{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T06:01:20Z","timestamp":1790834480664,"version":"4.1.0"},"reference-count":56,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop an edge-deployable greenhouse tomato cluster harvesting robot capable of accurate fruit detection, three-dimensional localization, autonomous navigation, and robotic harvesting under complex greenhouse conditions. The objective was to improve detection performance under fruit occlusion and variable illumination while maintaining real-time inference and stable robotic operation on embedded computing hardware.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A lightweight YOLOv8n-based tomato detection model, termed YOLOv8n-BiFPN-WIoU, was developed by incorporating a bidirectional feature pyramid network and Wise-IoU loss to improve multiscale feature fusion and localization accuracy. An RGB-D vision system based on the Intel RealSense D435 was used for three-dimensional fruit localization. The robotic system integrated a rail-guided mobile platform, a six-axis manipulator, a dual-claw harvesting end-effector, and a ROS-based distributed control architecture. The vision model was optimized and deployed on an NVIDIA Jetson Nano using ONNX and TensorRT. Robot kinematics, hand-eye transformation, trajectory planning, and autonomous harvesting procedures were integrated to enable station-to-station operation and fruit harvesting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed YOLOv8n-BiFPN-WIoU model achieved a precision of 88.534%, recall of 89.377%, F1-score of 88.954%, mAP@0.5 of 92.338%, and mAP@0.5:0.95 of 71.368%. Compared with the baseline YOLOv8n model, these metrics improved by 2.143, 2.779, 2.460, 4.587, and 5.675 percentage points, respectively. The proposed model increased the parameter count from 3.2 million to 3.6 million and computational complexity from 19.6 to 22.4 GFLOPs. After ONNX and TensorRT optimization, the model achieved an inference speed of 21.1 frames per second at an input resolution of 640 \u00d7 640 with batch size 1 on the Jetson Nano. The robotic system achieved a mean positioning error of 3.70 \u00b1 0.32 mm across five representative targets, demonstrating the feasibility of accurate visual localization and robotic positioning for greenhouse tomato harvesting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed edge-deployable greenhouse tomato cluster harvesting robot integrates lightweight deep learning, RGB-D three-dimensional localization, ROS-based autonomous control, rail-guided mobile operation, and robotic harvesting into a unified system. The YOLOv8n-BiFPN-WIoU model improved tomato detection performance while maintaining real-time inference on embedded hardware, and the integrated vision and manipulation system demonstrated accurate positioning suitable for autonomous harvesting. The results indicate that the proposed architecture provides a practical foundation for intelligent greenhouse tomato harvesting under complex visual and operational conditions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1926482","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:40:28Z","timestamp":1790833228000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Edge-deployable greenhouse tomato cluster harvesting robot integrating YOLOv8n-BiFPN-WIoU and ROS-based autonomous control"],"prefix":"10.3389","volume":"17","author":[{"given":"Fanzhao","family":"Meng","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Advanced Manufacturing, Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Li","sequence":"additional","affiliation":[{"name":"Shandong Shansu Robot Technology Co., Ltd.","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xizhen","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningrong","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongpo","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Shandong Huayu University of Technology","place":["Dezhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunqi","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Materials and Chemical Engineering, Hunan Institute of Technology","place":["Hengyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"B26","doi-asserted-by":"publisher","first-page":"4841","DOI":"10.1007\/s12008-024-01774-6","article-title":"Sensor fusion based multiple robot navigation in an indoor environment","volume":"18","author":"Arpitha Shankar","year":"2024","journal-title":"Int. J. Interactive Design Manufacturing (IJIDeM)"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112261","article-title":"Development and implementation of a hybrid visual prediction algorithm for robotic smart tomato harvesting","volume":"161","author":"Carbone","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B18","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.biosystemseng.2024.04.017","article-title":"3D pose estimation of tomato peduncle nodes using deep keypoint detection and point cloud","volume":"243","author":"Ci","year":"2024","journal-title":"Biosyst. Eng."},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1748741","article-title":"TRD-Net: an efficient tomato ripeness detection network based on improved YOLO v8 for selective harvesting","volume":"17","author":"Fan","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/j.biosystemseng.2026.104568","article-title":"Lateral and longitudinal tracking control of tracked orchard transport vehicles based on adaptive MPC","volume":"271","author":"Feng","year":"2026","journal-title":"Biosyst. Eng."},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1447263","article-title":"Multi-stage tomato fruit recognition method based on improved YOLOv8","volume":"15","author":"Fu","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.106879","article-title":"Development and evaluation of a pneumatic finger-like end-effector for cherry tomato harvesting robot in greenhouse","volume":"197","author":"Gao","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B1","doi-asserted-by":"publisher","first-page":"2715","DOI":"10.1007\/s11694-023-02349-x","article-title":"Tomato ripeness and shelf-life prediction system using machine learning","volume":"18","author":"Goyal","year":"2024","journal-title":"J. Food Meas. Charact."},{"key":"B34","doi-asserted-by":"publisher","first-page":"110125","DOI":"10.1016\/j.compag.2025.110125","article-title":"Research on multi-layer model attitude recognition and picking strategy of a small tomato picking robot","volume":"232","author":"Hou","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109520","article-title":"Excellent tomato detector based on pruning and distillation to balance accuracy and lightweight","volume":"227","author":"Huang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1596739","article-title":"AITP-YOLO: Improved tomato ripeness detection model based on multiple strategies","volume":"16","author":"Huang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B4","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1007\/s41315-024-00350-1","article-title":"ROS-based multi-sensor integrated localization system for cost-effective and accurate indoor navigation system","volume":"9","author":"Irwansyah","year":"2025","journal-title":"Int. J. Intell. Rob. Appl."},{"key":"B11","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.biosystemseng.2025.01.007","article-title":"Maturity recognition and localisation of broccoli under occlusion based on RGB-D instance segmentation network","volume":"250","author":"Kang","year":"2025","journal-title":"Biosyst. Eng."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108633","article-title":"Maturity identification and category determination method of broccoli based on semantic segmentation models","volume":"217","author":"Kang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.111007","article-title":"Time-optimal and path-optimal motion planning for selective broccoli harvesting manipulator","volume":"239","author":"Kang","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109654","article-title":"Design, integration, and field evaluation of a selective harvesting robot for broccoli","volume":"227","author":"Kang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B53","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1007\/s10462-025-11327-2","article-title":"Fault-tolerant control strategies for industrial robots: state of the art and future perspective on AI-based fault management","volume":"58","author":"Khan","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108004","article-title":"2D pose estimation of multiple tomato fruit-bearing systems for robotic harvesting","volume":"211","author":"Kim","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3390\/horticulturae11080949","article-title":"Cherry tomato bunch and picking point detection for robotic harvesting using an RGB-D sensor and a StarBL-YOLO network","volume":"11","author":"Li","year":"2025","journal-title":"Horticulturae"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cropro.2025.107215","article-title":"Model and experiment of target-specific variable spraying based on canopy volume perception","volume":"194","author":"Liu","year":"2025","journal-title":"Crop Prot."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.70460","article-title":"YOLOv8n\u2010SLW: A lightweight ripe yellow peach detection algorithm","volume":"38","author":"Liu","year":"2025","journal-title":"Concurrency Computation: Pract. Exp."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109118","article-title":"Faster-YOLO-AP: A lightweight apple detection algorithm based on improved YOLOv8 with a new efficient PDWConv in orchard","volume":"223","author":"Liu","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B8","doi-asserted-by":"publisher","first-page":"015219","DOI":"10.1088\/2631-8695\/ada720","article-title":"Deep learning-based real-time detection and classification of tomato ripeness stages using YOLOv8 on raspberry Pi","volume":"7","author":"Nahiduzzaman","year":"2025","journal-title":"Eng. Res. Express"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2023.1330496","article-title":"Soft gripper for small fruits harvesting and pick and place operations","volume":"10","author":"Navas","year":"2024","journal-title":"Front. Rob. AI"},{"key":"B38","doi-asserted-by":"publisher","first-page":"353","DOI":"10.3390\/pr13020353","article-title":"Development of an optimized YOLO-PP-based cherry tomato detection system for autonomous precision harvesting","volume":"13","author":"Qin","year":"2025","journal-title":"Processes"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1002\/rob.22230","article-title":"Towards autonomous selective harvesting: A review of robot perception, robot design, motion planning and control","volume":"41","author":"Rajendran","year":"2024","journal-title":"J. Field Rob."},{"key":"B48","doi-asserted-by":"publisher","first-page":"374","DOI":"10.6041\/j.issn.1000-1298.2025.03.037","article-title":"Improved YOLO v8n network for real-time detection of tomato maturity","volume":"56","author":"Ren","year":"2025","journal-title":"Trans. Chin. Soc. For. Agric. Machinery"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2955","DOI":"10.1007\/s40747-021-00522-7","article-title":"A peduncle detection method of tomato for autonomous harvesting","volume":"8","author":"Rong","year":"2022","journal-title":"Complex Intelligent Syst."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107741","article-title":"Tomato cluster detection and counting using improved YOLOv5 based on RGB-D fusion","volume":"207","author":"Rong","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B23","doi-asserted-by":"publisher","first-page":"27","DOI":"10.2174\/0122127976326652241018114550","article-title":"Research progress on industrial robots: A review","volume":"19","author":"Shinde","year":"2026","journal-title":"Recent Pat Mech Eng"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1771732","article-title":"YOLOv8-PnP fusion architecture for non-contact robotic pollination: A 6D pose estimation approach for autonomous greenhouse operations","volume":"17","author":"Singh","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B27","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1109\/ACCESS.2024.3520233","article-title":"A deep learning-based approach to strawberry grasping using a telescopic-link differential drive mobile robot in ros-gazebo for greenhouse digital twin environments","volume":"13","author":"Singh","year":"2024","journal-title":"IEEE Access"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3390\/s24206628","article-title":"Prototype of a new head grabber for robotic strawberry harvesting with a vision system","volume":"24","author":"Sobol","year":"2024","journal-title":"Sensors"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2885","DOI":"10.3390\/su17072885","article-title":"Research on high-precision target detection technology for tomato-picking robots in sustainable agriculture","volume":"17","author":"Song","year":"2025","journal-title":"Sustainability"},{"key":"B28","doi-asserted-by":"publisher","first-page":"427","DOI":"10.11922\/11-6035.nasdc.2022.0020.zh","article-title":"A dataset of greenhouse cluster tomato fruit in the Tomato Town of Jinzhong National Agricultural High-tech Industries Demonstration Zone in 2022","volume":"8","author":"Song","year":"2023","journal-title":"China Sci. Data"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1447855","article-title":"Study on the fusion of improved YOLOv8 and depth camera for bunch tomato stem picking point recognition and localization","volume":"15","author":"Song","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1451018","article-title":"Enhanced tomato detection in greenhouse environments: A lightweight model based on S-YOLO with high accuracy","volume":"15","author":"Sun","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"Terven","year":"2023","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"B52","doi-asserted-by":"publisher","first-page":"177","DOI":"10.3390\/act14040177","article-title":"Hybrid fault-tolerant control in cooperative robotics: advances in resilience and scalability","volume":"14","author":"Urrea","year":"2025","journal-title":"Actuators"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy13030947","article-title":"Design and testing of an end-effector for tomato picking","volume":"13","author":"Wang","year":"2023","journal-title":"Agronomy"},{"key":"B24","doi-asserted-by":"publisher","first-page":"177","DOI":"10.2174\/2212797616666230417104506","article-title":"Obstacle avoidance path planning of 7-DOF redundant manipulator based on improved ant colony optimization","volume":"16","author":"Wang","year":"2023","journal-title":"Recent Pat. Mech. Eng."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1656381","article-title":"YOLOv8-LBP: Multi-scale attention enhanced YOLOv8 for ripe tomato detection and harvesting keypoint localization","volume":"16","author":"Wang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2025.101465","article-title":"GCD-YOLO: A deep learning network for accurate tomato fruit stalks identification in unstructured environments","volume":"12","author":"Weng","year":"2025","journal-title":"Smart Agric. Technol."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.foodcont.2026.112044","article-title":"A lightweight network for non-destructive and precise prediction of loquat bruising volume based on RGB images","volume":"184","author":"Xu","year":"2026","journal-title":"Food Control"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.postharvbio.2023.112565","article-title":"Prediction of bruising susceptibility in white radish (Raphanus sativus L.) using FEA-RSM technique","volume":"206","author":"Xu","year":"2023","journal-title":"Postharvest Biol. Technol."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1080\/10589759.2026.2653119","article-title":"Accurate infrared interferometric thickness measurement of silicon carbide epitaxial layers using dynamic refractive index correction","author":"Yang","year":"2026","journal-title":"Nondestr Test Eval"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy13071824","article-title":"A lightweight YOLOv8 tomato detection algorithm combining feature enhancement and attention","volume":"13","author":"Yang","year":"2023","journal-title":"Agronomy"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1786144","article-title":"Tea bud pose estimation and grading detection network based on improved YOLOv7","volume":"17","author":"Yao","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"247","DOI":"10.25165\/j.ijabe.20251803.8954","article-title":"Key technologies of tomato-picking robots based on machine vision","volume":"18","author":"Yin","year":"2025","journal-title":"Int. J. Agric. Biol. Eng."},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107878","article-title":"TPMv2: An end-to-end tomato pose method based on 3D key points detection","volume":"210","author":"Zhang","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1747863","article-title":"Real-time on-device weed identification using a hardware-efficient lightweight CNN","volume":"17","author":"Zhang","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1468188","article-title":"An improved YOLOv8n-IRP model for natural rubber tree tapping surface detection and tapping key point positioning","volume":"15","author":"Zhang","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.3390\/s25061716","article-title":"Fault types and diagnostic methods of manipulator robots: a review","volume":"25","author":"Zhang","year":"2025","journal-title":"Sensors"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108519","article-title":"Greenhouse tomato detection and pose classification algorithm based on improved YOLOv5","volume":"216","author":"Zhang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1618214","article-title":"Ta-YOLO: Overcoming target blocked challenges in greenhouse tomato detection and counting","volume":"16","author":"Zhao","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14081764","article-title":"Tomato recognition method based on the YOLOv8-Tomato model in complex greenhouse environments","volume":"14","author":"Zheng","year":"2024","journal-title":"Agronomy"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1926482\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:40:31Z","timestamp":1790833231000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1926482\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":56,"alternative-id":["10.3389\/fpls.2026.1926482"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1926482","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"article-number":"1926482"}}