Smart Agriculture

Advances and Progress of Agricultural Machinery and Sensing Technology Fusion | Open Access

CHEN Xuegeng, WEN Haojun, ZHANG Weirong, PAN Fochu, ZHAO Yan

2020, 2(4): 1-16. doi:10.12133/j.smartag.2020.2.4.202002-SA003

Asbtract ( 3939 )

HTML ( 7684)

PDF (2650KB) ( 3008 )

References | Related Articles | Metrics

Agricultural machinery and equipment are important foundations for transforming agricultural development methods and promoting sustainable agricultural development, as well as are the key areas and core supports for promoting agricultural modernization. In order to clarify the development ideas of agricultural machinery informatization and find the key development directions, and vigorously promote the development of agricultural machinery intelligentization, the development status of foreign agricultural machinery and sensing technology fusion were analyzed in this article, and five major development characteristics: 1) development towarding digitalization, automation and informationization, 2) applying sensing technology to the design and manufacturing of agricultural machinery equipment, 3) rapidly developing of animal husbandry machinery sensing technology, 4) focusing on resource conservation and environmental protection, and sensing technology promoting sustainable agricultural development, and 5) towarding intelligent control, automatic operation and driving comfort development were summarized. Among them, some advanced intelligent agricultural machinery were introduced, including the German Krone BiGX700 self-propelled silage harvester, an automatic weeding and fertilization robot developed by the Queensland University of Technology in Australia—Agbot II, and John Deere CP690 self-propelled baler Cotton machine, etc. After that, the new characteristics of the development of agricultural mechanization in China were summarize, and the viewpoint was pointed out that although the current development of agricultural mechanization in China had achieved remarkable results, there were still problems such as low intelligence and informatization of agricultural machinery, and insufficient fusion of agricultural machinery and informatization. Then the prospects for the development of China's agricultural machinery and sensing technology fusion were put forward, including 1) promoting the development of intelligent perception technology and navigation technology research, 2) promoting the intelligentization of agricultural machinery and equipment, and building an agricultural intelligent operation system, 3) promoting the research of agricultural machinery autonomous operation technology and the construction of unmanned farms, and 4) strengthening the technical standard formulation of agricultural machinery informatization and the training of compound talents. The fusion of agricultural machinery and sensing technology can realize the effective and diversified fusion of agricultural mechanization and sensing technology, maximize the guiding effect of informatization, improve the efficiency of agricultural production in China, and promote the development of digital agriculture and modern agriculture.

Research Status and Development Direction of Design and Control Technology of Fruit and Vegetable Picking Robot System | Open Access

WU Jianqiao, FAN Shengzhe, GONG Liang, YUAN Jin, ZHOU Qiang, LIU Chengliang

2020, 2(4): 17-40. doi:10.12133/j.smartag.2020.2.4.202011-SA004

Asbtract ( 3685 )

HTML ( 4156)

PDF (2346KB) ( 5111 )

References | Related Articles | Metrics

Vegetable and fruit harvesting is the most difficult production process to achieve mechanized operations. High-efficiency and low-loss picking is also a worldwide problem in the field of agricultural robot research and development, resulting in few production and application equipment currently on the market. In response to the demand for picking vegetables and fruits, to improve the time-consuming, labor-intensive, low-efficiency, and low-automation problems of manual picking, scholars have designed a series of automated picking equipment in the recent 30 years, which has promoted the development of agricultural robot technology. In the research and development of fresh vegetable and fruit picking equipment, firstly, the harvesting object and harvesting scene should be determined according to the growth position, shape and weight of the crop, the complexity of the scene, the degree of automation required, through complexity estimation, mechanical characteristics analysis, pose modeling and other methods clarify the design requirements of agricultural robots. Secondly, as the core executor of the entire picking action, the design of the end effector of the picking robot is particularly important. In this article, the structure of the end effector was classified, the design process and method of the end effectors were summarized, the common end effector driving methods and cutting methods were expounded, and the fruit collection mechanism was summarized. Furthermore, the overall control scheme of the picking robot, recognition and positioning method, adaptive control scheme of obstacle avoidance method, quality classification method, human-computer interaction and multi-machine cooperation scheme were summarized. Finally, in order to evaluate the performance of the picking robot overall, the indicators of average picking efficiency, long-term picking efficiency, harvest quality, picking maturity rate and missed picking rate were proposed. The overall development trend was pointed that picking robots would develop toward generalization of picking target scenes, diversified structures, full automation, intelligence, and clustering were put forward in the end.

State-of-the-Art and Prospect of Automatic Navigation and Measurement Techniques Application in Conservation Tillage | Open Access

WANG Chunlei, LI Hongwen, HE Jin, WANG Qingjie, LU Caiyun, CHEN Liping

2020, 2(4): 41-55. doi:10.12133/j.smartag.2020.2.4.202002-SA002

Asbtract ( 1426 )

HTML ( 1715)

PDF (2504KB) ( 1258 )

References | Related Articles | Metrics

Intelligent technology is one of the important approaches to improve working quality and efficiency of conservation tillage machine. Automatic navigation and measurement & control technology, which are the key components of intelligent technology, have been rapidly developed and applied in conservation tillage. In this paper, the application progress of automatic navigation and measurement & control technology in conservation tillage, including automatic guidance technology, operation monitoring technology for operating parameters and operation controlling technology of conservation tillage machine were reviewed. Firstly, wheat-maize planting mode was taken as an example to expound the automatic guidance technology for conservation tillage machine due to many types of crop planting modes under conservation tillage. According to the principle of navigation, it could be divided into automatic guidance technology of touch type, automatic guidance technology of machine vision type and automatic guidance technology of GNSS type. From these different automatic guidance technologies for no/minimum tillage seeding in maize stubble field, the application progress of automatic navigation technology in conservation tillage machine was introduced in detail. Secondly, the development of the operation monitoring technology for operating parameters of conservation tillage machine was systematically presented as follows: 1) The rapid detection technology for surface straw coverage, including surface straw coverage before and after operation, which was of great significance for the determination of conservation tillage technology and the evaluation of the performance of the conservation tillage machine; 2) The monitoring technology for seeding parameters of no/minimum tillage planter, mainly contained seeding quantity, missed seeding and multiples seeding, which were the key indicators for seeding quality; 3) The monitoring technology for operating area of conservation tillage machine, which was mainly calculated based on the forward speed of the testing machine. Thirdly, the development status of operation controlling technology for conservation tillage machine was reviewed, mainly focusing on the compensation and controlling technology for missed seeding and operation depth controlling technology. The operation controlling technology for conservation tillage machine, which was capable of realizing certain active control of the machine key components under the condition of accurate and real-time monitoring of the current operation status of conservation tillage machine, was important for working quality. To be specific, the operation depth controlling technology was composed of seeding depth, subsoiling depth and topsoil tillage depth. In the end, on the basis of summarizing the current application of automatic navigation and measurement technology in conservation tillage, the future research directions of automatic guidance technology, operation monitoring technology for operating parameters, and operation controlling technology in conservation tillage machine were prospected.

Vision Servo Control Method and Tapping Experiment of Natural Rubber Tapping Robot | Open Access

ZHOU Hang, ZHANG Shunlu, ZHAI Yihao, WANG Song, ZHANG Chunlong, ZHANG Junxiong, LI Wei

2020, 2(4): 56-64. doi:10.12133/j.smartag.2020.2.4.202010-SA001

Asbtract ( 1196 )

HTML ( 238)

PDF (1923KB) ( 1105 )

References | Related Articles | Metrics

Automated rubber tapping not only frees the workers from heavy physical labor and harsh working conditions, but also reduces the dependence on the workers' skills and greatly increases tapping efficiency. The key technologies for tapping robots are the independent acquisition of operational information and servo control of the tapping position in unstructured environments. In this study, taking rubber tree in rubber plantations as object, incorporating robot kinematics, machine vision technology and multi-sensor feedback control technology, a modular prototype of a rubber tapping robot was developed. The rubber tapping robot was mainly composed of an orbital mobile platform, a multi-joint robotic arm, a binocular stereo vision system and an end-effector. The binocular stereo vision and structured light system were used to obtain the structural parameters of the rubber trunk and secant. A six-joint tandem robotic arm was used for the planning and realization of complex rubber tapping trajectories. An multi-sensor fusion end-effector was developed to complete the identification of the starting point, the measurement of cut compensation and the tapping operation. To address the technical difficulties in rubber tapping operations, such as complex and variable environment, superimposed interaction of operational information, similar target background features and sub-millimeter operational accuracy requirements, the spatial mathematical model of the rubber tapping trajectory was established to plan the robot's movement path for fast approaching and moving away from the operation space. The results of the field tests conducted at a natural rubber plantation in Hainan province showed that the accuracy in bark consumption was about 0.28 mm and the accuracy in cutting depth was about 0.49 mm when the rubber tapping robot cut 1 mm thick bark. Compared to manual operations, the continuity of the chips and the flatness of the rubber output surface were improved significantly. This research could provide a positive reference and development direction for exploring automated rubber tapping operations.

Visual Positioning and Harvesting Path Optimization of White Asparagus Harvesting Robot | Open Access

LI Yang, ZHANG Ping, YUAN Jin, LIU Xuemei

2020, 2(4): 65-78. doi:10.12133/j.smartag.2020.2.4.202009-SA003

Asbtract ( 1050 )

HTML ( 1001)

PDF (3495KB) ( 923 )

References | Related Articles | Metrics

For white asparagus selective harvesting is the best harvesting method determined by its growth characteristics. Focusing on the difficulties that the texture and the color of shoot tips are similar with ridge surface under machine vision, the recognition method of asparagus shoots and precise positioning were studied in this research. A changeable scale ROI detection method was proposed, with the fusion of color transformation, histogram averaging, morphology and texture filtering. After that, a harvesting path optimization method of multiple asparaguses was proposed, which solved the problem of harvesting efficiency reduction caused by unreasonable harvesting paths. Firstly, real-time acquisition of the image and individual RGB channel Gaussian filtering were implemented. Based on the HSV color transformation and histogram averaging processing, the asparagus shoot and soil feature clustering analysis were carried out. According to the sprout degrees of asparaguses, the changeable scale ROI detection method was studied. The morphology and the texture of the shoot, and soil were statistically analyzed. According to the texture feature parameters, the position of shoot was determined and its geometric center was calculated. Secondly, in order to improve harvesting efficiency, a path optimization algorithm based on multiple asparaguses was designed according to the locations of the asparaguses and the bins to obtain the optimal harvesting path. Finally, in order to verify the reliability of the proposed methods, asparagus shoot location and harvest verification tests were carried out on the established harvesting test platform. The results showed that the recognition rate of white asparagus in the visual system was more than 98.04%, the maximum positioning error of the center coordinate of the white asparagus shoot was 0.879 mm in X direction and 0.882 mm in Y direction, and the average reduction of end-effector motion distance could be 43.89% after path optimization under different circumstances, the success rate of end-effector localization was 100% and the harvest rate of white asparagus in the laboratory test was 88.13%. The research verified the feasibility of the visual positioning and harvesting path optimization of the white asparagus selective harvesting robot.

Design and Test of Disinfection Robot for Livestock and Poultry House | Open Access

FENG Qingchun, WANG Xiu, QIU Quan, ZHANG Chunfeng, LI Bin, XU Ruifeng, CHEN Liping

2020, 2(4): 79-88. doi:10.12133/j.smartag.2020.2.4.202010-SA005

Asbtract ( 1482 )

HTML ( 628)

PDF (2302KB) ( 1246 )

References | Related Articles | Metrics

In order to improve the efficiency and safety of epidemic prevention and disinfection operations for livestock and poultry breeding, the disinfection robot system and the automatic disinfecting mode were researched in this study. The robot system is composed of four components, namely the automatic bearing vehicle, the disinfection spraying unit, the environmental monitoring sensors, and the controller. The robot supports two working modes: fully automatic mode and remote control mode. Aiming at the low-light and low-stress condition in the livestock and poultry houses, the method for detecting navigation path based on "Magnet-RFID" marks in the ground was proposed to realize the robot's automatic moving between the cages. In view of the large-flow and long-range requirements of the disinfectant's spraying, the air-assisted nozzle was designed, which could atomize and disperse the liquid independently. Based on the CFD simulation of airflow in the nozzle, the nozzle's parts structural parameters were optimized, as the angle of the cone-shaped guide pad and the inclination angle of the grid respectively determined as 75°and 90°. Finally, the robot's performance was tested in a poultry house in Beijing. The results showed that, the robot's mobile platform could automatically navigate at the speed of 0.1－0.5 m/s, and the maximal deviation distance between the actual trajectory and the expected path was 50.8 mm. The air-assisted nozzle could realize the atomization and diffusion of the liquid medicine at the same time, and was suitable for spraying the liquid medicine with a flow rate of 200－400 mL/min. The diameter (DV.9) of the liquid droplets formed was 51.82－137.23 μL, and became larger as the flow rate of the liquid medicine increased. The deposition density of spray droplets formed by the nozzle was 116－149/cm², and decreased as the spray distance increased. The size and density of the liquid droplets of the spray nozzle in different areas of the cage all met the index requirements for effectively killing adherent pathogenic microorganisms. The robot could be applied as an automatic sprayer for disinfectant and immune reagent in the livestock and poultry house.

Visual Navigation System for Wheel-Type Grain Combine Harvester | Open Access

DING Youchun, WANG Xuping, PENG Jingye, XIA Zhongzhou

2020, 2(4): 89-102. doi:10.12133/j.smartag.2020.2.4.202010-SA002

Asbtract ( 891 )

HTML ( 271)

PDF (3064KB) ( 690 )

References | Related Articles | Metrics

Due to the short harvest period after grain ripening, the heavy of harvest tasks, the complicated operation of the combined harvester and the high driver's labor intensity, it is difficult to maintain the consistency of high cutting rate and cutting width of combined harvester. Based on computer vision, the combined harvester navigation method is being used to realize real-time control of the cut width of the combine harvester. To improve the working quality and efficiency of the wheel grain combine harvest, visual navigation control system was built in this research, it was composed of industrial camera, rear wheel angle measurement device, electro-hydraulic steering valve set, control box and notebook computer, etc. The industrial camera was mounted on the light frame of the front left turn of the combine harvester to capture the image information of the front field view of the harvester. The rear wheel angle measurement device was installed on the steering wheel bridge of the harvester, and the change and position of the rear wheel angle were fed back in real time. The steering cylinder was directly driven bypass connection way outside the electro-hydraulic steering valve set to make the rear wheel of the harvester turning. The control box integrated data acquisition card, power supply module, power amplifier, etc., for steering wheel control and steering wheel angle information measurement. As the main controller of the system, the notebook computer run the visual navigation software for image processing and deviation correction control, realized the automatic navigation process control of the combined harvester. Combined with OpenCV, a target path detection algorithm was designed to identify the boundary of harvested and non harvested paddy fields. After preprocessing, secondary edge segmentation and line detection, the forward-looking target path of visual navigation operation of combine harvester was obtained, and field dynamic calibration was carried out according to the relative position information of forward-looking path to obtain the full range harvesting status of combine harvester. A visual navigation tracking control method based on the front viewpoints was proposed in this research, through rectifying control implemented to maintain full cutting length at the same time prevent the leakage cut of crops, with full cut deviation, the front viewpoints pixel deviation and real-time steering rear corner as visual navigation controller input. The output steering wheel voltage was controlled according to the rectifying strategy. The results of paddy field experiments showed that the navigation system could basically realize the reliable acquisition of the position and the stable implementation of the target linear path tracking control. Under the condition that the field illumination conforming to the normal operation of human eyes, the detection accuracies of the image processing algorithm were higher than 96.28%, and the detection times of a single frame were less than 50 ms. Under the conditions that the nominal cutting width of the harvester was 2.56 m, the average full cutting width rate of visual navigation was 94.16%. Compared with the boundary of the first row, the straightness accuracy of the second row was increased by 44.92%. The research could provide technical support for the combine harvester to automatically navigate the operation of full cutting width.

Automatic Weed Detection Method Based on Fusion of Multiple Image Processing Algorithms | Open Access

MIAO Zhonghua, YU Xiaoyao, XU Meihong, HE Chuangxin, LI Nan, SUN Teng

2020, 2(4): 103-115. doi:10.12133/j.smartag.2020.2.4.202010-SA006

Asbtract ( 1301 )

HTML ( 1550)

PDF (4725KB) ( 1107 )

References | Related Articles | Metrics

Automatic weeding is a hot research field of smart agriculture, which has many benefits such as achieving precise weed control, saving human cost, and avoiding damage on crops, etc. Recently, many researchers have focused on the research using the deep learning method, such as the convolutional neural network (CNN) and recurrent neural network (RNN) and have achieved decent outcomes related to the automatic weed detection. However, there are still generally problems of the projects such as weak robustness and excessive reliance on a large number of samples. To solve these problems, a recognition algorithm for automatic identification and weed removal was designed, and a soybean field weed detection and localization method based on the fusion of multiple image processing methods was proposed in this study. The images and video stream were obtained through the camera mounted on a mobile robot platform. Firstly, the soil background inside the image was segmented from the foreground (including the weeds and crops) by setting the threshold for a specific color space (hue). Then, three different methods including the area threshold method, template matching and saturation threshold method were used to classify the crops and weeds. Finally, based on a proposed innovative voting method, the three recognition methods were comprehensively weighed and fused to achieve more accurate recognition and localization results of the crops and weeds inside the image. Experimental validations were carried out using the samples obtained through the moving platform, and the experimental results showed that the average accuracy of the proposed weed detection algorithm was as high as 98.21%, while the recognition error was only 1.79%. Meanwhile, compared with each single method as the scale threshold, template matching and saturation threshold, the fused method based on the weighted voting has been able to raise the average accuracy by 5.71%. Even though the samples used in the validations were limited in covering different scenarios, the high recognition accuracy has proved the practicability of the proposed method. In addition, the robustness test that images with raindrop and shadow interference in the complex and unstructured agricultural scene was carried out, and satisfied results showed that above 90% of the plant were successfully detected, which verified the fine adaptability and robustness of the proposed method.

Construction of Standard System Framework for Intelligent Agricultural Machinery in China | Open Access

HU Xiaolu, LIANG Xuexiu, ZHANG Junning, MEI Anjun, LYU Chengxu

2020, 2(4): 116-123. doi:10.12133/j.smartag.2020.2.4.202004-SA002

Asbtract ( 1261 )

HTML ( 584)

PDF (1107KB) ( 1014 )

References | Related Articles | Metrics

Standard system is the overall strategic planning and implementation guidance for standardization in professional field. In view of the missing of standard system on intelligent agricultural machinery, a standard system framework was contributed for the industry of intelligent agricultural machinery in this study. Currently, in China, standardization work for the industry of intelligent agricultural machinery is carrying out unplanned and disorderly. Published standard is of limited number, and could not meet the industry needs. The adopted international standards take a high percentage of national standards, however, China-made intelligent agricultural machinery standard has not been promoted abroad. Based on the development goals and principles of standard system framework, 9 dimensions of level, binding force, generality, property, object, standard category, reference model, industry classification and industry sector were identified for the standard system framework of intelligent agricultural machinery. Three dimensional standard system framework was contributed for intelligent agricultural machinery. The level dimension included 5 elements of national standard, industry standard, local standard, group standard, and enterprise standard. The category dimension included 8 elements of safety, health, environmental protection, basic, methods, management, products, and others. The industry sector dimension included 9 elements of power machinery, seeding and fertilizing machinery, plant protection machinery, harvester, seed breeding and selection machinery, agricultural product storage and transport machinery, facility agriculture, livestock and poultry breeding machinery, and agricultural product processing machinery. In order to clear standard level and intuitively guide standard system table development, the three dimensional standard system framework was decomposed in two dimensions. The first layer was basis, included terminology, safety, environmental protection and reliability. The second layer was common features, included information perception, navigation and positioning, control communication, big data analysis, agricultural management platform. The third layer was applications, included operating power, seeding and fertilization, plant protection, harvesting, selection and breeding of seed, agricultural product storage, facility agriculture, livestock and poultry breeding, and agricultural product processing. Suggestions were proposed for standardization of intelligent agricultural machinery in China. Firstly, priorities of the standard system table should be worked out based on industry need and technological maturity. Secondly, practicability of the standard was suggested to be improved by developing the standard content based on industry needs and market prospect. In addition, a variety of resources of industry, university and research institute was suggested to be organized together to contribute to standardization work. In addition, the progress of international standardization was suggested to be tracked, and the China-made standard was suggested to be internationalized. Finally, the standardization work should be operated by the professional organizations and specialized talents. This standard system framework could be used to systematically guide the development, revision, implementation, and service of intelligent agricultural machinery standards, and lead the rapid development of intelligent agricultural machinery industry in China.

Effect of Downwash Airflow Field of 8-rotor Unmanned Aerial Vehicle on Spray Deposition Distribution Characteristics under Different Flight Parameters | Open Access

WANG Changling, HE Xiongkui, BONDS Jane, QI Peng, YANG Yi, GAO Wanlin

2020, 2(4): 124-136. doi:10.12133/j.smartag.2020.2.4.202003-SA005

Asbtract ( 1158 )

HTML ( 284)

PDF (2470KB) ( 1107 )

References | Related Articles | Metrics

Pesticide application using UAV sprayer has become a new highlight in the development of agricultural machinery and plant protection in China. Spray droplets from UAV could reach the crop canopy and deposit on the control target surface under the assistance of rotor's downwash airflow after atomization, including a secondary atomization effect of airflow on the droplets, so the spray performance of aerial pesticide application is inseparable from the effect of the rotor's downwash airflow field. In order to explore the effect of downwash airflow field on UAV's spray deposition characteristics, taking the main model of eight-rotor UAV with "X-type" as the research object and designing the actual measuring test, a multi-channel micro-meteorology measurement system(MMMS) was used to determine the downwash airflow speed at different horizontal positions, and meanwhile the tracer Allura Red solution was applied instead of chemicals to obtain the distribution characteristics of spray deposition. The visual analysis of the measured results of the downwash airflow field distribution was focused, and then the distribution characteristics of both the downwash airflow field and the droplet deposition at a certain flight height and speed, and the correlation relationship between them were analyzed. During the flight operation of the 8-rotor UAV, as the flight speed increased from 1.0 to 6.0 m/s and the flight height increased from 1 to 2 m, the intensity of the downwash airflow field in directions of X, Y, and Z generally changed from strong to weak, and the distribution state changed from concentration to dispersion; the X direction airflow was the vortex generated by the interaction between the downwash airflow and the outside air and its effect on droplets was reversed flight direction; the airflow in Y direction was to the both sides from flight path, caused by the combination of downwash airflow and ground effect; the airflow in Z direction, the vertical downward component of the downwash airflow, had a direct promotion effect on spray deposition. Significant negative correlations were shown between both the flying speed and the peak value in the range of the downwash airflow field (P <0.05, r = -0.836), and the flying speed and the average deposition within the effective spray swath(P <0.05, r = -0.833). When the flight speed was 1.0 and 3.0 m/s, the droplet deposition showed a very significant positive correlation with downwash airflow speed(P <0.01, r> 0), that was, the stronger the downwash airflow field in the vertical ground direction, the more droplets deposited in the effective spray swath. When the flight speed increased to 6.0 m/s, the wind speed was significantly reduced, and the promotion effect of the downwash airflow field on the droplet deposition disappeared(P> 0.05). The operation speed of UAV should not be set faster than 6.0 m/s to avoid the chemicals loss caused by the weakened effect of the downwash airflow field. The findings of this study are expected to provide theoretical basis and data support for improving the quality of low-altitude and low-volume application operations and the formulation of UAV field operations specifications.

Optimal Model of Chicken Distribution Vehicle Scheduling Based on Order Clustering | Open Access

CHEN Dong, Tian'en CHEN, JIANG Shuwen, ZHANG Chi, WANG Cong, LU Mengyao

2020, 2(4): 137-148. doi:10.12133/j.smartag.2020.2.4.202011-SA006

Asbtract ( 753 )

HTML ( 447)

PDF (2529KB) ( 704 )

References | Related Articles | Metrics

In order to solve the problems that orders are widely distributed, scheduling of distribution vehicle needs a lot of manpower,and high cost of chicken distribution in large-scale poultry enterprise, in this research, combined with the idea of solving vehicle routing optimization problem, a chicken distribution vehicle scheduling optimization model based on order location clustering was proposed. By introducing the K-means clustering algorithm, a distribution unit division method based on order location was implemented, an automated order location clustering process based on the elbow rule and contour coefficient method to realize the autonomous division of order distribution units was designed. On the basis of the divided groups of orders, the optimal delivery cost was taken as the objective function to establish a chicken delivery vehicle scheduling optimization model, and the model was solved with an improved genetic algorithm.The actual order data of a poultry company in Beijing was used to compare the results of the overall scheduling optimization in the case of orders without clustering and the scheduling optimization in the case of with clustering grouping. The results showed that the model in the case of orders with clustering could reduce the average daily mileage of delivery vehicles by 69% compared with orders without clustering, it could be seen that the optimization of order grouping with clustering algorithm was more suitable for vehicle scheduling scenarios with a large actual order position span and a large number of orders. Based on the above research, a vehicle scheduling optimization service system was developed, functions such as automatic order clustering, delivery vehicle scheduling optimization were realized, and model service application programming interface was customized.The practical application results of the model showed that, the average total mileage per day decreased by 5.04% compared with manual routing, the manual routing time took 20 to 30 minutes per day, and the average time for the model to complete the routing was 14.49 s. The goal of providing intelligent delivery vehicle scheduling optimization services for poultry industry enterprises has been achieved, which could effectively improve the operation efficiency and reduce the distribution cost of the poultry enterprise.

Design and Application of Hardware-in-the-Loop Simulation Platform for AGV Controller in Hybrid Orchard | Open Access

WU Yingxin, WU Jianqiao, YANG Yuhang, LI Mutong, GAN Ling, GONG Liang, LIU Chengliang

2020, 2(4): 149-164. doi:10.12133/j.smartag.2020.2.4.202010-SA004

Asbtract ( 742 )

HTML ( 897)

PDF (3760KB) ( 802 )

References | Related Articles | Metrics

The orchard is usually with a wide area, complex terrain, many trenches, overgrown weeds, high soil moisture and relatively loose soil, which greatly restrict the mechanization and intelligence, and put forward higher standards and requirements for the design of mechanical structure, control system and energy system of Automated Guided Vehicle(AGV). The hybrid automatic navigation vehicle can meet the need of long-distance movement in orchard. In order to explore the appropriate hybrid AGV control system algorithm and energy management strategy, and to reduce the manpower, material resources and time cost of the controller design process, firstly, according to the requirements of the current orchard construction on the terrain and soil, and corresponding to the GB/T 7031-2005, the orchard pavement level was divided into F grade and above. In addition, according to the requirment that orchard AGV needed to adapt to the characteristics of a wide range of terrain, the tracked vehicle model structure was adopted. Using the current hardware-in-the-loop simulation technology, raspberry pie was used as the control system to carry the control algorithm. Matlab and RecurDyn software were used to establish the system real-time simulation model which included energy power system, motor drive system, tracked vehicle driving model and road model. Finally, the hardware-in-the-loop simulation function of series hybrid AGV controller was realized. The simulation results of cascade PID and fuzzy controller control algorithm showed that the fuzzy controller control algorithm could reduce the time cost caused by parameter adjustment, and the response speed was increased by 50% when the steering angle was small. When the steering angle was large, the cascade PID controller produced 10% overshoot, while the fuzzy controller had no overshoot, and the steering was more stable. The simulation verification of energy management strategy based on deterministic rules and instantaneous optimization showed that the instantaneous optimization strategy could reduce fuel consumption by about 13.04%. The results showed that the hardware-in-the-loop simulation platform could be effectively applied to the development of orchard AGV controller, avoiding the control of physical experiments, reduce the cost and greatly speed up the development process.

Table of Content