Pineapple harvesting is a key step in pineapple field production. At present, pineapple fruits are usually picked manually. With decreasing labor resources and increasing production costs, machines have been used instead of manual picking approaches in the modern pineapple industry. This paper briefly describes the basic situation of pineapple planting worldwide. Based on the degree of automation of mechanized pineapple harvesting equipment, the main structural forms, core technologies, and operation modes of semi-automatic, automatic, and intelligent pineapple harvesting equipment are summarized. The research status and existing problems of key pineapple fruit picking robots, such as fruit recognition, maturity classification, positioning, and separation of pineapple fruits, are analyzed. Considering the problems of pineapple harvesting equipment, such as difficulty entering the ground, low harvesting efficiency, low picking success rate, and fruit damage, innovative future research directions for mechanized pineapple harvesting technology are proposed, such as combining agricultural machinery and agronomical principles, integrating mechanized, automated, and intelligent technology, and developing modular designs and generalized approaches.

Cassava is one of the world’s staple crops and an important economic and food crop for one billion people. It holds significant value in food, feed, and industrial raw materials. However, cassava production is faced with the following problems: agricultural machinery and agronomy are not integrated, work efficiency is not high, it is not suitable for large-scale planting plots, and there is a lack of large-scale equipment, automation, and intelligent cassava production equipment. This study reviews research on cassava planting agronomy and mechanized production technologies and equipment, including planting, stem–tuber separation, and harvesting, both globally and in China. The shortcomings are analyzed, and recommendations are provided for current mechanized cassava production to accelerate the development of intelligent equipment and strengthen the shortcomings. Meanwhile, we used typical and extensive Chinese planting and harvesting machines as case studies. The future trends in cassava production are forecasted, underscoring the importance of advancing global mechanized technology and equipment for cassava production to enhance its efficiency, competitiveness, and modernization.

Targeting the issues of seed leakage and cutting segment adhesion due to poor seed feeding and cutting in real-time seed-cutting cassava planters, this study developed a seeding quality monitoring system. Based on the structure and working principle of the seed cutting and discharging device, the installation methods of the matrix fiber optic sensor and rotary encoder were determined. By combining the operational characteristics of the planter’s ground wheel drive with seed cutting and seed dropping, a monitoring model correlating the sowing parameters with seed dropping time was established; a monitoring window was created by extracting and processing the rotary encoder pulse signal, and the number of seeds sown after each opposing cutter’s operation was calculated based on the pulse width information within the monitoring window. The monitoring system’s statistics were compared and analyzed with the manual statistics, and the bench test showed that the monitoring system designed in this study offers high accuracy. When the simulated rotational speed of the opposing cutter ranges from 10 to 30 rpm, the average monitoring error between the monitored and actual seeding quantities for the left and right rows is less than 1.4%. The monitoring system can promptly and accurately activate sound and light alarms for faults, achieving a 100% success rate in alarms and an average fault response time of less than 0.4 seconds. Field tests demonstrate that the average error in seeding volume is 0.91%, and the monitoring system can timely alert to faults occurring in the planter. The system fulfills the requirements for real-time monitoring of cassava seeding volume at various operating speeds in field conditions, and can serve as a reference for monitoring operational parameters in subsequent cassava combine harvesters.

To achieve accurate detection of the pineapple fruit picking area and pose under complex backgrounds and varying lighting conditions, this study proposes a pineapple keypoint detection model (LTHRNet) based on an improved LiteHRNet. Image data of pineapple fruits under different lighting conditions were collected, and six keypoints were defined to characterize the morphological features of the fruit. In the model design, LTHRNet incorporates the LKA_Stem module to enhance initial feature extraction, the D-Mixer module to capture both global and local feature relationships, and the MS-FFN module to achieve multi-scale feature fusion. In addition, the model employs parallel sub-networks with different resolutions to maintain high-resolution feature information and improve the precision and spatial accuracy of keypoint detection. Experimental results show that LTHRNet performs well in pineapple keypoint detection. It achieves 93.5% and 95.1% in KAP_0.5 and KAR_0.5, respectively, outperforming other models in terms of detection accuracy and robustness under challenging lighting and occlusion conditions, with a detection speed of 21.1 fps. For pose estimation, the average offset angle (AOA) of LTHRNet is 2.37°, which is significantly lower than that of other models. In summary, the proposed LTHRNet model demonstrates high accuracy and strong robustness in pineapple keypoint detection and pose estimation, providing reliable keypoint localization and pose estimation data for pineapple harvesting, while also offering an effective reference for pose recognition in other fruit-picking tasks.

Sugarcane is an important economic crop in tropical and subtropical regions. Presawing planting is an important method for achieving automated and precise planting with sugarcane planting machines. The sawing process is a key stage in planting management, affecting not only the germination and survival rates of sugarcane, but also reflecting the mechanical performance of sawing. To reduce the peak sawing force and enhance the sawing surface quality of sugarcane seedlings, this study utilized a central composite experimental design method. Single-factor and multi-factor experiments were conducted with a specially designed sugarcane stalk sawing experimental rig to investigate the impact of factors such as the stalk diameter feeding speed, and sawing speed on the peak sawing force and sawing surface quality. Upon being developed and validated, multivariate mathematical regression models elucidated the relationships among these factors. The experimental results showed that the order of influence of each factor on the peak sawing force was the stalk diameter, feed speed, and sawing speed, while for the sawing surface quality, the sequence was the sawing speed, stalk diameter, and feed speed. Correspondingly, the determination coefficients for the peak sawing force and sawing surface quality prediction models were 0.9708 and 0.9675. With a maximum error of 7.6% for the peak sawing force and an average relative error of 7.1%, and a maximum error of 3.5% for the sawing surface quality and an average relative error of 2.83%, the calculated results from the regression models were in good agreement with the experimental findings. This indicates that the models are capable of quickly and accurately predicting the peak sawing force and sawing surface quality of sugarcane stalks under different conditions. The research findings provide valuable insights for the development and optimization of sugarcane stalk presawing equipment and related experimental studies.

In view of the lack of research on the extrusion of pineapple caused by the overall stress response of pineapple at the present stage of pineapple automatic harvesting, the finite element model of pineapples can be studied by constructing such a model. At present, there is still a lack of research on the mechanical properties of the pineapple stem. In this research, the mechanical properties of a pineapple stem were determined by a three-point bending test, a compression test, and a theoretical calculation. Based on the cohesive zone model (CZM), the relevant parameters of the pineapple fruit–stem junction were determined by the fracture test. The overall finite element model of pineapple was established, and then the verification test of the finite element model was carried out. In the validation test, the correlation between sample size parameters and results was analyzed, and the validity of the test sample selection was demonstrated. By substituting the simulation results into the derivation formula, the maximum traction strength and maximum displacement error values were calculated to be 4.3% and 2.9%, respectively, which verified the accuracy of the cohesive zone model parameters. By comparing the maximum load force and load displacement of the load point in the test and simulation, the error of the load force at the fracture point relative to the average value was 3.6%, and the error of the load displacement relative to the average value was 1.4%. The numerical results showed that the model reflected the accuracy of the process of pineapple plant fracture. This study provides a reliable finite element model for future research on pineapple automatic harvesting.