Recent studies have driven the development of innovative technologies, including smart agriculture and robotics, to optimize weed management practices. Precision agriculture, for example, leverages GPS technology and data analytics to target weed infestations with high accuracy, reducing chemical usage and mitigating harm to non-target plants [13]. Additionally, robotic weeders equipped with cameras and AI algorithms can autonomously identify and remove weeds, decreasing the need for manual labor and herbicides [14]. Smart laser weed control uses laser beams to selectively destroy weeds by heating their tissues, offering a chemical-free and highly precise alternative [15]. Recent advancements in autonomous weeding technologies have shown significant potential for enhancing agricultural efficiency. McCool et al. [16] introduced AgBot II, a system that integrates a camera and lighting module to differentiate between crops and weeds, using either a tine or an arrow hoe for precise, low-impact mechanical weeding. Building on this, Quan et al. [17] developed an intra-row mechanical system with a rotating disk knife, driven by a convolutional neural network (CNN) for accurate weed detection in maize crops. Additionally, Francesco et al. [18] advanced the field by proposing a two-camera system mounted on a four-wheel gantry robot, which refines plant detection and classification. Collectively, these innovations underscore the considerable progress and potential of autonomous systems in agricultural applications. Nonetheless, selectively removing early-stage weeds with laser in small farm fields remains challenging. Additionally, real-time weed detection and species classification using limited computational resources pose further barriers.