomparisonoftwo6dposeestimationalgorithmsinroboticfruitpickingtasks