Citrus harvesting is time-intensive and labor-intensive, relying mainly on manual harvesting. The automatic harvesting of fruit and vegetable crops can not only reduce the physical labor of fruit farmers in the harsh field environment but also greatly improve the harvesting efficiency. Based on the principle of manual citrus picking, an end-effector with three-finger grasping is designed in this study. First, the structure of the end-effector was designed to achieve the function of stable grasping and effective cutting of citrus fruits, and then the working process and key parameters of the end-effector were explained in detail. Finally, a picking test was conducted without considering robot vision. The test results show that the end-effector has a picking success rate of 95.23% for citrus with a diameter of 30–100 mm and an average picking time of 4.65 s for a single fruit. This end-effector can realize the picking function for citrus of different sizes and shapes and has the advantages of high adaptability, stable gripping and no damage to the fruit.
Despite the abundant clean energy resources on islands, energy supply on the islands in many countries and regions still depends on high-voltage power grids in neighboring continents and high-cost fossil energy such as oil. In China, increasing demand for private gasoline vehicles calls for an abundant gasoline supply, which is harmful to the renewable energy transformation on Chinese islands. The promotion of electric vehicles offers a potential solution. However, on large islands with large populations, insufficient electricity supply restricts residents' behavior, which has led to difficulties in promoting clean energy vehicles. To solve this problem, in 2019, the government formulated an 11-year plan to comprehensively promote clean energy vehicles from the energy supply side and user demand side to transform Hainan Island into a clean energy island. However, some predictions in the report are doubtful. As a result, this study takes Hainan Island in China as an example. Based on data on energy and electric vehicles, the greenhouse gas emissions and electricity demand of the transportation industry in Hainan Island under policy and non-policy scenarios are calculated using a generation substitution accounting model. Based on the results, this study evaluates the expected effect of Hainan Province's 11-year plan to develop clean energy vehicles and compares the results with those in the report. Policy implications based on the results are also proposed. This study combines the island's energy structure with the application of electric vehicles and expands the evaluation of government policies on the impact of large-scale energy transformation from the perspective of the energy supply chain. It also provides a reference for energy transformation on other large islands.
Fast assessment of the initial carbon to nitrogen ratio (C/N) of organic fraction of municipal solid waste (OFMSW) is an important prerequisite for automatic composting control to improve efficiency and stability of the bioconversion process. In this study, a novel approach was proposed to estimate the C/N of OFMSW, where an instance segmentation model was applied to predict the masks for the waste images. Then, by combining the instance segmentation model with the depth-camera-based volume calculation algorithm, the volumes occupied by each type of waste were obtained, therefore the C/N could be estimated based on the properties of each type of waste. First, an instance segmentation dataset including three common classes of OFMSW was built to train mask region-based convolutional neural networks (Mask R-CNN) model. Second, a volume measurement algorithm was proposed, where the measurement result of the object was derived by accumulating the volumes of small rectangular cuboids whose bottom area was calculated with the projection property. Then the calculated volume was corrected with linear regression models. The results showed that the trained instance segmentation model performed well with average precision scores AP50 = 82.9, AP75 = 72.5, and mask intersection over unit (Mask IoU) = 45.1. A high correlation was found between the estimated C/N and the ground truth with a coefficient of determination R2=0.97 and root mean square error RMSE = 0.10. The relative average error was 0.42% and the maximum error was only 1.71%, which indicated this approach has potential for practical applications. Keywords: carbon to nitrogen ratio, estimation, volume measurement, organic fraction of municipal solid waste, depth camera, instance segmentation DOI: 10.25165/j.ijabe.20211405.6382 Citation: Huang J J, Zhang H D, Xiao X, Huang J Q, Xie J X, Zhang L, et al. Method for C/N ratio estimation using Mask R-CNN and a depth camera for organic fraction of municipal solid wastes. Int J Agric & Biol Eng, 2021; 14(5): 222–229.
Abstract Currently, flexible tactile sensors integrating proximity‐pressure sensing encounter challenges in efficient multisignal acquisition, accurate recognition, cost control, and scalability. Herein, a fabric‐based multimodal flexible capacitive sensor (MFCS), combining an integrated fabric electrode design with a magnetic tilted micropillars (MTM) array microstructure, is developed. This innovative design significantly enhances the sensor's fringing effect, magnetic responsiveness, and dielectric layer's deformation ability, enabling precise perception of pressure, proximity, and magnetic field changes. The MFCS demonstrates high sensitivity and rapid response characteristics, achieving a sensitivity of 0.146 kPa⁻¹ under 0–2 kPa pressure with response/recovery times of ≈12/24 ms. Moreover, it detects hand proximity within a 20 cm range, with a sensitivity of −0.039 cm⁻¹ in the 0–2 cm range, and a magnetic field detection limit of 10 mT, showing a sensitivity of −1.72 T⁻¹ in the 60–230 mT range. The sensor operates effectively in both capacitance and resonant frequency modes, distinguishing different signals, thus offering new possibilities for smart wearable devices and interactive systems. Overall, the MFCS features multimodal sensing, a fully fabric structure, cost‐effectiveness, and ease of fabrication, making it promising for human–computer interaction, artificial intelligence, and health monitoring.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)