Autonomous Tractor Research Articles

Automation and AI in Precision Agriculture: Innovations for Enhanced Crop Management and Sustainability

Precision agriculture is one of the ways to achieve food security and sustainability through better resource-use optimization and crop productivity dealing with the challenges posed by the growing population and addressing environmental concerns. The study offers an in-depth look at the most recent developments in artificial intelligence (AI) and automation in precision agriculture (PA), with a particular emphasis on important technologies such as drones, autonomous tractors, AI-driven irrigation systems, and predictive analytics for crop management. The accuracy of crop monitoring and health assessments has increased by 30–50 percent as a result of AI-powered solutions, which have improved resource-based decision-making. Systems for precision irrigation and fertilization have increased crop yields by 5–15 percent when using 25–40 percent less water and 30-40 percent less fertilizer, respectively. Robotic harvesters and sprayers are examples of automation technologies that have reduced labor expenses by 20–40 percent and increased operational efficiency by 35 percent. Additionally, AI-based prediction models have reduced pest damage by 20–25 percent and reached an accuracy of 85–90 percent for crop yield forecasts and pest control. Despite these developments, issues of scalability, affordability for small farms, and data privacy still exist, which can hinder technology adoption among farmers. The evaluation follows by outlining ideas for future research, such as 5G, blockchain, and AI integration with cloud and edge computing. These technologies could improve decision-making and transparency in precision agriculture by enabling real-time data transmission, secure data management, and enhanced traceability, thus addressing current limitations and fostering trust among stakeholders.

Role of Artificial Intelligence in Vegetable Production: A Review

Role of Artificial Intelligence (AI) in vegetable production, emphasizing its potential to address critical challenges such as climate change, population growth, and resource scarcity. AI technologies, including machine learning, computer vision, and robotics, are revolutionizing agricultural practices. AI-driven innovations in crop management, pest control, and soil analysis enhance productivity, reduce labour costs, and ensure sustainable farming practices. Notable advancements include precision spraying by Blue River Technology, significantly reducing herbicide use, and deploying autonomous tractors and drones for efficient farm management. AI applications, such as PEAT's Plantix and Trace Genomics, provide accurate diagnostics for soil health and pest management. Satellite-based solutions like Farm Shots and aWhere offer real-time crop monitoring and weather prediction, optimizing resource use and mitigating risks. The review highlights the importance of making AI technologies more affordable and accessible to farmers, particularly in developing regions. Collaboration between researchers, industry stakeholders, and policymakers is crucial to harness AI's full potential in agriculture. As AI continues to evolve, its integration into vegetable production promises a more efficient, resilient, and sustainable agricultural sector, contributing to global food security and environmental preservation. The aim of the study is to evaluate the impact and effectiveness of Artificial Intelligence (AI) in vegetable production, focusing on how AI technologies enhance productivity, efficiency, and sustainability. The objectives are to assess current AI applications, analyze their benefits and challenges, and provide recommendations for future improvements and wider adoption in the agricultural sector. The research methodology for the study on the role of Artificial Intelligence in vegetable production involves a comprehensive literature review of existing AI technologies and their applications in agriculture, coupled with the analysis of case studies to evaluate real-world implementations. Additionally, expert interviews and surveys with farmers and industry professionals will be conducted to gather insights on the benefits, challenges, and future potential of AI in this sector. The theoretical implications of the study on the role of Artificial Intelligence in vegetable production include advancing the understanding of AI's capabilities in agricultural optimization and contributing to the academic discourse on sustainable farming practices. Practically, the study provides actionable insights for farmers and agribusinesses on implementing AI technologies to enhance crop yields, reduce resource wastage, and improve overall farm management efficiency.

Intelligent Surface Recognition for Autonomous Tractors Using Ensemble Learning with BNO055 IMU Sensor Data

This study aims to enhance the navigation capabilities of autonomous tractors by predicting the surface type they are traversing using data collected from BNO055 Inertial Measurement Units (IMU sensors). IMU sensor data were collected from a small mobile robot driven over seven different floor surfaces within a university environment, including tile, carpet, grass, gravel, asphalt, concrete, and sand. Several machine learning models, including Logistic Regression, K-Neighbors, SVC, Decision Tree, Random Forest, Gradient Boosting, AdaBoost, and XGBoost, were trained and evaluated to predict the surface type based on the sensor data. The results indicate that Random Forest and XGBoost achieved the highest accuracy, with scores of 98.5% and 98.7% in K-Fold Cross-Validation, respectively, and 98.8% and 98.6% in an 80/20 Random State split. These findings demonstrate that ensemble methods are highly effective for this classification task. Accurately identifying surface types can prevent operational errors and improve the overall efficiency of autonomous systems. Integrating these models into autonomous tractor systems can significantly enhance adaptability and reliability across various terrains, ensuring safer and more efficient operations.

Bi-level path tracking control of tractor semi-trailers by coordinated active front steering and differential braking

In recent years, autonomous tractor semi-trailers have been considered a promising solution for transportation on highways, ports, and large logistics centers to improve safety and efficiency. However, due to the complicated dynamics introduced by articulation structure, there are still challenges in achieving high-precision path tracking and stability control for tractor semi-trailers, especially in critical scenarios. In this work, a bi-level path tracking control scheme for the autonomous tractor semi-trailer is proposed. At the higher level, a robust model predictive controller coordinating active front steering and differential braking is devised for addressing path tracking, stability control and robustness for an autonomous tractor semi-trailer. At the lower level, incorporating a logic switching mechanism, the designed optimal braking torque distribution module and the PID-based longitudinal control module prioritize the implementation of differential braking and target speed tracking. Simulation results demonstrate that the proposed control strategy offers remarkable path tracking performance in three designed testing scenarios.

A model-free adaptive predictive path-tracking controller with PID terms for tractors

An efficient tractor path-tracking method can increase the operational accuracy, improve land utilisation, and more efficiently provide services for autonomous tractors and precision agriculture. In this study, a model-free adaptive predictive control-proportional-integral-derivative (MFAPC-PID) method was devised. Based on preview theory, a tracking system based on course deviation angle was designed. After the tracking system was linearised, an MFAPC tracking system was developed, and its inherent defects were analysed. Referring to the control structure of an incremental PID algorithm, the MFAPC was considered as an adaptive integral item, and the MFAPC-PID controller was obtained by adding adaptive proportional and differential terms. To verify the proposed controller, collaborative simulation and hardware-in-the-loop tests were performed. The controller was simulated and tested under different paths, road surfaces, and tractor models. Compared with other methods, the MFAPC-PID path-tracking method exhibits superior comprehensive performance, adaptability, universality, and robustness. Moreover, the MFAPC-PID method is insensitive to external interference and model changes of controlled objects.

Heuristic cooperative coverage path planning for multiple autonomous agricultural field machines performing sequentially dependent tasks of different working widths and turn characteristics

Coverage path planning is a central task in agricultural field operations such as tillage, planting, cultivation, and harvesting. In future visions, manual operation will be replaced by fleets of autonomous agricultural vehicles that perform the tasks autonomously. A step towards this transition is to enable simultaneous and safe cooperation of autonomous vehicles on the field. In this article a novel approach is presented for coverage path planning (CPP) for two autonomous tractors that perform sequentially dependent tasks simultaneously on the same area. The approach is based on the idea of computing the coverage solutions for each task by dividing them into short paths that consist of a swath and a turn. The approach ensures collision avoidance by examining that the simultaneous short paths, operated by different tractors, do not collide geometrically, and then schedules them to be operated simultaneously in real-time. The approach was demonstrated successfully in a real-world test environment with two autonomous tractors. The tractor that performed the first task was equipped with a disc cultivator and the second tractor was equipped with a seed drill. A test area of 0.8 ha was used for the demonstration drive, during which the tractors drove 22 swaths simultaneously. Both tractors completed their respective tasks.

Trajectory Re-Planning and Tracking Control for a Tractor–Trailer Mobile Robot Subject to Multiple Constraints

Autonomous tractor–trailer robots possess a broad spectrum of applications but pose significant challenges in control due to their nonlinear and underactuated dynamics. Unlike the tractor, the motion of the trailer cannot be directly actuated, which often results in a deviation from the intended path. In this study, we introduce a novel method for generating and following trajectories that circumvent obstacles, tailored for a tractor–trailer robotic system constrained by multiple factors. Firstly, leveraging the state information of both the obstacles and the desired trajectory, we formulate an improved trajectory for obstacle avoidance using the nonlinear least squares method. Subsequently, we propose an innovative tracking controller that integrates a universal barrier function with a state transformation strategy. This amalgamation facilitates the accurate tracking of the prescribed trajectory. Our theoretical analysis substantiates that the proposed control methodology ensures exponential convergence of the line-of-sight (LOS) distance and angle tracking errors, while enhancing the transient performance. To validate the efficacy of our approach, we present a series of simulation results, which demonstrate the applicability of the developed control strategy in managing the complex dynamics of tractor–trailer robots.

Extending the Framework for Developing Intelligent Virtual Environments (FIVE) with Artifacts for Modeling Internet of Things Devices and a New Decentralized Federated Learning Based on Consensus for Dynamic Networks.

One of the main lines of research in distributed learning in recent years is the one related to Federated Learning (FL). In this work, a decentralized Federated Learning algorithm based on consensus (CoL) is applied to Wireless Ad-hoc Networks (WANETs), where the agents communicate with other agents to share their learning model as they are available to the wireless connection range. When deploying a set of agents, it is essential to study whether all the WANET agents will be reachable before the deployment. The paper proposes to explore it by generating a simulation close to the real world using a framework (FIVE) that allows the easy development and modification of simulations based on Unity and SPADE agents. A fruit orchard with autonomous tractors is presented as a case study. The paper also presents how and why the concept of artifact has been included in the above-mentioned framework as a way to highlight the importance of some devices used in the environment that have to be located in specific places to ensure the full connection of the system. This inclusion is the first step to allow Digital Twins to be modeled with this framework, now allowing a Digital Shadow of those devices.

Model Predictive Control Based Path Planner Design for On-road Autonomous Tractor Trailer Vehicles

Efficient path planning for on-road autonomous tractor trailer vehicles (ATTVs) is a complex task due to the intricate kinematics introduced by the articulated trailer. This technical paper introduces a novel Model Predictive Control (MPC) based lateral path planner designed to address the unique challenges of maneuvering ATTVs, particularly in environments that require navigation through narrow spaces and around multiple obstacles on well-structured roads. The authors have expertly developed a Cartesian kinematic model tailored for ATTVs and have innovatively applied the Frenet frame to better apply constraints in structured road environments. The efficacy of the proposed path planner is confirmed through real-time testing on actual roadways, showcasing its practical application and the advantages it offers over existing methods.

Tire modeling for an autonomous tractor suitable for soft soils

Off-road autonomous vehicles such as tractors and agricultural machinery require an important power traction to cope with mobility issues on soft soils and rough terrains. This paper presents a simplified version of tyre modeling as an adapted Burckhardt tire model based on an analytical Bekker-Wong wheel-soil interaction model. The Bekker-Wong model is a fractional model in space and takes into account the plasticity theory and soil mechanics, however such a model is too complex to be usable in real-time. An adapted version of the Burckhardt model helps having a more compact model that can be usable in real-time. In this paper, an adapted Burckhardt tire model has been optimized for the E-Tract simulator and experiments have been carried out to validate the tractor simulator.

Vision-based autonomous navigation stack for tractors operating in peach orchards

Recently, camera-based approaches have been proposed to replace expensive LiDAR or real-time kinematic (RTK) based solutions for the unmanned tractors operating in an orchard-like environment. However, constructing a completely autonomous navigation stack with a low-costly camera and onboard computer presents extra difficulties, such as a computationally efficient perception model, rapid path planning without costly SLAM, and the capacity to avoid obstacles. In this paper, a novel vision-based autonomous navigation stack is devised to address challenges of the wholly autonomous tractor using stereo camera and inertial measurement unit (IMU) that are inexpensive. The computational pipeline consists primarily of three modules: (1) the multi-task perception network, (2) the frame transformation algorithm, and (3) the motion planning module. The multi-task perception network detects tree trunks, obstacles, and traversable areas simultaneously from the RGB image with high efficiency (69 FPS) and accuracy (mAP@.5 of 96.7% and mIoU of 98.1%). For global path planning and trajectory prediction, the frame transformation algorithm integrates the downsized the navigational features and transforms them to the tractor frame from the image frame. The motion planning module then uses the fused data to plan the appropriate path (i.e., the center of the tree row, U-turn path, or J-turn path) and search for the optimal trajectory utilizing the optimized dynamic window approach (DWA) for path tracking. In the peach orchard, the proposed stack is implemented on our autonomous retrofitted tractor and its efficacy is demonstrated compared with the human-driving tractor.

Main Paths of Creation of Autonomous (Unmanness) Tractors

The prerequisites, main paths and achievements in the field of creating autonomous (unmanned) tractors, and their development trends are considered. It has been revealed that the use of autonomous tractors makes it possible to create highly intelligent automated production of agricultural products. The purpose of using such tractors is to replace human labor, minimize the harmful effects of chemicals on humans and the environment, and increase the efficiency of agricultural production.

Numerical Analysis of Autonomous Tractors on S-shaped Track based on math models

Autonomous vehicles today have increased the attention of academics, the industrial sector, and agriculture with intelligent vehicle technology that showcases multidisciplinary science using a range of Artificial Intelligence (AI) equipped with sensors and controls. One of the things that are needed in agriculture is an autonomous tractor to relieve all the work in the agricultural field. Therefore, this study aims to analyze the speed of an autonomous tractor path with S coordinates with a speed of 18 km/h and a time of 15 sec to determine how strong the vehicle performs when driving on a winding lane and improve driver safety. In this study, a numeric analysis of the speed of the autonomous tractor path was carried out using a simulation method using Carsim software based on the Math Model. The numerical results obtained in graphs and curves demonstrate the simulator can analyze tractor performance, reduce accident rates, and improve safety in agriculture.

AgRIS: wind-adaptive wideband reconfigurable intelligent surfaces for resilient wireless agricultural networks at millimeter-wave spectrum

Wireless networks in agricultural environments are unique in many ways. Recent measurements reveal that the dynamics of crop growth impact wireless propagation channels with a long-term seasonal pattern. Additionally, short-term environmental factors, such as strong wind, result in variations in channel statistics. Next-generation agricultural fields, populated by autonomous tractors, drones, and high-throughput sensing systems, require high-throughput connectivity infrastructure, resulting in the future deployment of high-frequency networks, where they have not been deployed before. More specifically, when millimeter-wave (mmWave) communication systems, a viable candidate for 5G and 6G high-throughput solutions, are deployed for higher throughput, these issues become more prominent due to the relatively small wavelength at this frequency band. To improve coverage in the mmWave spectrum in agricultural settings, reconfigurable intelligent surfaces (RISs) are a promising solution with low energy consumption and high cost efficiency when compared to half-duplex active relays with multiple antennas. To ensure link resiliency under dynamic channel behavior, an adaptive RIS for broadband wireless agricultural networks (AgRIS) at mmWave band is designed in this work. AgRIS relies on output from a time-series model that forecasts the short-term wind speed based on measured wind data, which is readily available in most farms. The temporal correlation between link reliability and wind speed is demonstrated through extensive field experiments. Our simulation results demonstrate that AgRIS with a small footprint of 11 × 11 elements can help mitigate the adversarial effects of wind-induced signal level drop by up to 8 dB and provides high energy efficiency of 1 Gbits/joule.

An obstacle avoidance path planner for an autonomous tractor using the minimum snap algorithm

Autonomous tractors use a GNSS-based approach combined with other sensors to provide higher efficiency and minimize human intervention. The basis of field automated navigation is the agricultural route planning of the entire field. One of the main aspects of agricultural route planning is obstacle avoidance path planning, which can provide a safe continuous trajectory for autonomous tractors to pass obstacles. In this study, a collision-free path planning method was proposed using the minimum snap algorithm to enable the tractor to safely navigate from one point to another. To authenticate the proposed algorithm, a tripartite experimental scheme was designed, encompassing a ROS-based simulation, robot platform validation, and a field test. Simulation results demonstrate that the collision-free path generated by the proposed algorithms can effectively guide the tractor to follow the given path with a lateral error of 1.75 cm. For the robot platform validation test, the mean lateral deviations were 2.63 cm, 5.01 cm, and 6.80 cm at speeds of 0.5 m/s, 0.8 m/s, and 1.0 m/s, respectively. The feasibility of using the developed algorithms was followed by a field test with a 162-KW CVT autonomous tractor. The mean lateral deviations were 5.17 cm, 5.13 cm, and 6.10 cm at speeds of 0.6 m/s, 0.8 m/s, and 1.0 m/s, respectively. The test results showed that the model could provide a safe and stable collision-free path for agricultural machines operating in the field.

ТРЕНДИ В РОБОТИЗАЦІЇ МОБІЛЬНИХ СІЛЬСЬКОГОСПОДАРСЬКИХ ЗАСОБІВ

Summary The purpose of this article is research of the level of development and features of agricultural robots offered by global manufacturers and directions of robotics and their technological use in field crop rotations;the structuring and assessment of the prospects for the use of robotic agricultural autonomous means (robots) in field crop rotation. Methods: сase-studies of robotic agricultural autonomous means (robots) that are proposed for the use of mechanized processes in field crop rotations; structuring of technical solutions of robots according to their technological features and energy sources; analysis of navigation algorithms, sensor systems, artificial intelligence and other important components that are characteristic of field robots; identification of key developers/manufacturers of field robots, features of their proposed directions of robotics and technological use in field crop rotations; assessing the prospects for the application of field robots and the technological benefits of their application and taking into account the challenges such as legal aspects, safety and acceptance of the technology by farmers. Results. The conducted factor analyzes of the structural elements of field robots show that both traditional tractors and special chassis are used to transform energy into traction and drive capacity, and different levels of sensor and software are achieved. This made it possible to assess the autonomy levels of field robots and predict the scope of application depending on the power. The tractor, retrofitted with sensors and appropriate programs, provides semi-autonomous performance of basic operations in a unit with traditional agricultural machines in field crop rotations, but the presence of a person is still mandatory. Conclusions. New directions for the development of field robots use convergent technologies and are based on the deep modernization of tractors and the use of specially designed chassis with their own transmissions (concepts), the use of new energy sources and a significantly higher level of autonomy and remote control of work modes. Concepts are created as single designs and are oriented towards the performance of separate operations in a unit with agricultural machines, or with special attachments for working bodies and even in single-row execution. As a rule, they have an electric transmission, but not high power, which narrows the scope of their application. Keywords: robotic agricultural tools, field robots, autonomous tractors, electric tractors, agricultural robots, control systems of agricultural tools, mobile autonomous tools.

A vision-based road detection system for the navigation of an agricultural autonomous tractor

A vision-based road detection system for the navigation of an agricultural autonomous tractor

Optimal Path Generation with Obstacle Avoidance and Subfield Connection for an Autonomous Tractor

As autonomous tractors become more common crop harvesting applications, the need to optimize the global servicing path becomes crucial for maximizing efficiency and crop yield. In recent years, several methods of path generation have been researched, but very few have studied their applications on complex field shapes. In this study, a method of creating the optimal servicing path for simple and complex field shapes is proposed. The proposed algorithm creates subfields for a target land, optimizes the track direction for several subfields individually, merges subfields that result in overall increased efficiency, and finds the minimum non-operating paths to travel from subfield to subfield while selecting the respective optimal subfield starting locations. Additionally, it is required that this process must be done within 3 seconds to meet performance requirements. Results from 3 separate field shapes show that the field traversal efficiency can range from 68.0% to 94.4%, and the coverage ratio can range from 98.8% to 99.9% for several different conditions. In comparison with previous studies using the same field shape, the proposed methods demonstrate an increase of 5.5% in field traversal efficiency.

Impact of lowered vehicle weight of electric autonomous tractors in a systems perspective

Modern agriculture rely on heavy machinery that has increased risk of detrimental soil compaction of arable fields. This can lead to negative effects such as reduced yields, reduced field trafficability and increased fuel use. Electric, autonomous tractors makes it possible to replace one heavy machine with several lighter without increased labour costs. In this study, the economic and environmental effects of reduced soil compaction for smaller autonomous tractors were assessed and compared to a scenario with conventional tractors. A discrete event simulation of a Swedish 200 ha grain farm with clay soil was used for the calculations. The electric, autonomous system had lower soil compaction impacts as well as other benefits, and reduced cost in total from 385 to 258 € ha-1 and the climate impact from 270 to 77 kg CO2eq ha−1 compared to the conventional scenario. Soil compaction constituted 20% of the cost and 26% of the climate impact for the conventional scenario. It was concluded that soil compaction was impactful in machinery studies, especially on heavier soil like clay, and should not be omitted. Soil compaction avoidance alone was not impactful enough to warrant a change to electric, autonomous tractors but it reinforced already existing trends and further improved the cost and environmental benefits.

강화학습을 이용한 자율주행 트랙터의 가변형 전방주시거리 튜닝 알고리즘 개발

Robust path tracking is important for an autonomous tractor to accurately track a path, including straight and curved paths, with headland turning in farmlands. To improve the performance of a path-tracking method developed on the basis of fixed look-ahead distances, this paper presents a look-ahead distance tuning algorithm based on reinforcement learning (RL). The RL architecture is designed to provide variable look-ahead distances in real time based on navigation conditions caused by changes in the lateral deviations and heading errors. The RL agent performed self-learning in the simulation while following C-type turning-based paths. For more effective RL, a simulation model was built by applying the actual responses of a tractor steering system measured using a data acquisition system. An evaluation test was conducted in terms of the lateral deviation in response to the reference path. The proposed method improved the path-tracking accuracy of the lateral deviation by a root mean-squared error of about 62% compared to a path-tracking controller with fixed look-ahead distances.