Design of Autonomous Driving Algorithms for Fruit harvesting in orchards

Lee, Hea-Min; Noh, Dong-Hee; Kang, Hyungu; Byun, Sung-Woo; Choi, Joo-Ho

doi:10.1109/icufn55119.2022.9829690

Cited by 3 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The robotic weeder can recognize the remaining weeds in an orchard and can be designed to move toward the location of the weeds. Even for mature trees without structural support, such as poles, diameter information is used to guide the tree-oriented circular movement of robot weeders in interrow areas [38]. Figure 10 shows examples of segmentation objects obtained using custom-trained YOLOv8n-seg, with the confidence set at 0.25.…”

Section: Discussionmentioning

confidence: 99%

Intrarow Uncut Weed Detection Using You-Only-Look-Once Instance Segmentation for Orchard Plantations

Sampurno,

Liu,

Abeyrathna

et al. 2024

Sensors

View full text Add to dashboard Cite

Mechanical weed management is a drudging task that requires manpower and has risks when conducted within rows of orchards. However, intrarow weeding must still be conducted by manual labor due to the restricted movements of riding mowers within the rows of orchards due to their confined structures with nets and poles. However, autonomous robotic weeders still face challenges identifying uncut weeds due to the obstruction of Global Navigation Satellite System (GNSS) signals caused by poles and tree canopies. A properly designed intelligent vision system would have the potential to achieve the desired outcome by utilizing an autonomous weeder to perform operations in uncut sections. Therefore, the objective of this study is to develop a vision module using a custom-trained dataset on YOLO instance segmentation algorithms to support autonomous robotic weeders in recognizing uncut weeds and obstacles (i.e., fruit tree trunks, fixed poles) within rows. The training dataset was acquired from a pear orchard located at the Tsukuba Plant Innovation Research Center (T-PIRC) at the University of Tsukuba, Japan. In total, 5000 images were preprocessed and labeled for training and testing using YOLO models. Four versions of edge-device-dedicated YOLO instance segmentation were utilized in this research—YOLOv5n-seg, YOLOv5s-seg, YOLOv8n-seg, and YOLOv8s-seg—for real-time application with an autonomous weeder. A comparison study was conducted to evaluate all YOLO models in terms of detection accuracy, model complexity, and inference speed. The smaller YOLOv5-based and YOLOv8-based models were found to be more efficient than the larger models, and YOLOv8n-seg was selected as the vision module for the autonomous weeder. In the evaluation process, YOLOv8n-seg had better segmentation accuracy than YOLOv5n-seg, while the latter had the fastest inference time. The performance of YOLOv8n-seg was also acceptable when it was deployed on a resource-constrained device that is appropriate for robotic weeders. The results indicated that the proposed deep learning-based detection accuracy and inference speed can be used for object recognition via edge devices for robotic operation during intrarow weeding operations in orchards.

show abstract

Section: Discussionmentioning

confidence: 99%