In this review, we examine opportunities and challenges for 21st-century robotic agricultural cotton harvesting research and commercial development. The paper reviews opportunities present in the agricultural robotics industry, and a detailed analysis is conducted for the cotton harvesting robot industry. The review is divided into four sections: (1) general agricultural robotic operations, where we check the current robotic technologies in agriculture; (2) opportunities and advances in related robotic harvesting fields, which is focused on investigating robotic harvesting technologies; (3) status and progress in cotton harvesting robot research, which concentrates on the current research and technology development in cotton harvesting robots; and (4) challenges in commercial deployment of agricultural robots, where challenges to commercializing and using these robots are reviewed. Conclusions are drawn about cotton harvesting robot research and the potential of multipurpose robotic operations in general. The development of multipurpose robots that can do multiple operations on different crops to increase the value of the robots is discussed. In each of the sections except the conclusion, the analysis is divided into four robotic system categories; mobility and steering, sensing and localization, path planning, and robotic manipulation.

This study proposes an algorithm that controls an autonomous, multi-purpose, center-articulated hydrostatic transmission rover to navigate along crop rows. This multi-purpose rover (MPR) is being developed to harvest undefoliated cotton to expand the harvest window to up to 50 days. The rover would harvest cotton in teams by performing several passes as the bolls become ready to harvest. We propose that a small robot could make cotton production more profitable for farmers and more accessible to owners of smaller plots of land who cannot afford large tractors and harvesting equipment. The rover was localized with a low-cost Real-Time Kinematic Global Navigation Satellite System (RTK-GNSS), encoders, and Inertial Measurement Unit (IMU)s for heading. Robot Operating System (ROS)-based software was developed to harness the sensor information, localize the rover, and execute path following controls. To test the localization and modified pure-pursuit path-following controls, first, GNSS waypoints were obtained by manually steering the rover over the rows followed by the rover autonomously driving over the rows. The results showed that the robot achieved a mean absolute error (MAE) of 0.04 m, 0.06 m, and 0.09 m for the first, second and third passes of the experiment, respectively. The robot achieved an MAE of 0.06 m. When turning at the end of the row, the MAE from the RTK-GNSS-generated path was 0.24 m. The turning errors were acceptable for the open field at the end of the row. Errors while driving down the row did damage the plants by moving close to the plants’ stems, and these errors likely would not impede operations designed for the MPR. Therefore, the designed rover and control algorithms are good and can be used for cotton harvesting operations.

Cotton harvesting is performed by using expensive combine harvesters which makes it difficult for small to medium-size cotton farmers to grow cotton economically. Advances in robotics have provided an opportunity to harvest cotton using small and robust autonomous rovers that can be deployed in the field as a “swarm” of harvesters, with each harvester responsible for a small hectarage. However, rovers need high-performance navigation to obtain the necessary precision for harvesting. Current precision harvesting systems depend heavily on Real-Time Kinematic Global Navigation Satellite System (RTK-GNSS) to navigate rows of crops. However, GNSS cannot be the only method used to navigate the farm because for robots to work as a coordinated multiagent unit on the same farm because they also require visual systems to navigate, avoid collisions, and to accommodate plant growth and canopy changes. Hence, the optical system remains to be a complementary method for increasing the efficiency of the GNSS. In this study, visual detection of cotton rows and bolls was developed, demonstrated, and evaluated. A pixel-based algorithm was used to calculate and determine the upper and lower part of the canopy of the cotton rows by assuming the normal distribution of the high and low depth pixels. The left and right rows were detected by using perspective transformation and pixel-based sliding window algorithms. Then, the system determined the Bayesian score of the detection and calculated the center of the rows for the smooth navigation of the rover. This visual system achieved an accuracy of 92.3% and an F1 score of 0.951 for the detection of cotton rows. Furthermore, the same stereo vision system was used to detect the location of the cotton bolls. A comparison of the cotton bolls’ distances above the ground to the manual measurements showed that the system achieved an average R2 value of 99% with a root mean square error (RMSE) of 9 mm when stationary and 95% with an RMSE of 34 mm when moving at approximately 0.64 km/h. The rover might have needed to stop several times to improve its detection accuracy or move more slowly. Therefore, the accuracy obtained in row detection and boll location estimation is favorable for use in a cotton harvesting robotic system. Future research should involve testing of the models in a large farm with undefoliated plants.

Multiple small rovers can repeatedly pick cotton as bolls begin to open until the end of the season. Several of these rovers can move between rows of cotton, and when bolls are detected, use a manipulator to pick the bolls. To develop such a multi-agent cotton-harvesting system, each cotton-harvesting rover would need to accomplish three motions: the rover must move forward/backward, turn left/right, and the robotic manipulator must move to harvest cotton bolls. Controlling these actions can involve several complex states and transitions. However, using the robot operating system (ROS)-independent finite state machine (SMACH), adaptive and optimal control can be achieved. SMACH provides task level capability for deploying multiple tasks to the rover and manipulator. In this study, a center-articulated hydrostatic cotton-harvesting rover, using a stereo camera to locate end-effector and pick cotton bolls, was developed. The robot harvested the bolls by using a 2D manipulator that moves linearly horizontally and vertically perpendicular to the direction of the rover’s movement. We demonstrate preliminary results in an environment simulating direct sunlight, as well as in an actual cotton field. This study contributes to cotton engineering by presenting a robotic system that operates in the real field. The designed robot demonstrates that it is possible to use a Cartesian manipulator for the robotic harvesting of cotton; however, to reach commercial viability, the speed of harvest and successful removal of bolls (Action Success Ratio (ASR)) must be improved.

Maize is one of the most highly produced crops around the world. Factors such as population density, solar radiation, temperature, availability of nutrients and water, and proper tillage method can have favorable results in increasing yield. This project began in 2015, at two different locations in Georgia (Tifton and Camilla), GA, USA, and has been evaluated for three consecutive maize growing seasons. In each location, a different irrigation method was applied; the University of Georgia (UGA) maize checkbook method was utilized in Tifton and a soil moisture sensor-based method was utilized in Camilla. The different treatments consisted of two tillage methods, conservation and conventional, and four plant densities (69K, 88K, 99K, and 133K plants/ha). The purpose of the project was the evaluation of water requirements by population and tillage method for achieving high maize yields. Soil moisture information was collected hourly in both fields. The results showed that higher plant densities do not necessarily require higher irrigation amounts and do not always have the best results in terms of yield. Conventional tillage had slightly better yield results but not statistically different from conservation tilled plots. Additionally, the results showed that applied irrigation can help in higher maize production. However, increasing the amount of water does not directly equate to higher yield results.

Soil moisture prediction is a key parameter for effective irrigation scheduling and water use efficiency. However, accurate long-term prediction remains challenging, as most existing models excel in short- to medium-term prediction but struggle to capture the complex temporal dependencies and non-linear interactions of soil moisture variables over extended horizons. This study proposes a hybrid soil moisture prediction method, integrating a long short-term memory (LSTM) network and extreme gradient boosting (XGBoost) model for multistep soil moisture prediction at 24 h, 72 h, and 168 h horizons. The LSTM captures temporal dependencies and extracts high-level features from the dataset, which are then used by XGBoost for final predictions. The study uses real-world data from the D.A.T.A (Demonstrating Applied Technology in Agriculture) research farm at ABAC (Abraham Baldwin Agricultural College) Tifton, GA, USA, utilizing watermark soil moisture sensors and weather station’s data installed on the farm. Results show that the proposed method outperforms other hybrid models, achieving R² values of 98.67%, 98.54%, and 98.56% for 24, 72, and 168 h predictions, respectively. The study findings highlight that LSTM-XGBoost offers a precise long-term soil moisture prediction, making it a practical tool for real-time irrigation scheduling, enhancing water use efficiency in precision agriculture.