To address the challenges of limited detection range, unstable tracking, and object flickering caused by ground interference from uneven farmland, inaccurate visual masks, and sparse LiDAR point clouds at mid-to-long distances, this study constructs a multi-sensor fusion perception system based on 3D LiDAR and cameras. Furthermore, it proposes an obstacle detection method incorporating cascaded ground filtering, multimodal feature fusion, and temporal tracking. The method first utilizes a cascaded algorithm combining Random Sample Consensus (RANSAC) and Cloth Simulation Filter (CSF) to address the challenge of ground clutter filtering in uneven terrain. To account for the varying reliability of sensor modalities at different distances, a matching strategy based on hybrid cost is developed. This strategy enables a robust association between LiDAR clusters and visual targets by adaptively weighting the precise boundary information from visual masks and the stable positional features from detection bounding boxes. A Kalman filter is subsequently integrated to impose temporal smoothness on the fusion results and eliminate long-range object flickering. Experimental results demonstrate that the proposed method reduces the ground false positive rate to 0.3% and achieves an overall average precision of 91.4%. Regarding mid-to-long distance detection, in contrast to the baseline method where the recall drops sharply beyond 35 m, the proposed method achieves an average recall of 98.2% within the entire 0-45 m range. Furthermore, accuracy (MOTA) and tracking continuity (IDF1) are improved to 92.93% and 98.03%, respectively. Therefore, the proposed method satisfies the requirements for high precision, high recall, and stable environmental perception in complex farmland scenarios.

To address issues such as significant communication delay fluctuations and low task scheduling efficiency in the coordinated operation of multiple intelligent agricultural machines on large-scale farms, this study proposes a distributed control node-driven multi-machine coordination control method for intelligent agricultural machinery. Taking rice harvesting and grain transportation coordination as the research scenario, the method employs a hybrid low-latency communication network model based on edge computing to establish a distributed control node-driven agricultural machinery coordination system. By integrating game theory and partially observable Markov decision models, it achieves global profit optimization. This approach constructs a hybrid low-latency communication network model based on edge computing to establish a distributed control node-driven agricultural machinery cooperative operation system. By integrating game theory and partially observable Markov decision models, it achieves global benefit optimization. A dynamic priority scheduling algorithm is designed using a proximity policy optimization algorithm, enabling global optimization of operation time and enhanced stability of the cluster control system in large-scale agricultural environments. To validate the proposed method's effectiveness, simulations and field trials were conducted. Simulation results demonstrate that by dynamically adjusting machinery priorities, the system's optimal gap is reduced from 4.8% to 1.1%. Field tests further confirmed that the introduction of the dynamic priority mechanism increased the system benefit ratio from 87.9% to 92.1%, while maintaining stable operational performance even during equipment failure and recovery scenarios. These research findings provide technical support for addressing the challenge of efficient cooperative control in intelligent agricultural machinery clusters within complex agricultural environments, effectively enhancing stability.

The hard bottom layer in paddy fields significantly impacts the driving stability, operational quality, and efficiency of agricultural machinery. Continuously improving the precision and efficiency of unmanned, precision operations for paddy field machinery is essential for realizing unmanned smart rice farms. Addressing the unclear influence patterns of hard bottom contours on typical scenarios of agricultural machinery motion and posture changes, this paper employs a rice transplanter chassis equipped with GNSS and AHRS. It proposes methods for acquiring motion state information and hard bottom contour data during agricultural operations, establishing motion state expression models for key points on the machinery antenna, bottom of the wheel, and rear axle center. A correlation analysis method between motion state and hard bottom contour parameters was established, revealing the influence mechanisms of typical hard bottom contours on machinery trajectory deviation, attitude response, and wheel trapping. Results indicate that hard bottom contour height and local roughness exert extremely significant effects on agricultural machinery heading deviation and lateral movement. Heading variation positively correlates with ridge height and negatively with wheel diameter. The constructed mathematical model for heading variation based on hard bottom contour height difference and wheel diameter achieves a coefficient of determination R2 of 0.92. The roll attitude variation in agricultural machinery is primarily influenced by the terrain characteristics encountered by rear wheels. A theoretical model was developed for the offset displacement of the antenna position relative to the horizontal plane during roll motion. The accuracy of lateral deviation detection using the posture-corrected rear axle center and bottom of the wheel center improved by 40.7% and 39.0%, respectively, compared to direct measurement using the positioning antenna. During typical vehicle-trapping events, a segmented discrimination function for trapping states is developed when the terrain profile steeply declines within 5 s and roughness increases from 0.008 to 0.012. This method for analyzing how hard bottom terrain contours affect the position and attitude changes in agricultural machinery provides theoretical foundations and technical support for designing wheeled agricultural robots, path-tracking control for unmanned precision operations, and vehicle-trapping early warning systems. It holds significant importance for enhancing the intelligence and operational efficiency of paddy field machinery.

In multi-machine operations on modern unmanned farms, local progress deviations can readily propagate into fleet-wide coordination imbalance, while conventional control strategies struggle to reconcile operational efficiency with physical hardware constraints. To address this problem, an event-periodic hybrid-driven cooperative control method for agricultural machinery fleets is proposed. A global performance index integrating the accumulated deviation cost and control-input cost is formulated, with operating speed, operation quality, and engine power imposed as physical bounds of the optimal control problem. For recoverable routine disturbances, a receding horizon control (RHC) strategy adjusts the control input online. For unrecoverable severe failures, a mixed-integer linear programming (MILP)-based dynamic scheduling model is embedded in the RHC framework to couple macroscopic task scheduling with low-level control. Simulation and field experiments were conducted using Yanmar YR60D fully electronically controlled rice transplanters. The results showed that, under multiple random disturbances, the proposed method reduced the simulated completion time by 4.8% compared with conventional PI control while maintaining the peak engine power within the rated safe range. In the field test, the proposed method completed the same predefined task 234 s earlier than PI control, corresponding to a 9.06% reduction in completion time. In the simulated severe single-machine failure scenario, dynamic scheduling and residual-task reallocation were successfully performed, and the progress deviations of the healthy machines from their updated global trajectories decreased to within 0.1% in 550 and 516 s, respectively. The proposed method improves progress-recovery performance under routine disturbances and enables task reconfiguration and coordinated recovery following a machine failure while satisfying the constraints on operating speed, operation quality, and engine power.

To achieve an unmanned rice farm, in this study, a cotransporter system was developed using a tracked rice harvester and transporter for autonomous harvesting, unloading, and transportation. Additionally, two unloading and transportation modes-harvester waiting for unloading (HWU) and transporter following for unloading (TFU)-were proposed, and a harvesting-unloading-transportation (HUT) strategy was defined. By breaking down the main stages of the collaborative operation, designing module-state machines (MSMs), and constructing state-transition chains, a HUT collaborative operation logic framework suitable for the embedded navigation controller was designed using the concept and method of the finite-state machine (FSM). This method addresses the multiple-stage, nonsequential, and complex processes in HUT collaborative operations. Simulations and field-harvesting experiments were performed to evaluate the applicability of this proposed strategy and system. The experimental results showed that the HUT collaborative operation strategy effectively integrated path planning, path-tracking control, inter-vehicle communication, collaborative operation control, and implementation control. The cotransporter system completed the entire process of harvesting, unloading, and transportation. The fieldharvesting experiment revealed that a harvest efficiency of 0.42 hm2 center dot h-1 was achieved. This study can provide insight into collaborative harvesting and solutions for the harvesting process of unmanned farms. (c) 2024 THE AUTHORS. Published by Elsevier LTD on behalf of Chinese Academy of Engineering and Higher Education Press Limited Company. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

This study aims to enhance smart agricultural machinery for more efficient and high-quality rice production by addressing the challenge of sensing wheel rut depth in paddy fields. Monitoring the hard-bottom layer beneath the tillage zone is difficult due to repeated machinery rolling. An unmanned rice direct seeder, which shares the same mobile chassis as the rice transplanter, was equipped with a dual-antenna Global Navigation Satellite System and dual Attitude and Heading Reference System sensors, and was used as a sensing platform. Methods were developed to calibrate sensors, remove outliers, and estimate implement height using numerical fitting and interquartile range detection. Soil compaction and wheel rut depth measurements were used to compare hardbottom variations in dry and wet fields. A spatial motion model was created to measure wheel rut depth based on relationships between antenna-to-wheel and antenna-to-implement distances. Digital modeling and interpolation techniques were used to generate accurate models of the mud surface and hard-bottom layer for depth estimation across the field. Field trials showed repetitive rolling in dry fields created localized hard soil layers and increased compaction, while minimal changes occurred in wet fields. The wheel rut depth in dry fields was under 1.0 cm after three passes, but in wet fields, it ranged from 1.9 to 2.9 cm after 2 to 7 passes, with decreasing increments. Wheel sink sensing experiments achieved a standard deviation of 0.678 cm. The surface slope of the paddy field measured by the unmanned direct seeder was 0.03 degrees, which is smaller than the slope of the hard bottom layer at 0.07 degrees. Sink depths were greater in low-lying areas, averaging 23.47 cm, with a variance of 1.84 cm and a maximum depth of 38.10 cm. On a 5-hectare rice farm, the rice transplanter measured mean wheel rut depths of 22.15 cm (variance: 2.17 cm) in Area I and 22.60 cm (variance: 2.53 cm) in Area II. The proposed methods enable continuous, precise monitoring of hard-bottom layer changes and wheel rut depths, characterize the effects of repeated rolling, and produce critical terrain maps. These results support adaptive speed control and entrapment prevention strategies for unmanned smart farm machinery.

To address the issue of agricultural robot loss of control caused by GNSS signal degradation or loss in complex agricultural environments such as farmland and orchards, this study proposes a neural network-based SLAM/GNSS fusion localization algorithm aiming to enhance the robot’s localization accuracy and stability in weak or GNSS-denied environments. It achieves multi-sensor observed pose coordinate system unification through coordinate system alignment preprocessing, optimizes SLAM poses via outlier filtering and drift correction, and dynamically adjusts the weights of poses from distinct coordinate systems via a neural network according to the GDOP. Experimental results on the robotic platform demonstrate that, compared to the SLAM algorithm without pose optimization, the proposed SLAM/GNSS fusion localization algorithm reduced the whole process average position deviation by 37%. Compared to the fixed-weight fusion localization algorithm, the proposed SLAM/GNSS fusion localization algorithm achieved a 74% reduction in average position deviation during transitional segments with GNSS signal degradation or recovery. These results validate the superior positioning accuracy and stability of the proposed SLAM/GNSS fusion localization algorithm in weak or GNSS-denied environments. Orchard experimental results demonstrate that, at an average speed of 0.55 m/s, the proposed SLAM/GNSS fusion localization algorithm achieves an overall average position deviation of 0.12 m, with average position deviation of 0.06 m in high GNSS signal quality zones, 0.11 m in transitional sections under signal degradation or recovery, and 0.14 m in fully GNSS-denied environments. These results validate that the proposed SLAM/GNSS fusion localization algorithm maintains high localization accuracy and stability even under conditions of low and highly fluctuating GNSS signal quality, meeting the operational requirements of most agricultural robots.

In situ detection of growth information in greenhouse crops is crucial for germplasm resource optimization and intelligent greenhouse management. To address the limitations of poor flexibility and low automation in traditional phenotyping platforms, this study developed a controlled environment inspection robot. By means of a SCARA robotic arm equipped with an information acquisition device consisting of an RGB camera, a depth camera, and an infrared thermal imager, high-throughput and in situ acquisition of lettuce phenotypic information can be achieved. Through semantic segmentation and point cloud reconstruction, 12 phenotypic parameters, such as lettuce plant height and crown width, were extracted from the acquired images as inputs for three machine learning models to predict fresh weight. By analyzing the training results, a Backpropagation Neural Network (BPNN) with an added feature dimension-increasing module (DE-BP) was proposed, achieving improved prediction accuracy. The R2 values for plant height, crown width, and fresh weight predictions were 0.85, 0.93, and 0.84, respectively, with RMSE values of 7 mm, 6 mm, and 8 g, respectively. This study achieved in situ, high-throughput acquisition of lettuce phenotypic information under controlled environmental conditions, providing a lightweight solution for crop phenotypic information analysis algorithms tailored for inspection tasks.

To address the problems of traditional methods that rely on destructive sampling, the poor adaptability of fixed equipment, and the susceptibility of single-view angle measurements to occlusions, a non-destructive and portable device for three-dimensional phenotyping and biomass detection in lettuce was developed. Based on the Structure-from-Motion Multi-View Stereo (SFM-MVS) algorithms, a high-precision three-dimensional point cloud model was reconstructed from multi-view RGB image sequences, and 12 phenotypic parameters, such as plant height, crown width, were accurately extracted. Through regression analyses of plant height, crown width, and crown height, and the R2 values were 0.98, 0.99, and 0.99, respectively, the RMSE values were 2.26 mm, 1.74 mm, and 1.69 mm, respectively. On this basis, four biomass prediction models were developed using Adaptive Boosting (AdaBoost), Support Vector Regression (SVR), Gradient Boosting Decision Tree (GBDT), and Random Forest Regression (RFR). The results indicated that the RFR model based on the projected convex hull area, point cloud convex hull surface area, and projected convex hull perimeter performed the best, with an R2 of 0.90, an RMSE of 2.63 g, and an RMSEn of 9.53%, indicating that the RFR was able to accurately simulate lettuce biomass. This research achieves three-dimensional reconstruction and accurate biomass prediction of facility lettuce, and provides a portable and lightweight solution for facility crop growth detection.

Field surface topography and tillage depth are crucial information for guiding crop production. However, the separate measurement of field surface topography and tillage depth increases production costs. To address issues, this study proposes an integrated measurement method for field surface topography and tillage depth in rotary tillage operations. Based on the operational characteristics of the rotary tiller, a simultaneous measurement method for field surface and the tillage bottom-layer topography (FS-TBLSM) was proposed. Building on this, a method was developed to arrange grid points, referred to as the directional adaptive gridding method in plane topography (DAG-PT), and a sample-approximated Gaussian process regression (SA-GPR) algorithm was used to estimate the field surface topography height and tillage depth at a given grid point. The accuracy of these methods was evaluated using verification and field tests. The verification results showed that the FS-TBLSM method achieved a static root mean square error (RMSE) of less than 15.00 mm along all three axes, with dynamic RMSEs below 20.00 mm, confirming the effectiveness of the FS-TBLSM method and its good dynamic tracking capability. Further field test results indicated that the field surface topography measured using the FSTBLSM method aligned with the true topography. The measured field surface topography height exhibited an average absolute error (AAE) of 18.13 mm and an RMSE of 20.58 mm, validating the accuracy and reliability of this method for field surface topography measurement. Using true surface topographic height and tillage depth at 20 points as references, an AAE and RMSE of 17.13 and 17.95 mm, respectively, were obtained for surface topographic height estimation; estimated tillage depth exhibited an AAE and RMSE of 14.52 and 16.49 mm, respectively. These results demonstrate that the SA-GPR algorithm can accurately estimate the field surface topography height and tillage depth after rotary tillage operations. The integrated measurement method performs the measurement in a single operation, reducing the number of field operations by 50 %, saving an estimated 15.57 kg/ha in fuel consumption. Additionally, this study provides key inputs for leveling operations, including setting the base height, calculating earthwork volume, and planning paths. It also supports active control of seeding depth and provides references for yield assessment.

The unmanned farm control platform is of great significance in promoting the supervision of farm production with less manpower or autonomous operation of farm machinery and the construction of farm informatization. Addressing the existing control platform for farm location information acquisition is time-consuming, labor-intensive, and lacks the whole process control of multiple types of farm machinery. In this paper, we propose an Internet of Things (IoT) control scheme for intelligent farm machinery operation of unmanned farms and design the access standards for multiple types of farm machinery, as well as realize the remote control of intelligent farm machinery operation by constructing a remote control model. A high-precision map construction method is designed to improve the DeepLabV3+ algorithm to identify fields and roads. The control models of path planning, remote task, remote control, and safety system are built to achieve the remote control of intelligent agricultural machinery operation. The proposed technology is implemented in the platform integration and application tests are carried out. The error of the constructed high-precision map is less than 3 cm, the completeness rate of the automatic boundary extraction rate is 96.71%, and the correctness rate is 95.63%, which can be used to obtain the boundary instead of manual labeling or on-site point picking. The use of the platform for the simultaneous control of three farm machinery operations reduces the number of people in operation and production and reduces the professional requirements of the personnel, which will promote the management of the entire farm by one person or even by no one in the future.

Path planning is one of the key technologies that determines the efficiency and quality of field operations using autonomous agricultural machinery. To date, there has been extensive research on global coverage path planning for unmanned agricultural machinery within the working area; however, the issue of "encircling and edging" left by the machinery during headland turns is often overlooked. This study focuses on the operational conditions of unmanned agricultural machinery in the rice fields of southern China. The path planning problem is abstracted under physical constraints, such as the space at the field headland, the agricultural environment (e.g., types of field ridges), the turning characteristics of the machinery, turning radius, working width, and minimum safety distance, into mathematical constraints. This yields an optimized path planning model and sequence combination. Based on the improved Reeds-Shepp curve, an en-circling and edging path planning algorithm is designed. The planned path for the unmanned agricultural machinery from start to finish consists only of arcs and straight lines, suitable for the right-angle turning, reversing, and 180 degrees U-turn operations required for rice field machinery, thus significantly improving the coverage of field edges and missed areas at the headland. A rice directseeding machine was used as a test subject for encircling and edging field trials, with tests conducted in rectangular, trapezoidal, and irregular quadrilateral rice fields. The results show that, for rectangular plots, the fullfield coverage rate of rice direct-seeding operations can reach 96.44%; for trapezoidal plots, the coverage rate is 95.47%; and for irregular quadrilateral fields, the coverage rate is 95.69%. These results are promising, indicating that the encircling and edging path planning based on the improved Reeds-Shepp curve can effectively increase the full-field coverage rate of unmanned agricultural machinery, improving work quality and meeting the needs of modernized, intelligent agricultural machinery operations.

Cutting-edge detection is a critical step in mechanized rice harvesting. Through visual cutting-edge detection, an algorithm can sense in real-time whether the rice harvesting process is along the cutting-edge, reducing loss and improving the efficiency of mechanized harvest. Although convolutional neural network-based models, which have strong local feature acquisition ability, have been widely used in rice production, these models involve large receptive fields only in the deep network. Besides, a self-attention-based Transformer can effectively provide global features to complement the disadvantages of CNNs. Hence, to quickly and accurately complete the task of cutting-edge detection in a complex rice harvesting environment, this article develops a Transformer Convolution Network (TCNet). This cutting-edge detection algorithm combines the Transformer with a CNN. Specifically, the Transformer realizes a patch embedding through a 3 × 3 convolution, and the output is employed as the input of the Transformer module. Additionally, the multi-head attention in the Transformer module undergoes dimensionality reduction to reduce overall network computation. In the Feed-forward network, a 7 × 7 convolution operation is used to realize the position-coding of different patches. Moreover, CNN uses depth-separable convolutions to extract local features from the images. The global features extracted by the Transformer and the local features extracted by the CNN are integrated into the fusion module. The test results demonstrated that TCNet could segment 97.88% of the Intersection over Union and 98.95% of the Accuracy in the unharvested region, and the number of parameters is only 10.796M. Cutting-edge detection is better than common lightweight backbone networks, achieving the detection effect of deep convolutional networks (ResNet-50) with fewer parameters. The proposed TCNet shows the advantages of a Transformer combined with a CNN and provides real-time and reliable reference information for the subsequent operation of rice harvesting.

To improve the GNSS receiver's accuracy, continuity, and stability in measuring the height of agricultural implements, this study proposed a variable -parameter Kalman filter (VPKF) algorithm based on GNSS and accelerometer to estimate the height of the implements optimally. The VPKF was verified, and its accuracy was evaluated by parallel rail platform and field tests. From the parallel rail test results, when the GNSS receiver was in real -time kinematic (RTK) positioning and the time delay of differential correction data (TDDCD) was less than or equal to 4 s, the root mean square error (RMSE) of the VPKF estimation was 9.82 mm. The RMSE of the GNSS measurement was 18.85 mm. When the GNSS receiver lost differential correction data within 28 s, the absolute error of VPKF was less than 30 mm, and the RMSE was 16.93 mm. The field test results showed that when the GNSS receiver was in RTK positioning and the TDDCD was less than or equal to 4 s, the RMSE of VPKF estimation was 13.43 mm, and the GNSS measurement was 14.56 mm. When the GNSS receiver lost differential correction data within 28 s, the RMSE of the VPKF estimate was 15.22 mm. These results show that VPKF can optimally estimate implement height with better accuracy. Overall, the VPKF can obtain a more accurate, continuous, and stable height of the implement, and increase the application scenarios of the GNSS receiver to measure the implement height.

Path planning is one of the key technologies that determines the efficiency and quality of field operations using autonomous agricultural machinery. To date, there has been extensive research on global coverage path planning for unmanned agricultural machinery within the working area; however, the issue of “encircling and edging” left by the machinery during headland turns is often overlooked. This study focuses on the operational conditions of unmanned agricultural machinery in the rice fields of southern China. The path planning problem is abstracted under physical constraints, such as the space at the field headland, the agricultural environment (e.g., types of field ridges), the turning characteristics of the machinery, turning radius, working width, and minimum safety distance, into mathematical constraints. This yields an optimized path planning model and sequence combination. Based on the improved Reeds–Shepp curve, an encircling and edging path planning algorithm is designed. The planned path for the unmanned agricultural machinery from start to finish consists only of arcs and straight lines, suitable for the right-angle turning, reversing, and 180° U-turn operations required for rice field machinery, thus significantly improving the coverage of field edges and missed areas at the headland. A rice direct-seeding machine is used as a test subject for encircling and edging field trials, with tests conducted in rectangular, trapezoidal, and irregular quadrilateral rice fields. The results show that, for rectangular plots, the full-field coverage rate of rice direct-seeding operations can reach 96.44%; for trapezoidal plots, the coverage rate is 95.47%; and for irregular quadrilateral fields, the coverage rate is 95.69%. These results are promising, indicating that the encircling and edging path planning based on the improved Reeds–Shepp curve can effectively increase the full-field coverage rate of unmanned agricultural machinery, improving work quality and meeting the needs of modernized, intelligent agricultural machinery operations.

Weeds in paddy fields can seriously reduce rice yield. An intra-row weeding device with double-layer elastic rods was designed, considering the differences in mechanical properties between rice and weeds, which can press weeds into the soil and avoid damaging rice. The elastic force of the elastic rods can be adjusted by changing the position of the regulating mechanism to adapt to different weeding conditions. A measurement experiment was conducted to determine the variation rule of elastic force. The quadratic orthogonal rotation combination discrete element simulation experiment, which used weeding depth and weeding speed as experimental factors, and the amount of soil disturbance and the force of the inner and outer elastic rod in the horizontal and vertical directions as experimental indicators, was conducted to study the interaction between the weeding device and the soil. The optimal weeding parameters were obtained: the weeding depth was 15 mm, the weeding speed was 0.9 m/s. The field experiment, which used the various parameters of the weeding device as experimental factors and the weeding rate and damaging seedling rate as experimental indicators, was conducted to determine the weeding effect. The experimental results showed that the optimal position of the regulating mechanism was 270 mm, with a weeding rate of 80.65% and a damaging seedling rate of 3.36%. The weeding rate can be increased by at least 11.18% by adjusting the regulating mechanism to a suitable position under the same weeding conditions. This study can provide a reference for research on weeding machinery for organic rice.

Land leveling technology is necessary for land cultivation and is an important support for sustainable agricultural development. First, this paper reviews the current status of land-leveling implements, including dry-land and paddy-field leveling implements. Second, two precision land-leveling technologies, laser-controlled systems and the Global Navigation Satellite System (GNSS), are reviewed. The current status of laser-controlled leveling technology is considered in terms of its three primary components, the laser transmitter, laser receiver, and control terminal. The current status of GNSS-controlled leveling technology is also considered in terms of three aspects: three-dimensional (3D) topographical measurement of farmland, calculation of reference height and soil volume, and planning of work paths. The actual benefits of land-leveling technology applied to the production of different crops are statistically analyzed using metrics including improved land utilization, water savings, and increased yields. Finally, the challenges and future trends in land-leveling implements and technologies are discussed.

In order to solve the positioning problem of global navigation satellite system（GNSS） based robots and autonomous agricultural machinery, which is low accuracy or even unable to locate under the environment of weak or no satellite signals such as hangars and greenhouses. This research proposes an agricultural robot positioning system based on laser sensing. The system is designed by using two-dimensional laser scanner and laser receiver, which obtains the point cloud of the laser receiver on the robot through the scanning laser emitted by the two-dimensional laser scanner, and the laser receiver inductively scans by the laser scanner, the location of mobile laser receiver（i.e. agricultural robot） is obtained by fusing the time difference of laser scanning induction and the point cloud characteristics of mobile laser receiver. The agricultural robot positioning system based on laser sensing consists of mobile laser receiver, processor, fixed laser receiver and two-dimensional laser scanner. The mobile laser receiver and processor are installed on the robot, and the fixed laser receiver and two-dimensional laser radar are fixed at the known geodetic coordinate position. According to the position relationship between the laser scanner coordinate system and the known geodetic coordinate system. The laser scanner scanning at a certain period to obtain a known number of fixed-order point cloud data. The fixed laser receiver senses the periodic irradiation of the laser scanner to generate the base station laser signal, and the serial number of the fixed laser receiver shell in the point cloud is known. The mobile laser receiver senses the periodic irradiation of the laser radar to generate the mobile laser signal during the movement of the robot. According to the trigger time difference between the fixed laser signal and the mobile laser signal, the angle between the laser rays that are irradiated to the mobile laser receiver and the laser rays that are irradiated to the fixed laser receiver can be obtained in a scanning period of the laser scanner. And the scattered point set of the mobile laser receiver in the laser radar point cloud can be found, and the center coordinate of the mobile laser receiver can be obtained by combining the point cloud feature matching algorithm. The robot positioning can be calculated by combined with the geodetic coordinates of the laser scanner and the position relationship between the laser scanner coordinate system and the geodetic coordinate system, the central coordinates of the mobile laser receiver under the geodetic coordinate system. The geodetic coordinates of the robot are calculated by the positioning algorithm based on laser sensing, and the geodetic coordinates of the robot without GNSS signal are supplemented without changing the positioning solution and control algorithm of the existing robot unmanned system. For example, when the robot leaves the hangar, it switches to the GNSS positioning system for positioning and navigation in the area with both the positioning signals of the robot positioning system based on laser perception and the GNSS signal. When entering the hangar, switch to the robot positioning system based on laser sensing for positioning and navigation in the area cover with both the positioning signal of the robot positioning system based on laser perception and the GNSS signal. The verification test is carried out with the reference of total station which shows that within the scanning range of laser radar, when the robot is at a speed of 0.8 m/s, the absolute average value of the maximum deviation of the positioning error in a straight line is 4.1 cm, and the maximum root mean square error is 1.5 cm; when the robot driving on a curve, the absolute average value of the maximum deviation of positioning error is 6.2 cm, and the maximum root mean square error is 2.6 cm. The result shows that this method can achieve accurate robot positioning and meets the positioning accuracy requirements for automatic navigation of agricultural robots in agricultural machinery warehouses and other environments.

Rice lodging is a crucial problem in rice production. Lodging during growing and harvesting periods can decrease rice yields. Practical lodging judgment for rice can provide effective reference information for yield prediction and harvesting. This article proposes a binocular camera-based lodging judgment method for rice in real-time. As a first step, the binocular camera and Inertial Measurement Unit (IMU) were calibrated. Secondly, Census and Grayscale Level cost features are constructed for stereo matching of left and right images. The Cross-Matching Cost Aggregation method is improved to compute the aggregation space in the LAB color space. Then, the Winner-Takes-All algorithm is applied to determine the optimal disparity for each pixel. A disparity map is constructed, and Multi-Step Disparity Refinement is applied to the disparity map to generate the final one. Finally, coordinate transformation obtains 3D world coordinates corresponding to pixels. IMU calculates the real-time pose of the binocular camera. A pose transformation is applied to the 3D world coordinates of the rice to obtain its 3D world coordinates in the horizontal state of the camera (pitch and roll angles are equal to 0). Based on the distance between the rice and the camera level, thresholding was used to determine whether the region to be detected belonged to lodging rice. The disparity map effect of the proposed matching algorithm was tested on the Middlebury Benchmark v3 dataset. The results show that the proposed algorithm is superior to the widely used Semi-Global Block Matching (SGBM) stereo-matching algorithm. Field images of rice were analyzed for lodging judgments. After the threshold judgment, the lodging region results were accurate and could be used to judge rice lodging. By combining the algorithms with binocular cameras, the research results can provide practical technical support for yield estimation and intelligent control of rice harvesters.