A notable development in precision agriculture is the creation of an autonomous herbicide sprayer robot specifically designed for agriculture. This innovative robot uses recent technology to identify and target weeds among sesame plants, reducing the need for herbicides and minimizing environmental impact. Equipped with sophisticated sensors and cameras, the robot navigates the field autonomously, distinguishing weeds from crops. By accurately detecting and applying herbicides to weeds, the robot maximizes weed control while protecting the health of plants. This autonomous approach to weed management enhances sustainability, lowers labour costs, and increases efficiency by incorporating robotics into agricultural practices. The proposed method has several practical applications in agriculture, including weed management, crop yield optimization, and environmental sustainability. Furthermore, it has potential uses when integrated with other precision farming equipment, making it a cost-effective solution for farmers. Additionally, in this study, we developed and implemented a CNN-based crop-weed detection system for a sprayer robot tailored for targeted spraying in sesame fields. To achieve this, we trained and evaluated two different variants of the YOLOv9 object detection algorithm on a custom dataset containing 2148 real-time images gathered from sesame farmlands. The proposed algorithm achieved a precision of 92.7%, a recall of 85.7%, and mAP of 94.2% and F1 score of 84.2%, showcasing significant improvements in accuracy and efficiency compared to existing methods.