Agricultural Robotics in Precision Agriculture: A Literature Review of Technologies, Applications, and Future Directions

Population growth is a common problem that affects all countries around the world. The world population is expected to increase by around 28.94% by 2050, which means it reaches 9.8 billion people [1]. The population growth factor is associated with the growing demand for food, so farmers are forced to change their crops, increasing their production capacity [2]. In contrast to population growth, arable land worldwide is decreasing as rural scenarios are being transformed into urban ones. In 1991, the percentage of arable land was around 39.47%, but in 2013, this percentage fell to 37.70%, making it difficult to increase food production since the production space is increasingly smaller [3].

Furthermore, there is a need for human labor, which in turn is subject to health problems, such as the global public health crisis generated by the Coronavirus pandemic. This crisis has had a substantial impact on social and economic activities. Despite the challenges arising from population growth, urbanization, and the susceptibility of human labor to disease situations, technological innovations in the agricultural sector are reshaping the agricultural scenario for the better. Robots in agriculture demand the application of Artificial Intelligence (AI) and Internet of Things (IoT) technologies. These technologies support precision agriculture, which consists of a management strategy that uses electronic information and other technologies to collect, process, and analyze spatial and temporal data to guide targeted actions that improve agricultural operations efficiency, productivity, and sustainability [4]. The performance of robots depends on the type of crop and the task that the robot must perform. In this context, several research studies have been proposed regarding agriculture robots, such as solving navigation problems of wheeled mobile robots [5] and performing general tasks, as in [6]; thus, a brief literature revision is necessary to analyze the recent developments, opportunities, and challenges in the field of agriculture robotics. The remainder of the manuscript presents a revision of agricultural robots’ main applications, challenges, and opportunities.

An agriculture robot is a robotic system developed to carry out agricultural tasks without human intervention. These robots are designed to optimize the execution of several operations in the context of precision agriculture. Despite the different operations they are designed to perform, all agricultural robots have basic operations in common: moving to the indicated position, recognizing the object of interest, directing the effector to it, and performing the desired action. Thus, each stage requires mature technologies to achieve the objective effectively and accurately. The agricultural environment is subject to sudden changes in field conditions and crops, which means that agricultural robots must face dynamic and unstructured environmental problems [7] (Figure 1).

Figure 1:Components of an agriculture robot.

The agriculture robot is composed of a hardware and software system as presented in Figure 1. Agricultural robots integrate hardware components with advanced software systems to perform tasks with intelligence and adaptability. The hardware integrates the mechanical components that will perform the task depending on the specific application of the robot; these mechanical components can correspond to a robotic arm, ground vehicle, or drone. Moreover, the end effector is the specific tool that operates in the agricultural environment to perform the work; this tool can be grippers, cutters, sprayers, and smart actuators. The actuators apply mechanical power to move the mechanical components according to the commands defined by the controller. Moreover, the sensors inform the controller of the actual state of the robot; this information is necessary to compute the commands to be executed by the actuators. On the other hand, the software encompasses a set of algorithms aimed at perception, motion control, and motion planning to perform movement coordination, allowing the robot to respond autonomously and efficiently to environmental conditions [8]. Additionally, artificial intelligence and big data are essential in precision agriculture. In addition, many agricultural robots have robotic arms responsible for executing specific tasks, such as fruit harvesting. In addition, the end effectors encompass technologies to perform the final task of harvesting and pruning, allowing careful and efficient collection with less damage to food. Finally, the robot’s sensory perception is vital; sensors and computer vision are used in the control algorithms, in addition to target recognition and obstacle avoidance [6].

The software consists of algorithms that permit the perception of the environment based on vision systems. These algorithms are mainly based on Artificial Intelligence (AI) frameworks. Thus, it is important to note that the robot needs self-orientation and maneuverability to navigate the crop fields autonomously. In the same context, robots must be equipped with sensors that allow position and posture detection, such as Global Positioning System (GPS) and Inertial Measurement Units (IMU) or vision systems that deliver the required information to perception algorithms to execute the motions during the operations executions. Motion, terrain perception, and navigation sensors are also found in most agricultural robots, so these mobile robots recognize their state when performing necessary tasks [9]. Robots use environmental maps to predict a path and avoid collisions, as well as to obtain a more precise apprehension and navigation through dynamic obstacles.

Agricultural robots can be classified according to the tasks they perform in precision agriculture operations. In this way, the application is defined in terms of the specific task performed by the robot system, considering their contributions in terms of precision and sustainability [10]. The main categories of agricultural robots according to their application are:
1. Soil preparation robots: They autonomously navigate the fields to optimize soil preparation before planting. They perform soil conditioning operations such as plowing, harrowing, and leveling.
2. Planting and seeding robots: This robot performs precise placement of seeds in the soil, improving germination rates and reducing seed wastage.
3. Weeding and crop care robots: These robots detect and eliminate weeds by precisely applying fertilizers or spraying pesticides to minimize environmental impacts.
4. Monitoring robots: These devices are used to collect realtime data on soil conditions, crop health, and pest infestations.
5. Harvesting and picking robots: These robots are used to accurately identify and collect fruits and vegetables.
6. Irrigation robots: These systems optimize water use, reducing waste in crop irrigation processes.

Moreover, according to the robot’s mobility, agriculture robots can be classified as stationary robots, Automated Guided Vehicles (AGVs), Unmanned Aerial Vehicles (UAVs), Autonomous Underwater Vehicles (AUVs), and Remotely Operated Underwater Vehicles (ROVs). This classification describes the adaptation of the mobility of the robots in several agriculture tasks [11].

The main applications and contributions reported in the literature are presented in Table 1 according to the application of robotic systems (Table 1) [9,12-22].

Table 1:Robotic systems applied to agricultural operations.

Agricultural robots have undergone significant advances over time, encountering challenges and opportunities along the way, including integrating agronomic and biomimetic principles to improve operations’ accuracy and efficiency and applying big data and artificial intelligence algorithms to optimize decision-making and increase adaptability [15]. Therefore, future studies should address the problems related to these contexts to improve even more accurate and optimal operations in the context of precision agriculture. Furthermore, unstructured and dynamic environments, such as agricultural ones, make the performance of robotic systems difficult. In this regard, studies that solve the problems of low durability, control and manufacturing complexity, and high energy consumption of bionic arms are necessary.

Furthermore, integrating sensors and algorithms to increase automation and efficiency in crop management is a challenge in the current scenario. Therefore, universities and research centers have sought to develop modular platforms for acquiring agricultural data, enabling the study of spatial variability and improving precision agriculture techniques [23]. Furthermore, the challenges related to Big Data and Artificial Intelligence include data quality, high computational demand, information security, and high costs.

Therefore, the adoption of agricultural robots in agriculture faces challenges arising from the fragility of the machines, the high cost of technology, limited efficiency, and difficulties of operation in outdoor environments. Furthermore, research focuses on the individual development of robots, not fully considering agricultural needs, which compromises project quality and evolution. In addition, issues such as energy consumption and computational limitations are also challenges encountered in the current scenario.

Agricultural robotics encompasses innovative technologies for modern food production, which is facing the challenges of increasing food demands and environmental sustainability. This review has explored agricultural robots’ structural components and software capabilities and their main applications in soil preparation, planting, monitoring, and harvesting. Challenges remain despite the relevant progress in recent years, particularly in dealing with unstructured environments, energy efficiency, high development costs, and integration with advanced perception and decision-making systems. Interdisciplinary cooperation is required to enhance engineering solutions to cope with the limitations of agricultural robotic systems. These issues include hardware and software design innovation to convey robust and adaptive solutions to the specific demands of agricultural operations. Future developments should also demand modular, scalable, data-driven systems to enhance agricultural operations. These technological advances will increase the usage of agricultural robots to guarantee food security and sustainable solutions in the context of precision agriculture.

1. Kopittke PM, Menzies NW, Wang P, McKenna BA, Lombi E (2019) Soil and the intensification of agriculture for global food security. Environment International 132: 105078.
2. Hirel B, Tétu T, Lea PJ, Dubois F (2011) Improving nitrogen use efficiency in crops for sustainable agriculture. Sustainability 3(9): 1452-1485.
3. Zhang L, Dabipi IK, Brown WL Jr (2018) Chapter 18 Internet of things applications for agriculture, John Wiley & Sons Ltd: Hoboken NJ, USA, pp. 507-528.
4. Lowenberg-DeBoer J, Erickson B (2019) Setting the record straight on precision agriculture adoption. Agron J 111(4): 1552-1569.
5. Gao X, Li J, Fan L, Zhou Q, Yin K, et al. (2018) Review of wheeled mobile robots’ navigation problems and application prospects in agriculture. IEEE Access 6: 49248-49268.
6. Fountas S, Mylonas N, Malounas I, Rodias E, Santos CH, et al. (2020) Agricultural robotics for field operations. Sensors 20(9): 2672.
7. Gonzalez-de-Santos P, Fernandez R, Sepulveda D, Navas E, Emmi L, et al. (2020) Field robots for intelligent farms-inhering features from industry. Agronomy 10(11):1638.
8. Jin T, Han X (2024) Robotic arms in precision agriculture: A comprehensive review of the technologies, applications, challenges, and future prospects. Computers and Electronics in Agriculture 221.
9. Yang Q, Du X, Wang Z, Meng Z, Ma Z, et al. (2023) A review of core agricultural robot technologies for crop productions. Computers and Electronics in Agriculture, New York 206(13): 107701.
10. Oliveira LFP, Moreira AP, Silva MF (2021) Advances in agriculture robotics: A state-of-the-art review and challenges ahead. Robotics 10(2): 52.
11. Vidoni R, Carabin G, Quaglia G, Botta A, Reina G, et al. (2024) Advances in mobility platforms for agricultural robots.
12. Zhang B, Chen X, Zhang H, Shen C, FU W (2022) Design and performance test of a jujube pruning manipulator. Agriculture 12(4): 552.
13. Tinoco V, Silva MF, Santos FN, Rocha LF, Magalhães S, et al. (2021) A review of pruning and harvesting manipulators. IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), Santa Maria da Feira, Portugal pp. 155-160.
14. Botta A, Cavallone P, Baglieri L, Colucci G, Tagliavini L, et al. (2022) A review of robots, perception, and tasks in precision agriculture. Appl. Mech 3: 830-854.
15. Klerkx L, Jakku E, Labarthe P (2019) A review of social science on digital agriculture, smart farming and agriculture 4.0: New contributions and a future research agenda. NJAS - Wageningen Journal of Life Sciences 90-91(1): 1-16.
16. Ju C, Kim J, Seol J, Son HI (2022) A review on multirobot systems in agriculture. Computers and Electronics in Agriculture 202: 107336.
17. Bechar A, Vigneault C (2016) Agricultural robots for field operations: Concepts and components. Biosystems Engineering 149: 94-111.
18. Lytridis C, Kaburlasos VG, Pachidis T, Manios M, Vrochidou E (2021) An overview of cooperative robotics in agriculture. Agronomy 11(9): 1818.
19. Tinôco V, Silva MF, Santos FN, Valente A, Rocha LF, et al. (2022) An overview of pruning and harvesting manipulators. Industrial Robot: the international journal of robotics research and application 49(4).
20. Liu W, Tian S, Wang Q, Jiang H (2023) Key technologies of plug tray seedling transplanters in protected agriculture: A review. Agriculture 13(8): 1488.
21. Bogue R (2016) Robots poised to revolutionise agriculture. Industrial Robot 43(5): 450-456.
22. Zhang B, Xie Y, Zhou J, Wang K, Zhang Z (2020) State-of-the-art robotic grippers, grasping and control strategies, as well as their applications in agricultural robots: A review. Computers and Electronics in Agriculture 177: 105694.
23. Upadhyay A, Zhang Y, Koparan C, Rai N, Howatt K, et al. (2024) Advances in ground robotic technologies for site-specific weed management in precision agriculture: A review. Computers and Electronics in Agriculture 225: 109363.