Answers are grounded in this paper and cite their sources.
The automation of flower harvesting has become a critical research direction in modern floriculture due to increased global demand for ornamental plants, labor shortages, and the high sensitivity of flowers to mechanical damage. Traditional manual harvesting is labor-intensive, time-consuming, and heavily dependent on skilled workers, resulting in inconsistent product quality and rising production costs. Intelligent robotic systems equipped with advanced perception, motion planning, and adaptive end-effectors have emerged as a promising solution to improve harvesting efficiency, reduce labor dependence, and ensure high-quality yield. This review presents a comprehensive analysis of robotic flower-harvesting technologies, with a focus on machine-vision algorithms, image-processing methods, mechanical architectures, end-effector designs, control approaches, and mobility platforms. The review considers both whole-flower harvesting and emerging selective harvesting scenarios targeting valuable floral components, including specific flower organs such as petals and sepals, which require precise perception and manipulation strategies. Recent developments in deep learning-based flower detection, soft robotics, and multi-sensor fusion are discussed, along with performance evaluation benchmarks and quality-assessment criteria reported in the literature. Additionally, global research trends, publication dynamics, key contributing countries, and keyword evolution are analyzed to highlight technological progress and research distribution. Finally, emerging opportunities such as collaborative robots, multi-robot coordination, generative AI models, and sustainable automation strategies are explored to outline future research directions. This review aims to provide researchers and industry professionals with an organized reference and insight framework to guide innovation toward efficient, precise, and commercially practical robotic flower-harvesting systems.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: