Design of and Experiment with a Dual-Arm Apple Harvesting Robot System

Robotic harvesting has become an urgent need for the development of the apple industry, due to the sharp decline in agricultural labor. At present, harvesting apples using robots in unstructured orchard environments remains a significant challenge. This paper focuses on addressing the challenges of...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenlei Huang, Zhonghua Miao, Tao Wu, Zhengwei Guo, Wenkai Han, Tao Li
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Horticulturae
Subjects:
Online Access:https://www.mdpi.com/2311-7524/10/12/1268
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104454771769344
author Wenlei Huang
Zhonghua Miao
Tao Wu
Zhengwei Guo
Wenkai Han
Tao Li
author_facet Wenlei Huang
Zhonghua Miao
Tao Wu
Zhengwei Guo
Wenkai Han
Tao Li
author_sort Wenlei Huang
collection DOAJ
description Robotic harvesting has become an urgent need for the development of the apple industry, due to the sharp decline in agricultural labor. At present, harvesting apples using robots in unstructured orchard environments remains a significant challenge. This paper focuses on addressing the challenges of perception, localization, and dual-arm coordination in harvesting robots and presents a dual-arm apple harvesting robot system. First, the paper introduces the integration of the robot’s hardware and software systems, as well as the control system architecture, and describes the robot’s workflow. Secondly, combining a dual-vision perception system, the paper adopts a fruit recognition method based on a multi-task network model and a frustum-based fruit localization approach to identify and localize fruits. Finally, to improve collaboration efficiency, a multi-arm task planning method based on a genetic algorithm is used to optimize the target harvesting sequence for each arm. Field experiments were conducted in an orchard to evaluate the overall performance of the robot system. The field trials demonstrated that the robot system achieved an overall harvest success rate of 76.97%, with an average fruit picking time of 7.29 s per fruit and a fruit damage rate of only 5.56%.
format Article
id doaj-art-c5f87b7dfd41452cbf0bca6939c98beb
institution Kabale University
issn 2311-7524
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Horticulturae
spelling doaj-art-c5f87b7dfd41452cbf0bca6939c98beb2024-12-27T14:29:05ZengMDPI AGHorticulturae2311-75242024-11-011012126810.3390/horticulturae10121268Design of and Experiment with a Dual-Arm Apple Harvesting Robot SystemWenlei Huang0Zhonghua Miao1Tao Wu2Zhengwei Guo3Wenkai Han4Tao Li5School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaSchool of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaIntelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaRobotic harvesting has become an urgent need for the development of the apple industry, due to the sharp decline in agricultural labor. At present, harvesting apples using robots in unstructured orchard environments remains a significant challenge. This paper focuses on addressing the challenges of perception, localization, and dual-arm coordination in harvesting robots and presents a dual-arm apple harvesting robot system. First, the paper introduces the integration of the robot’s hardware and software systems, as well as the control system architecture, and describes the robot’s workflow. Secondly, combining a dual-vision perception system, the paper adopts a fruit recognition method based on a multi-task network model and a frustum-based fruit localization approach to identify and localize fruits. Finally, to improve collaboration efficiency, a multi-arm task planning method based on a genetic algorithm is used to optimize the target harvesting sequence for each arm. Field experiments were conducted in an orchard to evaluate the overall performance of the robot system. The field trials demonstrated that the robot system achieved an overall harvest success rate of 76.97%, with an average fruit picking time of 7.29 s per fruit and a fruit damage rate of only 5.56%.https://www.mdpi.com/2311-7524/10/12/1268applesharvesting robottarget perceptiondual-arm coordinationfield trials
spellingShingle Wenlei Huang
Zhonghua Miao
Tao Wu
Zhengwei Guo
Wenkai Han
Tao Li
Design of and Experiment with a Dual-Arm Apple Harvesting Robot System
Horticulturae
apples
harvesting robot
target perception
dual-arm coordination
field trials
title Design of and Experiment with a Dual-Arm Apple Harvesting Robot System
title_full Design of and Experiment with a Dual-Arm Apple Harvesting Robot System
title_fullStr Design of and Experiment with a Dual-Arm Apple Harvesting Robot System
title_full_unstemmed Design of and Experiment with a Dual-Arm Apple Harvesting Robot System
title_short Design of and Experiment with a Dual-Arm Apple Harvesting Robot System
title_sort design of and experiment with a dual arm apple harvesting robot system
topic apples
harvesting robot
target perception
dual-arm coordination
field trials
url https://www.mdpi.com/2311-7524/10/12/1268
work_keys_str_mv AT wenleihuang designofandexperimentwithadualarmappleharvestingrobotsystem
AT zhonghuamiao designofandexperimentwithadualarmappleharvestingrobotsystem
AT taowu designofandexperimentwithadualarmappleharvestingrobotsystem
AT zhengweiguo designofandexperimentwithadualarmappleharvestingrobotsystem
AT wenkaihan designofandexperimentwithadualarmappleharvestingrobotsystem
AT taoli designofandexperimentwithadualarmappleharvestingrobotsystem