The demand for efficient and sustainable agricultural practices has fostered the development of advanced technologies for pest management. This paper presents a research study on the detection of slugs on lettuce and the 3D localization ( \(x,y,z\) coordinates) of the detected slugs, with the goal of enabling a robotic arm to collect them in a horticultural application. In this regard, deep-learning models (YOLOv5), were developed as a tool in this study. The real-time 3D coordinates of the centers of the detected slugs were calculated by the developed YOLOv5 models. A total of 4344 images were captured under diverse conditions and manually labeled for training (3098 images) and validation (775 images) of the models, while an additional 471 images were used for testing. The evaluation of the YOLOv5l model on the test dataset showed promising results, with 98.6% recall, 98.9% precision, and a mean average precision (mAP) 50–95 of 78.8%. The comparison of box losses during training and validation demonstrated that YOLOv5l had the lowest box losses, emphasizing its better performance. The experimental results show the effectiveness of the developed system in slug detection on lettuce and in providing accurate 3D coordinates of the detected slugs in real-time. This research shows a promising approach to be implemented in a horticultural robotic platform capable of autonomously detecting and collecting slugs, which could contribute to enhanced efficiency and sustainability in agriculture and horticulture.
