Robotic Grasping of Harvested Tomato Trusses Using Vision and Online Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F24%3A00375256" target="_blank" >RIV/68407700:21730/24:00375256 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICRA57147.2024.10610089" target="_blank" >https://doi.org/10.1109/ICRA57147.2024.10610089</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICRA57147.2024.10610089" target="_blank" >10.1109/ICRA57147.2024.10610089</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Robotic Grasping of Harvested Tomato Trusses Using Vision and Online Learning

Popis výsledku v původním jazyce

Currently, truss tomato weighing and packaging require significant manual work. The main obstacle to automation lies in the difficulty of developing a reliable robotic grasping system for already harvested trusses. We propose a method to grasp trusses that are stacked in a crate with considerable clutter, which is how they are commonly stored and transported after harvest. The method consists of a deep learning-based vision system to first identify the individual trusses in the crate and then determine a suitable grasping location on the stem. To this end, we have introduced a grasp pose ranking algorithm with online learning capabilities. After selecting the most promising grasp pose, the robot executes a pinch grasp without needing touch sensors or geometric models. Lab experiments with a robotic manipulator equipped with an eye-in-hand RGB-D camera showed a 100% clearance rate when tasked to pick all trusses from a pile. 93% of the trusses were successfully grasped on the first try, while the remaining 7% required more attempts.

Název v anglickém jazyce

Robotic Grasping of Harvested Tomato Trusses Using Vision and Online Learning

Popis výsledku anglicky

Currently, truss tomato weighing and packaging require significant manual work. The main obstacle to automation lies in the difficulty of developing a reliable robotic grasping system for already harvested trusses. We propose a method to grasp trusses that are stacked in a crate with considerable clutter, which is how they are commonly stored and transported after harvest. The method consists of a deep learning-based vision system to first identify the individual trusses in the crate and then determine a suitable grasping location on the stem. To this end, we have introduced a grasp pose ranking algorithm with online learning capabilities. After selecting the most promising grasp pose, the robot executes a pinch grasp without needing touch sensors or geometric models. Lab experiments with a robotic manipulator equipped with an eye-in-hand RGB-D camera showed a 100% clearance rate when tasked to pick all trusses from a pile. 93% of the trusses were successfully grasped on the first try, while the remaining 7% required more attempts.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotika a pokročilá průmyslová výroba</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 IEEE International Conference on Robotics and Automation (ICRA)

ISBN

979-8-3503-8457-4

ISSN

1050-4729

e-ISSN

2577-087X

Počet stran výsledku

7

Strana od-do

13947-13953

Název nakladatele

IEEE Industrial Electronic Society

Místo vydání

Vienna

Místo konání akce

Yokohama

Datum konání akce

13. 5. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001369728003111