Apple-Harvesting Robot Based on the YOLOv5-RACF Model.

Abstract

To address the issue of automated apple harvesting in orchards, we propose a YOLOv5-RACF algorithm for identifying apples and calculating apple diameters. This algorithm employs the robot operating dystem (ROS) to control the robot's locomotion system, Lidar mapping, and navigation, as well as the robotic arm's posture and grasping operations, achieving automated apple harvesting and placement. The tests were conducted in an actual orchard environment. The algorithm model achieved an average apple detection accuracy (mAP@0.5) of 98.748% and a (mAP@0.5:0.95) of 90.02%. The time to calculate the diameter of one apple was 0.13 s, with a measurement accuracy within an error range of 1-3 mm. The robot takes an average of 9 s to pick an apple and return to the initial pose. These results demonstrate the system's efficiency and reliability in real agricultural environments.

Plant phenotyping relevance

リンゴ収穫ロボットを主目的とするが、画像からリンゴ径を算出する手法を開発・評価しており、収穫対象の単なる検出を超えた再利用可能な果実形質推定が中心的に含まれる。

Code and data availability

The supplied blocks describe an apple-harvesting robot with a YOLOv5-RACF model, a custom apple image dataset (3070 original images from online sources and Jilin Agricultural University orchard), and ROS-based navigation/grasping experiments. However, no block contains any data availability statement, public repository

No evidence-backed public reproduction asset is currently recorded.