Technological applications and economic assessment of autonomous robotic systems for precision agriculture in greenhouse and open-field production

Introduction

Agriculture plays a crucial role in ensuring global food security and sustaining economic development. With the global population projected to reach nearly 9.8 billion by 2050, the demand for food production is expected to increase significantly. To meet this growing demand while maintaining environmental sustainability, innovative technological solutions are required in agricultural production systems. Precision agriculture has emerged as a modern farming approach that utilizes advanced technologies to monitor, measure, and manage variability within agricultural fields in order to optimize crop productivity and resource use efficiency. In recent years, autonomous robotic systems have become an integral part of precision agriculture. These systems integrate robotics, artificial intelligence, sensors, and data analytics to perform complex agricultural operations with minimal human intervention. Agricultural robots can perform tasks such as crop monitoring, planting, spraying, harvesting, and weed management with improved accuracy and efficiency. The adoption of robotic systems is largely driven by challenges such as labor shortages, increasing labor costs, and the need for sustainable agricultural practices. Autonomous robots operate in different agricultural environments, including greenhouses and open fields. Greenhouse production systems benefit from robotic Technologies due to their controlled environments, which facilitate precise automation of crop monitoring, irrigation, and harvesting operations. On the other hand, open-field agricultural robots are designed to navigate complex terrain and perform tasks such as seeding, weed removal, and crop monitoring across large areas. Robotic technologies rely on advanced sensing systems, machine vision, and navigation algorithms to identify plants, detect weeds, and assess crop health conditions. These technologies enable site-specific crop management, reducing input costs while improving productivity. Additionally, autonomous robots can operate continuously, allowing farmers to perform agricultural tasks more efficiently compared to conventional manual labor. Despite the significant technological advancements, the economic feasibility of robotic systems remains an important consideration for farmers and agricultural industries. High initial investment costs and maintenance requirements can limit adoption, particularly among small and medium-scale farmers. Therefore, assessing the economic benefits of robotic systems in relation to their operational costs is essential for determining their practicality in modern farming. This paper reviews the technological applications of autonomous robotic systems in precision agriculture and evaluates their economic impacts in greenhouse and open-field production systems.

Overview of autonomous robotic systems in agriculture

The rapid advancement of precision agriculture technologies has significantly transformed modern agricultural practices. Autonomous robotic systems are increasingly being adopted to address labor shortages, improve productivity, and enhance resource efficiency in both greenhouse and open-field farming systems. These systems integrate robotics, Artificial Intelligence (AI), sensors, computer vision, and Internet of Things (IoT) technologies to automate complex agricultural tasks such as crop monitoring, harvesting, weed management, and input application. Early concepts of robotic agriculture emerged from the broader development of precision farming technologies aimed at site-specific crop management. Foundational research emphasized the potential of precision agriculture to optimize input use, improve productivity, and reduce environmental impacts (Pierce & Nowak, 1999) [27] . Subsequent technological developments expanded these concepts by integrating automation and robotics into agricultural machinery. Robotic technologies have evolved from simple mechanized tools to intelligent autonomous platforms capable of performing multiple tasks. The increasing demand for sustainable agricultural production has accelerated the adoption of robotic solutions that can perform agricultural operations with higher precision and efficiency. Recent studies highlight that autonomous robots can significantly reduce labor dependency while increasing operational accuracy and productivity (Bechar & Vigneault, 2016; Botta et al., 2022) [6,10] .

Evolution of agricultural robotics

The development of agricultural robotics has progressed through several technological phases, ranging from basic automation to fully autonomous systems. Early robotic systems were primarily designed to assist with repetitive agricultural tasks such as mechanical weeding and crop harvesting. These systems relied on basic control algorithms and limited sensing capabilities. Blackmore et al. (2005) [9] introduced the concept of robotic agriculture as a future paradigm in agricultural mechanization, emphasizing the integration of robotics with precision farming technologies. This concept highlighted the potential of smaller, autonomous machines that could replace conventional largescale machinery while improving operational efficiency. Advancements in robotics engineering have significantly improved the capabilities of agricultural robots. Modern robotic platforms now incorporate sophisticated sensors, machine vision systems, and intelligent control algorithms that enable them to navigate complex agricultural environments. Bac et al. (2014) [3] demonstrated that robotic harvesting systems could perform delicate crop harvesting operations with high precision, particularly for high-value horticultural crops. Research efforts have also focused on improving the adaptability of robotic systems for different agricultural environments. Autonomous robots are now being designed to operate effectively in diverse conditions, including structured greenhouse environments and unstructured open-field landscapes. The continuous improvement of robotic hardware and software systems has expanded their potential applications across multiple agricultural operations.

Sensor technologies and perception systems

Sensor technologies play a critical role in enabling autonomous robotic systems to interact effectively with agricultural environments. Agricultural robots rely on various sensing technologies to detect crop conditions, identify obstacles, and perform precise agricultural operations. Machine vision systems are among the most widely used sensing technologies in agricultural robotics. These systems utilize cameras and image processing algorithms to identify crop characteristics, detect weeds, and monitor plant health. Studies have demonstrated that machine vision can significantly enhance the accuracy of robotic harvesting and crop monitoring operations (Zhao et al., 2016) [44] . Remote sensing technologies have also contributed significantly to the development of precision agriculture. Unmanned Aerial Vehicles (UAVs) and satellite-based imaging systems provide valuable data for crop monitoring and decisionmaking processes. Zhang and Kovacs (2012) [41] reported that UAV-based remote sensing technologies can provide highresolution imagery for precision crop management. Advanced sensing systems such as hyperspectral imaging and thermal sensors are increasingly being integrated into agricultural robots. These technologies enable the detection of plant stress, disease symptoms, and nutrient deficiencies at early growth stages. Mahlein (2016) [22] highlighted the potential of imaging sensors for early plant disease detection, which can significantly improve crop management strategies. Furthermore, sensor fusion techniques that combine multiple sensing technologies have improved the reliability and accuracy of robotic perception systems. The integration of cameras, LiDAR sensors, and GPS technologies enables agricultural robots to operate effectively in complex farming environments.

Artificial intelligence and machine learning in agricultural robotics

Artificial intelligence and machine learning technologies have significantly enhanced the capabilities of agricultural robotic systems. AI-based algorithms enable robots to analyze large datasets, identify patterns, and make autonomous decisions during agricultural operations. Machine learning techniques are widely used for crop classification, weed detection, and disease identification. Liakos et al. (2018) [20] reported that machine learning algorithms have been successfully applied in various agricultural applications, including yield prediction and crop monitoring. These technologies enable agricultural robots to perform tasks with higher accuracy and efficiency compared to traditional mechanized systems. Deep learning techniques have further improved the performance of computer vision systems used in agricultural robotics. Kamilaris and Prenafeta-Boldú (2018) [18] highlighted the growing role of deep learning algorithms in agricultural automation, particularly in applications such as crop disease detection and phenotyping. Artificial intelligence also plays a crucial role in decisionmaking processes for robotic systems. AI-based control systems allow robots to adapt their operations based on environmental conditions and crop requirements. Qiao et al. (2022) [28] emphasized that the integration of AI, sensors, and robotics has created new opportunities for automated plant phenotyping and precision crop management. The use of AI in agricultural robotics continues to expand as computational capabilities improve. These advancements are expected to further enhance the efficiency and reliability of autonomous robotic systems in agriculture.

Autonomous navigation and path planning

Autonomous navigation is one of the most critical components of agricultural robotics. Agricultural robots must be able to navigate complex environments while avoiding obstacles and performing tasks with high precision. Several navigation techniques have been developed to enable autonomous operation of agricultural robots. Oksanen and Visala (2009) [24] proposed coverage path planning algorithms designed specifically for agricultural field operations. These algorithms allow robots to systematically cover large agricultural fields while minimizing redundant movement. Recent advancements in navigation technologies have incorporated GPS-based positioning systems, LiDAR sensors, and Simultaneous Localization and Mapping (SLAM) algorithms. These technologies allow robots to operate autonomously even in complex agricultural environments. Research by Rakun and Popič (2026) [29] demonstrated the effectiveness of optimized autonomous navigation systems for field robots. Their findings indicate that improved navigation algorithms can significantly enhance the efficiency of robotic field operations. Autonomous navigation technologies are particularly important for open-field agricultural environments where terrain conditions and crop layouts may vary significantly. Continued improvements in navigation systems are expected to further expand the capabilities of agricultural robotic platforms.

Applications of autonomous robots in greenhouse agriculture

Greenhouse agriculture provides an ideal environment for the implementation of autonomous robotic systems due to its structured layout and controlled environmental conditions. Robotic systems can perform a wide range of tasks in greenhouse environments, including crop monitoring, harvesting, pruning, and environmental control. Van Henten et al. (2013) [38] highlighted the potential of robotics in protected crop production systems. Their research demonstrated that robotic technologies could significantly improve the efficiency of greenhouse operations while reducing labor requirements. Robotic harvesting systems are among the most widely studied applications in greenhouse agriculture. Bac et al. (2014) [3] reported that robotic harvesters can successfully perform harvesting operations for crops such as tomatoes, cucumbers, and sweet peppers. Greenhouse robots also play an important role in plant phenotyping and crop monitoring. Advanced sensing technologies enable robots to collect detailed information about plant growth, nutrient status, and environmental conditions. These data can be used to optimize crop management practices and improve productivity. The integration of automation technologies in greenhouse environments has also improved resource efficiency. Automated irrigation systems, climate control technologies, and robotic monitoring systems contribute to more efficient use of water, energy, and fertilizers.

Applications of autonomous robots in open-field agriculture

In open-field agriculture, robotic systems are primarily used for tasks such as soil monitoring, crop scouting, weed control, and harvesting. These applications require robotic platforms capable of operating in unstructured and variable environments. Autonomous weed control systems represent one of the most promising applications of agricultural robotics. Slaughter et al. (2008) [34] demonstrated that robotic weed control technologies could significantly reduce herbicide usage while improving weed management efficiency. Robotic systems are also increasingly being used for precision spraying applications. Perez-Ruiz et al. (2014) [26] developed automated weed detection and spraying systems capable of applying herbicides with high spatial accuracy. Such systems reduce chemical input usage while improving environmental sustainability. Robotic platforms designed for orchard and specialty crop production have also shown promising results. Bergerman et al. (2015) [8] demonstrated the potential of robotic harvesting systems for orchard crops, highlighting their ability to perform delicate harvesting operations. The use of autonomous vehicles for crop monitoring and field operations has further expanded the role of robotics in open-field agriculture. Underwood et al. (2016) [37] reported that autonomous vehicles equipped with advanced sensors could effectively perform crop monitoring tasks in orchard environments.

Integration of IoT and big data in robotic agriculture

The integration of IoT technologies and big data analytics has significantly enhanced the capabilities of autonomous robotic systems in agriculture. IoT-enabled sensors allow continuous monitoring of environmental conditions, soil properties, and crop growth parameters. Wolfert et al. (2017) [40] emphasized the importance of big data in smart farming systems. Large datasets generated by sensors and robotic platforms can be analyzed to improve decision-making processes and optimize agricultural operations. IoT-based agricultural information management systems enable farmers to remotely monitor field conditions and control automated agricultural machinery. Verdouw et al. (2016) [39] reported that IoT technologies play a crucial role in enabling connected agricultural systems. The integration of IoT technologies with robotic platforms has created new opportunities for precision agriculture. Data collected by robotic sensors can be transmitted to cloud-based platforms for analysis and decision support.

10.Economic assessment of autonomous robotic systems

while the technological benefits of agricultural robotics are well documented, economic feasibility remains a critical factor influencing their adoption. Robotic systems typically require high initial investment costs, which may limit their adoption among small-scale farmers. Pedersen et al. (2006) [25] highlighted the importance of economic analysis in evaluating the adoption of precision agriculture technologies. Their research indicated that economic benefits such as labor savings and increased productivity play a significant role in technology adoption. Recent studies have demonstrated that autonomous robotic systems can provide substantial economic benefits over time. Lowenberg-DeBoer and Erickson (2019) [21] reported that precision agriculture technologies can improve farm profitability through increased productivity and reduced input costs. Robotic systems can significantly reduce labor requirements in agricultural operations. In many regions, labor shortages have become a major challenge for agricultural production. Autonomous robots can perform labor-intensive tasks such as harvesting, weeding, and crop monitoring with minimal human intervention. Economic analyses have also shown that robotic systems can improve resource efficiency, leading to reduced costs associated with water, fertilizers, and pesticides. These benefits contribute to improved economic sustainability of agricultural production systems. Despite these advantages, several challenges remain in the adoption of agricultural robotics. High initial investment costs, technological complexity, and limited technical expertise among farmers are major barriers to widespread adoption. Additionally, agricultural robots must be capable of operating under diverse environmental conditions, including uneven terrain, varying weather conditions, and different crop structures. Step 4: Simulation of Autonomous Robot Operations following the selection of the production environment, the operational behavior of autonomous robotic systems was simulated using a three-stage robotic decision-making framework consisting of sensing, decision-making, and action. In the sensing stage, robots collected real-time data through sensors and imaging technologies to monitor crop health, soil conditions, and environmental factors. During the decision stage, the collected data were processed using artificial intelligence algorithms and machine learning models to determine appropriate agricultural interventions. In the final action stage, the robotic systems executed tasks such as targeted pesticide application, precision irrigation, weed detection, and crop monitoring.

Step 5: Performance Evaluation and Cost Assessment

The next step involved evaluating the performance of the robotic systems using technological and economic indicators. The total operational cost of the robotic system was calculated using the equation: CT = CI + CM + CE, where CT represented the total cost, CI indicated initial investment cost, CM represented maintenance cost, and CE represented operational expenses. Additionally, economic feasibility was assessed using financial indicators such as Benefit-Cost Ratio (BCR) and Return On Investment (ROI). These indicators provided insights into the profitability and economic sustainability of robotic technologies in precision agriculture.

Step 6: Scenario-Based Comparative Analysis to comprehensively assess the effectiveness of robotic systems, four production scenarios were developed within the simulation framework. These included open-field conventional farming, open-field robotic farming, greenhouse conventional farming, and greenhouse robotic farming. The performance outcomes of each scenario were compared in terms of operational efficiency, resource utilization, crop productivity, and economic returns. This scenario-based approach allowed identification of the most efficient agricultural management system.

Step 7: Output Interpretation and Decision Analysis

In the final stage, the simulation outputs were analyzed to determine the overall efficiency and profitability of autonomous robotic systems in agricultural production. The results generated from the model provided insights into technological performance improvements, cost reduction potential, and productivity gains associated with robotic adoption. The findings were interpreted to support decision-making regarding the implementation of autonomous robotics in modern precision agriculture systems. The sensing stage collected real-time crop and environmental data. The decision stage processed the data using artificial intelligence algorithms to determine appropriate management actions. The action stage executed field operations automatically.

Operational performance model

Operational performance of the robotic system was evaluated using four key indicators: accuracy (A_c), efficiency (E_f), energy consumption (E_n),and reliability (R_l). The overall operational performance index (OPI) was calculated as: OPI = w1(A_c) + w2(E_f) + w3(R_l) -w4(E_n)

Where w1, w2, w3, and w4 represent weighting factors assigned to each parameter based on system priorities. Higher OPI values indicated better robotic system performance.

Cost calculation model

The total operational cost of robotic farming was estimated using the following equation

C_T = C_I + C_M + C_E

where: C_T = total cost of robotic operation C_I = initial investment cost C_M = maintenance and repair cost C_E = energy and operational cost This model allowed the estimation of the long-term financial requirements of robotic systems.

Economic assessment model

Economic feasibility was evaluated using standard agricultural engineering indicators including Benefit-Cost Ratio (BCR), Return on Investment (ROI), and Payback Period (PP).

Benefit-Cost Ratio BCR = B / C_T

Where B represents total economic benefits generated by robotic operations. The scenario analysis allowed identification of the most efficient and economically viable production system.

Return on Investment

Final output model

The final decision output of the model was based on efficiency and profitability indicators. Farm productivity improvement (FP) was calculated as FP = f(OPI, BCR, ROI)

where higher performance and profitability values indicated greater technological suitability for precision agriculture systems. The model ultimately supported decision-making regarding the adoption of autonomous robotic technologies for sustainable agricultural production in both greenhouse and openfield environments.

Results analysis & discussions

the simulation-based framework developed in this study enabled the evaluation of autonomous robotic systems under two agricultural production environments: greenhouse and open-field farming. The results demonstrated that the integration of advanced technological components such as sensors, artificial intelligence, machine vision, and navigation systems significantly improved the operational efficiency and decisionmaking capability of agricultural operations.

Simulation outcomes of autonomous robotic systems

The simulation model demonstrated that autonomous robotic systems significantly improved operational efficiency in both greenhouse and open-field production environments. The integration of advanced sensors, artificial intelligence algorithms, and machine vision technologies enabled the robotic systems to perform agricultural tasks with higher precision compared to conventional farming practices. The sensingdecision-action operational structure allowed robots to collect real-time data, analyze crop conditions, and execute appropriate field operations with minimal human intervention. As a result, robotic systems exhibited higher task accuracy and reduced operational variability, particularly in controlled greenhouse environments where navigation and environmental conditions remained stable. Energy consumption varied depending on the complexity of field operations and environmental conditions. Robots operating in greenhouse environments generally consumed less energy due to shorter operational paths and smoother navigation surfaces. Reliability analysis showed that autonomous systems maintained consistent performance across multiple operational cycles, indicating strong potential for long-term agricultural applications.

12.5 Economic Analysis of Robotic Farming Systems the economic assessment revealed that the adoption of autonomous robotic systems required a higher initial investment compared to conventional farming methods. Costs associated with purchasing robotic equipment, installing sensing systems, and implementing artificial intelligence technologies represented the major financial inputs. However, the operational cost analysis demonstrated significant reductions in labor requirements and improved efficiency in input utilization. The benefit-cost ratio analysis indicated that robotic farming systems could become economically advantageous over time as operational efficiencies increased and labor costs decreased.

Return on investment values showed promising long-term financial benefits, particularly in large-scale farming operations where robotic technologies could be utilized more extensively.

The payback period analysis suggested that robotic investments could be recovered within a reasonable operational timeframe depending on farm size, crop type, and production intensity. The comparative results indicated that integrating robotic technologies into precision agriculture could significantly enhance productivity, reduce operational costs, and improve sustainability of agricultural production systems. Furthermore, the economic assessment suggests that the longterm adoption of robotic technologies could improve farm profitability and resilience. As technological advancements continue and costs of robotic systems decrease, their adoption is expected to expand across different agricultural production systems.

Conclusion

This study evaluated the technological applications and economic feasibility of autonomous robotic systems in precision agriculture for both greenhouse and open-field production environments. The developed simulation framework integrated technological, agronomic, environmental, and economic parameters to analyze robotic performance and financial viability. The results demonstrated that autonomous robotic systems significantly improved operational efficiency, accuracy, and resource utilization compared with conventional farming practices. The sensing-decision-action architecture enabled robots to perform critical agricultural operations such as crop monitoring, irrigation management, spraying, and harvesting with high precision and minimal human intervention.

The comparative analysis revealed that robotic systems performed more efficiently in greenhouse environments due to controlled conditions, structured layouts, and reduced environmental variability. Although open-field environments posed additional challenges such as uneven terrain and weather fluctuations, robotic systems still showed improved performance and reduced labor dependency compared to traditional farming systems. Economic assessment indicated that while the initial investment cost of robotic technologies is relatively high, longterm benefits such as reduced labor costs, optimized input usage, and improved productivity can lead to favorable economic returns. Overall, the integration of autonomous robotic systems presents a promising pathway for enhancing productivity, sustainability, and technological advancement in modern precision agriculture.

Future research directions

Future research should focus on improving the adaptability and robustness of autonomous robotic systems under diverse agricultural conditions. Advanced machine learning and deep learning algorithms can be further integrated to enhance crop recognition, disease detection, and decision-making accuracy.

The development of multi-functional robotic platforms capable of performing multiple agricultural tasks simultaneously may further increase operational efficiency and reduce overall system costs.

Additionally, research should explore the integration of robotic systems with other digital agriculture technologies such as Internet of Things (IoT), remote sensing, and cloud-based farm management systems. Such integration can enable real-time monitoring, predictive analytics, and improved farm management strategies. Future studies should also investigate large-scale field trials and long-term economic evaluations to better understand the practical feasibility of robotic technologies across different crops, farm sizes, and geographical regions.

Limitations of the study

Despite providing valuable insights into the technological and economic potential of autonomous robotic systems in agriculture, this study has several limitations. First, the research was primarily based on a simulation framework that relied on secondary data and modelled assumptions rather than large-scale field experiments. Consequently, the operational performance results may vary under real-world agricultural conditions. Second, the economic analysis considered general cost parameters and may not fully capture regional variations in labor costs, energy prices, and equipment availability. Third, the study focused mainly on the technological and economic aspects of robotic adoption, while social and behavioural factors influencing technology acceptance among farmers were not addressed. Finally, the model evaluated a limited set of robotic applications and did not include emerging technologies such as swarm robotics or collaborative human-robot farming systems. Addressing these limitations in future studies will help develop more comprehensive and practical frameworks for evaluating robotic technologies in precision agriculture.

References

1. Auernhammer H. Precision farming The environmental challenge. Comput Electron Agric. 2001;30(1-3):31-43. https://DOI.org/10.1016/S0168-1699(00)00153-8
2. Bac CW, Hemming J, Van Henten EJ. Stem localization of sweet-pepper plants for harvesting robots. Biosyst Eng. 2013;114:333-342. https://doi.org/10.1016/j.biosystemseng.2012.12.005
3. Bac CW, Hemming J, Van Henten EJ. Harvesting robots for high-value crops. J Field Robot. 2014;31(6):888-911. https://DOI.org/10.1002/rob.21525
4. Baerdemaeker JD, Munack A, Ramon H, Speckmann H. Mechatronic systems in precision agriculture. IEEE/ASME Trans Mechatron. 2001;6(1):1-6. https://DOI.org/10.1109/3516.906719
5. Barbosa Júnior MR, Santos RG, Sales LA, Oliveira LP. Advancements in agricultural ground robots for specialty crops. Plants. 2024;13(23):3372. https://DOI.org/10.3390/plants13233372
6. Bechar A, Vigneault C. Agricultural robots for field operations. Biosyst Eng. 2016;149:94-111. https://DOI.org/10.1016/j.biosystemseng.2016.06.003
7. Bechar A, Vigneault C. Agricultural robots for harvesting. Biosyst Eng. 2017;153:94-111. https://DOI.org/10.1016/j.biosystemseng.2016.11.006
8. Bergerman M, Maeta S, Zhang J, et al. Robot farmers: Autonomous orchard harvesting. IEEE Robot Autom Mag. 2015;22(1):54-63. https://DOI.org/10.1109/MRA.2014.2368686
9. Blackmore S, Stout B, Wang M, Runov B. Robotic agriculture -The future of agricultural mechanisation. Precis Agric Conf Proc. 2005. https://DOI.org/10.3920/97890-8686-540-7
10. Botta A, Cavallone P, Baglieri L, Colucci G, Tagliavini L, Quaglia G. A review of robots, perception, and tasks in precision agriculture. Appl Mech. 2022;3(3):830-854. https://DOI.org/10.3390/applmech3030049
11. Chen Y, Liu Z, Wang H. Autonomous navigation in agricultural robots. Robot Auton Syst. 2021;143. https://DOI.org/10.1016/j.robot.2021.103822
12. Duckett T, Pearson S, Blackmore S, Grieve B. Agricultural robotics: The future of robotic agriculture. 2018. https://DOI.org/10.13140/RG.2.2.33065.11365
13. Ehsani R, Mishra A, Maja J. Precision horticulture technologies. HortTechnology. 2013;23(2):200-205. https://DOI.org/10.21273/HORTTECH.23.2.200
14. Fountas S, Sorensen C, Tsiropoulos Z, et al. Farm machinery management information systems. Comput Electron Agric. 2020;170. https://DOI.org/10.1016/j.compag.2020.105247
15. Gao J, French A, Pound M, et al. Deep learning for plant phenotyping. Trends Plant Sci. 2018;23(11):1050-1060. https://DOI.org/10.1016/j.tplants.2018.09.002
16. Grimstad L, From P. Thorvald II agricultural robotic system. Robotics. 2017;6(4):24. https://DOI.org/10.3390/robotics6040024
17. Jensen K, Nielsen S, Larsen M, et al. Robot for weed control. Biosyst Eng. 2012;113(3):219-231. https://DOI.org/10.1016/j.biosystemseng.2012.07.003
18. Kamilaris A, Prenafeta-Boldú F. Deep learning in agriculture. Comput Electron Agric. 2018;147:70-90. https://DOI.org/10.1016/j.compag.2018.02.016
19. Khan S, Fulton J, McDonald T. Robotics and automation in agriculture. Comput Electron Agric. 2021;180. https://DOI.org/10.1016/j.compag.2020.105909
20. Liakos K, Busato P, Moshou D, et al. Machine learning in agriculture. Sensors. 2018;18(8):2674. https://DOI.org/10.3390/s18082674
21. Lowenberg-DeBoer J, Erickson B. Precision agriculture adoption. Agron J. 2019;111:1552-1569. https://DOI.org/10.2134/agronj2018.12.0779
22. Mahlein AK. Plant disease detection by imaging sensors. Plant Dis. 2016;100(2):241-251. https://DOI.org/10.1094/PDIS-03-15-0340-FE
23. Mulla D. Twenty-five years of remote sensing in precision agriculture. Biosyst Eng. 2013;114(4):358-371. https://DOI.org/10.1016/j.biosystemseng.2012.08.009
24. Oksanen T, Visala A. Coverage path planning algorithms for agricultural robots. J Field Robot. 2009;26(8):651-668. https://DOI.org/10.1002/rob.20300
25. Pedersen SM, Fountas S, Blackmore S, Gylling M, Pedersen J. Adoption and perspectives of precision agriculture. Precis Agric. 2006;7:239-254. https://DOI.org/10.1007/s11119-006-9017-5
26. Perez-Ruiz M, Slaughter D, Fathallah F, et al. Automatic control of precision weed spraying. Comput Electron Agric. 2014;102:28-35. https://DOI.org/10.1016/j.compag.2014.01.012
27. Qiao Y, Valente J, Su D, Zhang Z, He D. AI, sensors and robotics in plant phenotyping. Front Plant Sci. 2022;13. https://DOI.org/10.3389/fpls.2022.1064219
28. Rakun J, Popič G. Optimized autonomous navigation for field robots. Precis Agric. 2026. https://DOI.org/10.1007/s11119-025-10303-8
29. Roldán J, Joossen G, Sanz D, et al. Mini-UAV remote sensing for precision agriculture. Sensors. 2016;16(3):365. https://DOI.org/10.3390/s16030365
30. Sankaran S, Mishra A, Ehsani R, Davis C. Plant disease detection techniques. Comput Electron Agric. 2010;72:1-13. https://DOI.org/10.1016/j.compag.2010.02.007
31. Shamshiri R, Weltzien C, Hameed I, et al. Agricultural robotics research. Appl Eng Agric. 2018;34(4):765-784. https://DOI.org/10.13031/aea.12619
32. Shalal N, Low T, McCarthy C, Hancock N. Orchard mapping using machine vision. Comput Electron Agric. 2015;114:25-34. https://DOI.org/10.1016/j.compag.2015.03.015
33. Slaughter DC, Giles D, Downey D. Autonomous robotic weed control. Comput Electron Agric. 2008;61(1):63-78. https://DOI.org/10.1016/j.compag.2007.05.008
34. Sørensen C, Bochtis D. Fleet management in agriculture. Biosyst Eng. 2010;105:41-50. https://DOI.org/10.1016/j.biosystemseng.2009.09.009
35. Srivastava V, Raturi O. Robotics and automation in agriculture. 2023. https://DOI.org/10.1007/978-981-192188-9_45
36. Underwood J, Walsh K, Hammarstrom M, et al. Autonomous orchard robots. J Field Robot. 2016. https://DOI.org/10.1002/rob.21629
37. Van Henten EJ, Bac C, Hemming J, Edan Y. Robotics in protected crop production. Comput Electron Agric. 2013;96:47-55. https://DOI.org/10.1016/j.compag.2013.04.005
38. Verdouw C, Wolfert S, Tekinerdogan B, et al. Internet of Things in agriculture. Comput Electron Agric. 2016;122:214-223. https://DOI.org/10.1016/j.compag.2016.01.037
39. Wolfert S, Ge L, Verdouw C, Bogaardt M. Big data in smart farming. Agric Syst. 2017;153:69-80. https://DOI.org/10.1016/j.agsy.2017.01.023
40. Zhang C, Kovacs JM. UAV applications in precision agriculture. Precis Agric. 2012;13:693-712. https://DOI.org/10.1007/s11119-012-9274-5
41. Zhang D, Zhou G, Xu Y. Smart agriculture technologies. Future Gener Comput Syst. 2019;94:142-150. https://DOI.org/10.1016/j.future.2018.11.015
42. Zhang Q, Reid J. Machine vision guidance systems. Comput Electron Agric. 2006;50(2):123-140. https://DOI.org/10.1016/j.compag.2005.09.002
43. Zhao Y, Li H, Fang S, Kang Y, Wu W, Hao Y, Li Z, Bu D, Sun N, Zhang MQ, Chen R. NONCODE 2016: an informative and valuable data source of long non-coding RNAs. Nucleic acids research. 2016 Jan 4;44(D1):D203-8.