In the past decade, intelligent technologies have advanced rapidly, particularly due to improvements in automatic control, which have had a significant impact on forestry, as well as animal husbandry and the future of farm management. However, the degree of production and management mechanization in natural rubber plantations is low, especially since the methods of tapping still rely heavily on labor. The decrease of skilled rubber tappers and the increase in labor costs have led to the development of the mechanization of rubber tapping operations. The application of emerging intelligent agricultural technologies could provide an alternative in order to maximize the potential productivity of natural rubber. Based on this vision, we reviewed the literature on rubber tapping from the past decade for system implementation in rubber plantations. In this review, selected references on rubber tapping were categorized into several directions of research, including rubber tapping machines, the key technologies applied in tapping operations, and some related protective research, analyzing research works from 2010 to 2022 that focused on tapping methods. The review also discusses the application of intelligent agricultural technologies, such as the recognition of tapping trajectory and tapping path planning. A summary of challenges and future trends is also provided in this study. Based on the relevant research, the use of intelligent technologies in rubber tapping machines is still in its initial stage and has broad prospects. Through this study, we aim to provide a reference for researchers in the field of rubber tapping machines and thus to play a positive role in future rubber tapping.

Rubber tree powdery mildew (PM) is one of the most devastating leaf diseases in rubber forest plantations. To prevent and control PM, timely and accurate detection is essential. In recent years, unmanned Aerial Vehicle (UAV) remote sensing technology has been widely used in the field of agriculture and forestry, but it has not been widely used to detect forest diseases. In this study, we propose a method to detect the severity of PM based on UAV low-altitude remote sensing and multispectral imaging technology. The method uses UAVs to collect multispectral images of rubber forest canopies that are naturally infected, and then extracts 19 spectral features (five spectral bands + 14 vegetation indices), eight texture features, and 10 color features. Meanwhile, Pearson correlation analysis and sequential backward selection (SBS) algorithm were used to eliminate redundant features and discover sensitive feature combinations. The feature combinations include spectral, texture, and color features and their combinations. The combinations of these features were used as inputs to the RF, BPNN, and SVM algorithms to construct PM severity models and identify different PM stages (Asymptomatic, Healthy, Early, Middle and Serious). The results showed that the SVM model with fused spectral, texture, and color features had the best performance (OA = 95.88%, Kappa = 0.94), as well as the highest recognition rate of 93.2% for PM in early stages.

The object detection algorithm is one of the core technologies of the intelligent rubber tapping robot, but most of the existing detection algorithms cannot effectively meet the tapping trajectory detection of natural rubber trees in the complex forest environment. This paper proposes a tapping trajectory detection method for natural rubber trees based on an improved YOLOv5 model to accomplish fast and accurate detection. Firstly, the coordinate attention (CA) mechanism is added to the Backbone network to embed the location information into the channel attention, which effectively improves the detection accuracy. Secondly, a module called convolution and GhostBottleneck (CGB) is designed, based on the Ghost module, to substitute the Cross Stage Partial Network (CSP) module in the Neck network, which ensures the detection accuracy while reducing model parameters. Finally, the EIoU loss function is introduced to enable a more accurate regression of the model. The experimental results show that the overall performance of the YOLOv5-CCE model outperforms the original YOLOv5 and other classical lightweight detection algorithms. Compared with the original YOLOv5 model, the YOLOv5-CCE model has a 2.1% improvement in mAP value, a 2.5% compression of model parameters, and a 7.0% reduction in the number of floating point operations (FLOPs). Therefore, the improved model can fully meet the requirements of real-time detection, providing a robust detection method for rubber tapping robots.

Aiming at the problem that the rubber tapping robot finds it difficult to accurately detect the tapped area and locate the new tapping line for natural rubber trees due to the influence of the rubber plantation environment during the rubber tapping operation, this study proposes a method for detecting the tapped area and locating the new tapping line for natural rubber trees based on the improved mask region convolutional neural network (Mask RCNN). First, Mask RCNN was improved by fusing the attention mechanism into the ResNeXt, modifying the anchor box parameters, and adding a tiny fully connected layer branch into the mask branch to realize the detection and rough segmentation of the tapped area. Then, the fine segmentation of the existing tapping line was realized by combining edge detection and logic operation. Finally, the existing tapping line was moved down a certain distance along the center line direction of the left and right edge lines of the tapped area to obtain the new tapping line. The tapped area detection results of 560 test images showed that the detection accuracy, segmentation accuracy, detection average precision, segmentation average precision, and intersection over union values of the improved Mask RCNN were 98.23%, 99.52%, 99.6%, 99.78%, and 93.71%, respectively. Compared with other state-of-the-art approaches, the improved Mask RCNN had better detection and segmentation performance, which could better detect and segment the tapped area of natural rubber trees under different shooting conditions. The location results of 560 new tapping lines under different shooting conditions showed that the average location success rate of new tapping lines was 90% and the average location time was 0.189 s. The average values of the location errors in the x and y directions were 3 and 2.8 pixels, respectively, and the average value of the total location error was 4.5 pixels. This research not only provides a location method for the new tapping line for the rubber tapping robot but also provides theoretical support for the realization of rubber tapping mechanization and automation.

Rubber tree is one of the essential tropical economic crops, and rubber tree powdery mildew (PM) is the most damaging disease to the growth of rubber trees. Accurate and timely detection of PM is the key to preventing the large-scale spread of PM. Recently, unmanned aerial vehicle (UAV) remote sensing technology has been widely used in the field of agroforestry. The objective of this study was to establish a method for identifying rubber trees infected or uninfected by PM using UAV-based multispectral images. We resampled the original multispectral image with 3.4 cm spatial resolution to multispectral images with different spatial resolutions (7 cm, 14 cm, and 30 cm) using the nearest neighbor method, extracted 22 vegetation index features and 40 texture features to construct the initial feature space, and then used the SPA, ReliefF, and Boruta–SHAP algorithms to optimize the feature space. Finally, a rubber tree PM monitoring model was constructed based on the optimized features as input combined with KNN, RF, and SVM algorithms. The results show that the simulation of images with different spatial resolutions indicates that, with resolutions higher than 7 cm, a promising classification result (>90%) is achieved in all feature sets and three optimized feature subsets, in which the 3.4 cm resolution is the highest and better than 7 cm, 14 cm, and 30 cm. Meanwhile, the best classification accuracy was achieved by combining the Boruta–SHAP optimized feature subset and SVM model, which were 98.16%, 96.32%, 95.71%, and 88.34% at 3.4 cm, 7 cm, 14 cm, and 30 cm resolutions, respectively. Compared with SPA–SVM and ReliefF–SVM, the classification accuracy was improved by 6.14%, 5.52%, 12.89%, and 9.2% and 1.84%, 0.61%, 1.23%, and 6.13%, respectively. This study’s results will guide rubber tree plantation management and PM monitoring.

Simultaneous localization and mapping (SLAM) in rubber plantations is a challenging task for rubber-tapping robots. Due to the long-term stability of tree trunks in rubber plantations, a SLAM system based on semantic segmentation, called Se-LOAM, is proposed in this work. The 3D lidar point cloud datasets of trunks collected in rubber plantations of Hainan University are used to train the semantic model, and the model is used to extract features of trunk point clouds. After clustering the trunk point clouds, each single rubber tree instance is segmented based on the Viterbi algorithm. The point clouds of tree instances are fitted to the cylindrical trunk models for semantic cluster association and positional estimation, which are used for lidar odometry and mapping. The experimental results show that the present SLAM system is accurate in establishing online mapping, and the location of the trunk in the map is clearer. Specifically, the average relative pose error is 0.02 m, which is better than the positioning performance of LOAM and LeGO-LOAM. The average error of estimating the diameter at breast height (DBH) is 0.57 cm, and it only takes 401.4 kB to store a map of the area of approximately 500 ${\mathrm{m}}^2$, which is about 10% less than other classic methods. Therefore, Se-LOAM can meet the requirements of online mapping, providing a robust SLAM method for rubber-tapping robots.