Development of a Harvesting Robot for Use in Soilless Greenhouses

DOI

10.2991/978-94-6239-666-1_2How to use a DOI?

Keywords

Harvest; Greenhouse; Artificial Intelligence; Robotic

Abstract

This study aims to achieve fully autonomous fruit harvesting in greenhouses utilizing soilless agriculture by integrating artificial intelligence (AI)-driven deep learning algorithms and robotic arm systems. Based on a comprehensive literature review, a conceptual model has been proposed featuring an articulated harvesting arm mounted on a mobile platform. The system employs depth-sensing vision sensors and advanced object recognition algorithms (e.g., YOLO, Faster R-CNN) to detect fruits and extract their three-dimensional positional data. Using inverse kinematics and robot control algorithms, the robotic arm is guided to the target location and performs harvesting according to the fruit’s ripeness level and optimal detachment point. The mechanical design incorporates adaptable gripper-cutter mechanisms to prevent fruit damage during the harvesting process. According to data from related studies, fruit detection accuracy typically ranges from 88% to 95%, while harvesting success rates vary between 80% and 100%. The average picking time per fruit ranges from 3 to 15 seconds, depending on the crop type and system specifications. Deep learning-based approaches have demonstrated high accuracy in both fruit detection and ripeness classification, while developments in adaptive end-effectors have significantly improved harvesting efficiency in robotic arms. This technical study explores the feasibility, constraints, and performance metrics of autonomous harvesting technologies in hydroponic greenhouses. It highlights the synergy between AI-based perception and precise mechanical actuation, offering insights into the integration of computer vision, robotics, and agronomic parameters in modern agriculture. By addressing both algorithmic precision and mechanical adaptability, this research contributes to the development of intelligent and scalable solutions for high-throughput and labor-efficient harvesting in controlled-environment agriculture.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Bahadır Demirel
AU  - Osman Mert Yaz
AU  - Gürkan Alp Kağan Gürdil
PY  - 2026
DA  - 2026/05/07
TI  - Development of a Harvesting Robot for Use in Soilless Greenhouses
BT  - Proceedings of the 5th International Conference on Research of Agricultural and Food Technologies (I-CRAFT 2025)
PB  - Atlantis Press
SP  - 7
EP  - 19
SN  - 3005-155X
UR  - https://doi.org/10.2991/978-94-6239-666-1_2
DO  - 10.2991/978-94-6239-666-1_2
ID  - Demirel2026
ER  -