ABSTRACT The advancement of agricultural robotics offers effective solutions to the complexities of harvesting fragile fruits. This paper provides a comprehensive review of research and development within the domain of fragile fruit harvesting, with a specific focus on analyzing core technologies across the perception–reasoning–execution pipeline. This analysis encompasses fruit recognition and localization, decision‐making, trajectory planning, and end‐effector design. By examining representative robotic systems from both academia and industry, critical technical parameters are systematically summarized. The analysis reveals that the deployment of current agricultural robots remains constrained by high costs and low efficiency. Moreover, harvesting fragile fruits faces significant challenges, including severe environmental occlusion, pronounced localization errors, and elevated fruit damage rates. To address these issues, the standardization of cultivation models, the integration of multimodal sensing, and the application of embodied intelligent algorithms are identified as primary strategies. Future efforts should integrate relevant technologies from general‐purpose robotics into agricultural production. By leveraging multidisciplinary synergy, precise, high‐efficiency, and nondestructive fruit harvesting can be facilitated.
Jiang et al. (Wed,) studied this question.