Post-harvest sorting is essential for converting the biological variability of chili peppers into consistent commercial grades, efficient processing, and higher market value. Rapid advances in machine vision, multimodal sensing, deep learning, and intelligent actuation are transforming sorting equipment from rule-based classifiers into integrated perception-to-execution systems. However, existing studies often evaluate isolated algorithms or components, leaving limited evidence that recognition accuracy translates into reliable sorting during continuous operation. We conducted a structured narrative review of English-language studies published from January 2008 to July 2026 using Web of Science, Scopus, AESC, and PubMed. Evidence was synthesized along a perception-to-execution chain, distinguishing pepper-specific sorting systems and component studies from cross-crop engineering evidence. Direct system-level evidence was concentrated in a small number of chili and bell pepper studies, whereas much of the technical discussion drew on apple, tomato, potato, sweet potato, and onion research. Visible, spectral, fluorescence, and multimodal features can distinguish ripeness, color grades, and surface defects, although performance remains sensitive to cultivar, illumination, pose, and dataset design. A small number of pepper sorting studies support the feasibility of integrating vision, conveying, and physical separation under specific operating conditions. Cross-crop studies inform the discussion of localization, pneumatic actuation, and system integration, but do not establish the performance of these approaches in chili pepper sorting. Reported performance is difficult to compare because studies rarely standardize latency, target association, false and missed rejections, product damage, energy use, and long-term reliability. Robust deployment therefore requires cross-batch datasets, synchronized target-level traceability, and evaluation protocols linking perception outputs to final physical destinations. This review identifies the boundaries of current pepper-specific evidence and proposes a system-level evaluation framework and research priorities for testing the transferability of cross-crop engineering approaches to pepper sorting.

Mechanized production of processing tomatoes depends on coordinated operations, but crop variability and successive material transfers make performance strongly condition-dependent. This narrative review used structured, non-systematic literature identification across multidisciplinary databases and publisher platforms, supplemented by backward reference tracing through July 2026. Evidence was synthesized through crop–agronomy conditions, machine responses, operational trade-offs, validation maturity, sustainability-related outcomes, and downstream residue requirements. Four findings emerge. First, architecture, maturity synchronization, fruit mechanics, stand geometry, and water status define machine operating envelopes. Second, harvesting is governed by a persistent conflict among detachment, loss, damage, impurity content, throughput, and energy demand; comparisons of settings benefit from a common basis in cultivar, feed rate, machine configuration, and metric definition. Third, sensing and prediction studies provide a foundation for automatic execution and feedback-based adjustment, with replicated whole-machine field trials offering the next step in evaluating multistage control. Fourth, residue discharge, size reduction, collection, and densification need to be specified backward from soil-incorporation or valorization requirements. Operation-specific sustainability benefits are most directly supported for water and input efficiency, marketable-yield retention, and residue recovery, with matched assessments of energy, cost, and life-cycle impacts providing opportunities to extend these findings. Progress therefore requires crop-specific tests that report engineering benefits together with losses, adverse effects, resource use, and operating boundaries.

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.