Fruit and vegetable picking is an important part of agricultural production, and it relies heavily on manual labor. The development and application of picking robots will greatly reduce labor dependence of picking operations. The picking robotic arm is a key part of the picking robot and a major focus of research on the picking robot. This paper classified the picking manipulators by the degree of freedom, and summarized the development process and research status of the picking manipulators in China and the rest of the world. Aiming at the problem of lack of standardized solutions in thechoice of freedom and configuration of the picking robotic arm for the same fruit and vegetable in the same cultivation mode, it is proposed that indepth integration of the picking manipulator research and agronomy is the key to solving the problem in future. At the same time, considering that the rigid body is difficult to adapt to the picking environment as well as the joint drive mode being single, it is believed that the flexible design of the picking manipulator body and the combined use of the drive mode will be the future development trend.

With the continuous development of lotus root industry in China, the mechanized harvesting technology of lotus root has been paid more and more attention in China. The development of reliable lotus root harvesting machinery has become the most important part of the modernization process of lotus root industry in China. Therefore, this paper summarized and analyzed the characteristics and harvesting requirements of lotus root plants, compared and analyzed the lotus root harvesting machinery at home and abroad, summarized the types, advantages and disadvantages of lotus root harvesting machinery in China, listed the representative research and development achievements of lotus root harvesting machinery in China, and pointed out that the planting mode of lotus root was not uniform in China. The problems of low degree of automation and single mechanical structure and function of lotus root harvesting machinery were put forward. Combined with Chinas national conditions, some development suggestions were put forward, such as standardizing the regional standardized planting mode of lotus root, formulating the standard requirements of lotus root harvester and increasing the research on key technologies of lotus root harvesting machinery, so as to provide reference for the further development of lotus root harvesting machinery.

Yam planting in China has a long history and a wide range. Due to its own growth characteristics, geographical environment and planting mode, the mechanization degree of yam harvesting is relatively low, and manual harvesting is mostly used. With the development of industrial structure, the development degree of yam harvesting mechanization directly affects the economic benefits of farmers. This paper analyzes the planting characteristics of several yams in China, summarizes the main harvesting methods of several yams in China, expounds the research status and progress of main harvesting equipment and technology of yams such as walking system, transmission system, trenching system, soil turning vibration mechanism and positioning system, and briefly discusses the research on yam harvester in foreign countries. On this basis, it is pointed out that the mechanization of yam harvesting in China faces problems such as insufficient integration of agricultural machinery and planting environment, inconsistent planting mode, poor quality of harvesting machines and tools, lack of innovation and imperfect harvesting function, and relevant suggestions are put forward for the problems faced by the mechanized harvesting equipment of Yam as follows: developing the mechanized harvesting equipment of yam according to local conditions. Promoting the construction of planting regulations, learning from the development experience of developed countries, improving the innovation ability of core components, and developing combine harvesters.

Intelligent field weeding robots are an important manifestation of the modernization, refinement and intelligence of contemporary agricultural development, and are of great significance to national social development and environmental protection. In order to clarify the current research status of key technologies and equipment of intelligent weeding robots, the research status and operation modes of typical weeding robots were summarized from the aspects of weeding modes, identification and positioning of seedlings and grasses, and intelligent navigation modes. Then the importance and research progress of the key technologies of intelligent navigation, seedling and weed identification and weeding execution system were summarized. Combined with the research characteristics of weeding robot, such as complex and changeable operation environment, delicate operation object, special use object and seasonal operation, the existing problems of current key technologies were pointed out. According to the problems, the future development trends of integrated navigation technology, image processing technology of complex field environment, weed classification, research and development of interplant weeding terminal actuator and mechanical structure optimization are explained. 

 White radish is an important economic vegetable in China. It has the advantages of short growth cycle, strong adaptability and high yield. Based on the growth characteristics and planting patterns, a pulling white radish combine harvester is designed. The harvester is mainly composed of cherry blossom pulling device, soil ripping device, clamping device, rhizome separation device and collection devices, which can perform the combined harvesting operation including lifting, scarifying, conveying, cutting and collecting in series. In order to ensure the smooth entry of white radish stems and leaves into the gripper and avoid the stems and leaves from being pulled off, a lifter with conical opening is designed. By adjusting the conical opening angle of the lifter through active and underactuated combination, the adaptability of the prototype is improved under the condition of low planting line straightness and uneven ridge surface. In order to realize stable flexible pulling and gripping conveying, and avoid stem and leaf fracture in the process of pulling and conveying, a flexible gripper and gripper force adjusting device is designed. The gripper belt is composed of rubber in which the antiskid pattern is printed on the working surface. According to the growth environment, soil mechanical properties and operation stress characteristics of white radish, the structural parameters of the ripper are designed. Through finite element analysis and strength check, the performance and reliability of ripper are improved. To avoid the cutting damage caused by the shaking of white radish during the cutting process, and achieve the effect of smooth cutting and neat incision, a double disc cutter is designed. The field performance tests indicate that the working performance is stable, with the damage rate of 2.7%, the missed rate of 1.8% and the efficiency of 0.08~0.26hm2/h. The popularization and application of pulling white radish combine harvester will effectively reduce labor intensity and improve harvest efficiency, which is helpful for improving the mechanization level of white radish in China.

The identification of crop disease is related to crop yield and quality, and it is an essential part in the development of intelligent agriculture. With the rapid development of deep learning in the field of image processing, the method of identifying crop disease types from images by deep learning has gradually become the mainstream. In this paper, we mainly review the methods of crop disease recognition based on deep learning, briefly introduce deep learning and convolutional neural network, and collect some common public disease image datasets. According to the different collection environment of training sample, we summarize the progress of deep learningbased disease identification methods in recent years from two aspects of laboratory and field, point out their advantages and disadvantages of each method, and conclude that there are three main problems in this research field such as insufficient data, difficult task and complex network structure of deep learning model. On this basis, we propose that the establishment of largescale, multispecies, and multitype disease database and the design of highperformance deep learning model are important development directions in the future.

With the continuous development of facilities vegetable industry and the increasing demand for facilities vegetable, the realization of mechanization and intelligent operation production has become the necessary link in the modernization process of facilities vegetable industry. Although facilities vegetable area, output and production value are expanding, there is still a big gap with facilities agriculture developed countries such as Europe and the United States. In order to improve the level of industrial mechanization of facilities in China and develop reliable mechanical equipment, this paper summarizes the research status and development trends of modern facilities of vegetable operating machinery in America, Japan, Holland and other countries, and summarizes the types, advantages and disadvantages of facilities of vegetable operating machinery. It is pointed out that some problems exist in the process of vegetable production, such as mechanization, low degree of automation, poor adaptability of machines and machines, and relatively backward application of agricultural robots. Combining with the situation of Chinese facilities, this paper puts forward some countermeasures to strengthen research and development of intellectualized facilities, informationized facilities agricultural equipment, and promote the application of new materials and new agricultural robot technology, which will point out the direction and provide reference for the development of Chinese facilities vegetable mechanization.

Precision sowing can effectively reduce the number of seeds used, save costs and money, and the quality of crops grown through precision sowing is high. In order to grasp the development level of electronically controlled precision sowing technology at home and abroad, this paper carries out research from precision sowing online detection technology, sowing volume control technology and seed replenishment technology, focusing on the advantages and disadvantages of photoelectric sensor detection, piezoelectric sensor detection, capacitive sensor detection, visual image detection and precision sowing control technology; and points out the lack of standardization of precision sowing machines in China, insufficient research and development of high precision sensors, and immature intelligent control technology. Finally, combined with the current development situation at home and abroad, the development trend of Chinas precision sowing technology in the direction of multimachine collaboration, remote control and intelligent control is to provide some reference for future researchers to understand electronically controlled precision sowing technology in China.

In order to realize the mechanization and automation of strawberry picking in greenhouse, a strawberry picking robot used in solar greenhouse was designed and manufactured. The robot can realize autonomous path planning, identify mature strawberries and complete picking during walking. This design uses ROS distributed computing system as the main control network, uses laser radar to build and locate the map of mobile robot, binocular depth camera to identify and locate mature strawberries, and a 6-DOF mechanical arm equipped with flexible bionic grippers to grasp and place target strawberries. This paper also designs a robot software platform， using improved A* algorithm to achieve autonomous path planning and navigation obstacle avoidance; The R-FCN target detection network and binocular vision technology were used to detect and locate mature strawberries. The experimental results show that: the strawberry picking robot can achieve target detection and positioning, the error between the detected strawberry coordinates and the robots paw coordinates is less than 4 mm, and the recognition rate of mature strawberries is 95%, meeting the picking requirements.

With the advent of the era of agricultural intelligence, the application of robot technology in the field of intelligent picking in agriculture and fruit industry is becoming more and more extensive. As the core technology of picking operation, the advanced degree of path planning algorithm plays a decisive role in the efficiency and quality of picking operation. Therefore, according to the characteristics of path planning algorithm of picking mechanical arm, it can be divided into four categories such as swarm optimization algorithm, graph search algorithm, probability map algorithm (PRM) and rapidly expanding random tree algorithm (RRT), and based on the above classification, the representative research achievements of domestic and foreign scholars in recent years are introduced, the advantages and disadvantages of various path planning algorithm applied in picking operations are analyzed, and the feasibility, applicability and limitations of various algorithms are systematically summarized by comparison. Finally, the future development direction of path planning algorithm of picking mechanical arm is prospected, and specific suggestions on algorithm optimization are put forward, providing some ideas for path planning research of picking mechanical arm.

Shelling is an essential part of walnut postharvest processing and plays an important role in the development of walnut industry in China. At present, in most areas of China, walnut harvesting was mainly based on primary processing, timeconsuming and laborious, with low mechanization degree, and the problems of low kernel exposure rate and high breakage rate in the shelling link and so on, which had become a key problem affecting the rapid development of walnut industry. Based on the analysis of 6 typical walnut shelling equipments structure, shelling principle, advantages or disadvantages, and so on, this paper expounded the development situation of walnut shelling equipment at home and abroad at present. This paper summed up the problems of walnut shelling equipment in China and it included single function, high operation cost, performance instability, low efficiency, poor universality, low utilization rate and so on. Finally this paper put forward to some relative measures and suggestions of our country in future. We should optimize and improve the key technology and structure, strengthen the application research of new technology, new theory and new method of walnut shelling and develop large walnut shelling equipment, promote the processing capacity of enterprises.

The use of deep learning to accurately identify weeds to achieve the goals of pesticide reduction, efficiency and safety has been widely concerned by researchers. Therefore, the research progress of using deep learning algorithms to identify and detect weeds of different crops in recent years is reviewed at home and abroad. The review status is summarized from the aspects of data acquisition, algorithm selection, optimization and recognition effect. It points out that the problems of timeconsuming and laborious data set establishment, low accuracy of field recognition, algorithm equipment deployment difficulty, realtime performance and accuracy cannot be both, and also proposes solutions. Meanwhile, it prospects the development trend of easy and accurate data set establishment, lightweight and robust algorithm model structure, and easy deployment of mobile devices, and methods for future applications., which  will provide a reference for the subsequent research on precise weed removal.

Focusing on the wholeprocess mechanization of soybean and corn strip compound planting, management and harvesting, using the special machines and tools for synchronous operation such as soybean and corn integrated seeder, synchronous belt spray rod sprayer, soybean and corn integrated harvester, as well as the stepwise applicable machines and tools such as highclearance corn harvester and small narrowrange harvester as research object, depending on the development of test and application situation in recent years, this paper deeply analysises and summaries the technical characteristics, research and development production, test verification, application and points for attention, mastering the special machinery development present situation, improve the operating efficiency, operation quality, adaptability and key structure clearly machinery research and development trend, for soybean corn belt compound planting wholecoursing mechanization development lay the foundation. Centering on the improvement of ripening and popularization of machinery and tools, suggestions were put forward from the aspects of selection and breeding of simultaneous sowing and simultaneous ripening varieties, research on key technologies, formulation of identification and evaluation methods, selection of applicable machinery and tools models, experimental demonstration and popularization, and consolidation of wholeprocess mechanization modes.

In recent years, the growing global demand for Chinese herbal medicine (CHM) has led to a continually increase in planting area under CHM, and the demand for harvesting machines for Rhizome Chinese herbal medicine (RCHM) enlarges. At present, the harvesting methods of RCHM in China are still mainly manual harvesting and small & mediumsized excavator harvesting. The low level of mechanization and low production efficiency have seriously restricted the development of CHM industry. This paper briefly describes the current situation of planting CHM in China, and comprehensively analyzes the application and current situation of harvesting mechanization of RCHM, as well as focus on the research on the key components of excavation mechanical structure, separation mechanical structure and conveying mechanical structure. The main existing problems of RCHM harvester is summarized: the integration of agricultural machinery and agronomy is insufficient, the enthusiasm for developing combine harvesters is not high, lack of systematic research on harvest rate and damage rate, and lack of research on intelligent regulation technology of harvesting operation. This paper expounds lowconsumption and deepexcavation technology, flexible and low loss technology and intelligent control technology are the future development trend of mechanization of RCHM in China. In order to provide reference for the research of RCHM harvesters, so as to promote the further development of harvesting mechanization of RCHM.

The aquaponic planting and breeding technology is a new type of composite breeding technology with multidisciplinary integration. It combines aquaculture and crop cultivation organically to realize the recycling of farming and production, and can effectively improve the negative impact of the traditional aquaculture mode on the discharge of large quantities of aquaculture tail water, environmental pollution and resource waste. In recent years, the aquaponic planting and breeding technology has developed rapidly. Taking the research progress of this technology as the main line, this paper summarizes the technical key points of aquaponic and the key factors affecting the balance of aquaponic. Through the objective analysis of the current stage of the development of aquaponic planting and breeding technology, there are existing problems such as insufficient research on the conversion of nitrogen and phosphorus by bacteria and algae, limited aquatic products and plant species, unclear economic feasibility, insufficient application of artificial intelligence technology, lack of professional personnel and government support. In view of the existing problems, this paper puts forward to promote the aquaponic and raising suggestions for the sustainable development of technology, such as the need to strengthen the use of all kinds of microorganisms and the study of transformation of nitrogen and phosphorus uptake efficiency, and realize in species diversity and accelerate the artificial intelligence technology combined with an aquaponic planting and breeding technology, and for the government to raise awareness, pay more attention to the training of professional talents, etc.

In order to solve the problem of poor uniformity of sowing operation, a wheat mechanized sowing control system based on STM32 single chip microcomputer is designed. The wheeled driving robot could travel with variable speed. According to the real-time driving speed of the wheeled driving robot, the speed of the seeding motor is controlled to realize the variable speed and uniform seeding. The system used multi-stage control of DC motor speed. The real-time speed signal of the wheeled driving robot is used for The first-stage control parameter, which is controlled by PID. The real-time current and speed of the seeder motor are used for secondary control parameters, which is controlled by fuzzy PID. Simulation results show that the control algorithm has short response time, small overshoot and good control effect. The results of sowing experiment have shown that the control accuracy of seeding amount under constant speed condition is 96.8% and that under variable speed condition is 95.1%.

The paper summarized and analyzed the development situation of aquaculture mechanization in China in 2021, mainly including the development of aquaculture industry， the development status of wholeprocess mechanization of four main aquaculture modes, such as pond aquaculture, cage aquaculture, factory aquaculture, raft cage and bottom sowing aquaculture. On this basis， we analyzed the main problems in the operation links of the four main breeding modes， such as the overall low level of mechanization and unbalanced development， the weak foundation of technical system， the insufficient integration of mechanization， information technology and intelligence， and the insufficient support ability of efficient applicable facilities and equipment. The countermeasures to promote the development of aquaculture mechanization were put forward as follows: transformation and upgrading of aquaculture facilities and equipment, establishing the whole process mechanization technology system of aquaculture healthy farming, and accelerating the demonstration and application of green, practical and efficient intelligent equipment

Accurate detection and identification of crop diseases is an important measure to promote the development of intelligent and modernized agricultural production. With the development of computer vision technology, deep learning methods have been rapidly applied, and the use of convolutional neural networks to detect and identify crop diseases has become a hot research topic in recent years. In this paper, the disadvantages of traditional crop disease identification methods are analyzed. Based on the convolutional neural network model structure of crop disease detection and recognition, combined with the development and optimization process of convolutional neural network model, the specific application of convolutional neural network in crop disease detection and recognition is classified. From based on public data sets and selfbuilt data set of crop disease classification; based on double stage of target detection and single phase detection of crop disease detection; foreign and domestic crop disease severity evaluation of three aspects, the research progress of convolutional neural network model are summarized, while also contrasted its performance. The current problems of convolutional neural network model based on crop disease detection and recognition are pointed out: the network model with good recognition performance on public data sets has poor recognition performance on selfbuilt complex data sets. The crop disease detection algorithm based on twostage target detection has poor realtime performance and is not suitable for small target detection; The detection accuracy of crop disease based on singlestage target detection is low in complex background. The accuracy of crop disease degree assessment model in complex field environment is low. Finally, the future research directions are prospected as follows: how to obtain highquality crop disease data sets; how to improve the network generalization performance; how to improve crop monitoring performance in field environment; how to locate the area of large area crop disease, and to evaluate the severity of disease and early warning of single branch crop disease.

Traditional electric tractors has some problems, such as low range, difficult to meet the operation demand of highpower section, etc., the incremental electric tractor is an additional power driving device based on the traditional electric tractor, which takes into account the economic and power requirements, and is one of the main development directions of the electric tractor in the future. On the basis of summarizing the main technologies such as power system research and energy management control strategy of incremental electric vehicle, this paper focuses on the research progress of incremental electric tractor in power system design, parameter matching and optimization algorithm with transmission system, torque distribution and energy management, and points out that precision, intelligence and how to find a better balance between power consumption and fuel consumption, improving the utilization rate of electric energy and reducing fuel consumption are the key and main development direction for the promotion of incremental electric tractors in the future. The modeling of the incremental electric tractor should fully consider the different operation needs of the tractor, such as transportation, soil ploughing, soil turning and land preparation. In the future, based on certain data analysis, the actual operation needs can be fully considered, and personalized and accurate modeling and parameter design can be implemented to improve accuracy. Based on the full analysis of the operating characteristics and energy demand of the extended range electric tractor, the research and development of batteries and related technologies suitable for the extended range electric tractor can be carried out to improve the endurance mileage.