Chili pepper (Capsicum annuum L.), a globally important economic crop, faces production challenges characterized by high labor intensity, cost, and inefficiency. Intelligent technologies offer key opportunities for sector transformation. This review begins by outlining the diversity of major chili pepper cultivars, differences in key quality indicators, and the resulting specific harvesting needs. It then reviews recent progress in intelligent perception, recognition, and automation within the chili pepper industry. For perception and recognition, the review covers the evolution from traditional image processing to deep learning-based methods (e.g., YOLO and Mask R-CNN achieving a mAP > 90% in specific studies) for pepper detection, segmentation, and fine-grained cultivar identification, analyzing the performance and optimization in complex environments. In terms of automation, we systematically discuss the principles and feasibility of different mechanized harvesting machines, consider the potential of vision-based keypoint detection for the point localization of picking, and explore motion planning and control for harvesting robots (e.g., robotic systems incorporating diverse end-effectors like soft grippers or cutting mechanisms and motion planning algorithms such as RRT) as well as seed cleaning/separation techniques and simulations (e.g., CFD and DEM) for equipment optimization. The main current research challenges are listed including the environmental adaptability/robustness, efficiency/real-time performance, multi-cultivar adaptability/flexibility, system integration, and cost-effectiveness. Finally, future directions are given (e.g., multimodal sensor fusion, lightweight models, and edge computing applications) in the hope of guiding the intelligent growth of the chili pepper industry.

Cumin (Cuminum cyminum L.) is a globally important spice crop, particularly significant in Xinjiang, China, where it is extensively cultivated in cotton–cumin intercropping systems. This review concentrates on the serious bottleneck hindering the development of the cumin industry: the low level of harvesting mechanization. Traditional manual harvesting methods are labor-intensive, inefficient, and result in high yield losses. This paper fully explores the prospects and challenges of mechanizing cumin harvesting in accordance with the particular biological characteristics of cumin plants and the complexity of intercropping systems. We review the current status of research in the following domains: (1) cumin biological traits and intercropping models; (2) grain loss and stalk damage patterns in stripper harvesting of similar crops; (3) factors influencing root–soil interaction during mechanical extraction; (4) uprooting–conveying harvesting techniques and row division/plant singulation methods applicable to root and tuber crops; and (5) cumin-threshing and -cleaning technologies. This review highlights the inadequacy of current grain-harvesting machinery for cumin and underscores the urgent need for specialized, low-loss harvesting technologies tailored to cumin’s delicate nature and intercropping context. Finally, we propose future research directions to overcome these mechanization challenges and promote the sustainable development of the cumin industry.

Cumin (Cuminum cyminum L. cv.′Xin Ziran 1′), classified within an agricultural crop, necessitates uprooting as a critical harvesting process. In this paper, we tried to study the force dynamics behind direct cumin uprooting by developing mechanical models for field uprooting and taproot–soil friction. A mechanical model for cumin uprooting and a friction model between the cumin taproot and sandy loam soil were built. The coefficient of static friction was determined using laboratory experiments. Pull-out, tensile force, and field uprooting experiments were conducted to validate the model. The physical and mechanical properties of the taproot were also measured. DEM simulation was employed for pull-out analysis. The static coefficient of friction between the cumin taproot and sandy loam soil was found to be approximately 0.766. The mechanical model showed high precision (0.4% and 5% error rates). Measured taproot properties included 80.91% moisture content, 0.40 Poisson’s ratio, 15.95 MPa elastic modulus, 5.70 MPa shear modulus, and 3.49 MPa bending strength. A DEM simulation revealed agreement with experimental observations for maximum frictional resistance at pull-out. The minimum resistance was noted at the extraction angle of 60°. The developed mechanical model for cumin uprooting was satisfactory in accuracy. Overcoming initial soil resistance is the primary factor affecting pull-out force magnitude. The optimized extraction angle had the potential to decrease uprooting resistance, improving harvesting efficiency.