Intelligent Harvesting Technologies for Cultivated Edible Mushrooms: A Structured Critical Review from Mechanized Equipment to Robotic Systems and Cross-Species Adaptation

Harvesting remains labor-intensive because delicate fruiting bodies, complex growing environments, selective harvesting demands, and interspecific morphological variation complicate mechanized and intelligent operation. A structured critical review of 200 publications synthesizes advances in mushroom harvesting from an agricultural-engineering perspective, focusing on harvesting mechanisms, machine vision, maturity assessment, three-dimensional localization, motion planning, end-effectors, damage reduction, and integrated robotic systems. Particular attention is given to how morphology, cultivation mode, harvesting requirements, and equipment configuration interact across representative species. On this basis, a conceptual cross-species adaptation framework links phenotypic traits with perception targets, contact constraints, separation mechanisms, and operational organization; its transferability remains to be validated through direct multi-species experiments. Key bottlenecks and evidence gaps include occlusion, clustered growth, variable maturity, mechanical damage, limited efficiency and robustness, and insufficient evidence for cross-site robustness and cross-species transfer. Future research should prioritize harvest-oriented phenotyping and multimodal perception, reconfigurable compliant modules, multi-stage perception–decision–execution coordination, cultivation–equipment co-design, interface standardization, virtual/digital validation, and long-duration production and economic evaluation. This review provides an integrated engineering framework for the transition from mechanized equipment to autonomous harvesting systems and for the development of efficient, low-damage, and adaptable mushroom-harvesting machinery.