Autonomous Tractor Research Articles

Comparative analysis of texture descriptors in maize fields with plants, soil and object discrimination

Precision Agriculture aims to apply selective treatments and tasks at localized areas concerning crop fields. Robotized and autonomous tractors, equipped with perception, decision-making and actuation systems, can apply specific treatments as may be required. Correct plant identification through the perception system, including crops and weeds, is an important issue. Additionally, it is well known that, in autonomous vehicles, safety is a major challenge, where unexpected obstacles in the working area must be conveniently addressed in order to guarantee the security and the continuity of the process. The objective of this study was to design a tri-class Support Vector Machine classifier for identifying plants (crops and weeds), soil and objects in maize fields based on unsupervised learning. For this, a strategy for automatic sample selection was designed to obtain elements of the three involved classes for the training process. In this context, the identification of obstacles for safe navigation makes an important contribution. A comparative analysis of different texture descriptors and local patterns was carried out with the aim of determining the best for characterizing the classes under study; results have shown that the Speeded-Up Robust Features descriptor is the most appropriate to discriminate between plants, soil and objects. The development of an object detection algorithm for agricultural images proved the effectiveness of the tri-class classifier with an accuracy of 94.3%.

Navigation of autonomous tractor for orchards and plantations using a laser range finder: Automatic control of trailer position with tractor

The autonomous control of a tractor-trailer system in orchards and plantations has frequently been observed for the transportation, loading and unloading of products between plants and trees. The objective of this research was to develop a control algorithm for a single-sensor tractor-trailer navigation system for navigating within a row plantation and travelling between plots. A control scheme for stopping the tractor-trailer for various in-field tasks, such as product loading/unloading using a laser range finder (LRF), is presented. The LRF was used to navigate a full-size autonomous agricultural tractor equipped with a two-wheeled trailer. For ease of operation in narrow rows, a sliding hitch bar (SHB) was developed to control the trailer by adjusting the position of the hitch-point between the tractor and trailer. Compared to the tractor-trailer system driven by human, the control system could navigate the tractor-trailer with the RMS differences of 0.275 m (SD: 0.009 m), 0.373 m (SD: 0.030 m) and 0.518 m (SD: 0.022 m) for wide curve , tight curve and U-turn experimental paths, respectively. The SHB unit also supported the navigation system with wider turn for the trailer than conventional single hitch point about 0.383 m (7.66% of the 5 m path width, SD: 0.028 m), 0.762 m (15.23% of 5 m path width, SD: 0.010 m) and 1.094 m (21.88% of 5 m path width, SD: 0.037 m) for wide curve , tight curve and U-turn experimental paths, respectively. The control system also stopped the tractor-trailer at the specified landmarks. The results show that the navigation of the tractor-trailer was demonstrated with satisfactory accuracy and that the trailer position was controlled by the SHB with a wider turn in the experimental paths. Therefore, this laser-based landmark navigation system, and the SHB unit, can be adopted for different applications of autonomous tractor-trailer systems with controlled trailer positioning.

Side-to-side 3D coverage path planning approach for agricultural robots to minimize skip/overlap areas between swaths

Automated path planning is an important tool for the automation and optimization of field operations. It can provide the waypoints required for guidance, navigation and control of agricultural robots and autonomous tractors throughout the execution of these field operations. Typical field operations are repetitively required nearly every cropping season and therefore it should be carried out in a manner that maximizes the yield and minimizes operational cost, time and environmental impact taking into account the topographic land features. Current 3D terrain field coverage path planning algorithms are simply 2D coverage path planning projected into 3D through field terrain represented by the field’s Digital Elevation Model (DEM). When projecting 2D coverage plan into its 3D counterpart, the actual distance between adjacent paths on the topographic surface either increases or decreases, and consequently there might be skips or overlaps between adjacent paths on the slopes. In addition, when the machine rolls on slopes the effective width of the implement decreases by a similar amount to double this error and complicates the problem. Skips and overlaps can lead to an inefficient use of land and resources. In this paper, a numerical approach to estimate the total skip/overlap areas is developed and applied to determine the optimum-driving angle that minimizes this impact. Also, a novel side-to-side 3D coverage path planning approach, which ensures zero skips/overlaps regardless of the topographical nature of the field terrain, is developed. The approaches developed in this paper are tested and validated using a hypothetical test field of a tailored terrain and a real experimental field of uneven terrain nature. The proposed approaches illustrated that a significant percentage of uncovered area could be saved if appropriate driving angle is chosen and if a side-to-side 3D coverage is used.

Navigation of an Autonomous Tractor for a Row-Type Tree Plantation Using a Laser Range Finder—Development of a Point-to-Go Algorithm

It is challenging to develop a control algorithm that uses only one sensor to guide an autonomous vehicle. The objective of this research was to develop a control algorithm with a single sensor for an autonomous agricultural vehicle that could identify landmarks in the row-type plantation environment and navigate a vehicle to a point-to-go target location through the plantation. To enable such a navigation system for the plantation system, a laser range finder (LRF) was used as a single sensor to detect objects and navigate a full-size autonomous agricultural tractor. The LRF was used to control the tractor as it followed a path, and landmarks were detected “on-the-go” in real time. The landmarks were selected based on data for their distances calculated by comparison with the surrounding objects. Once the landmarks were selected, a target point was calculated from the landmarks, and the tractor was navigated toward the target. Navigation experiments were successfully conducted on the selected paths without colliding with the surrounding objects. A real time kinematic global positioning system (RTK GPS) was used to compare the positioning between the autonomous control and manual control. The results of this study showed that this control system could navigate the autonomous tractor to follow the paths, and the vehicle position differed from the manually driven paths by 0.264, 0.370 and 0.542 m for the wide, tight, and U-turn paths, respectively, with directional accuracies of 3.139°, 4.394°, and 5.217°, respectively, which are satisfactory for the autonomous operation of tractors on rubber or palm plantations. Therefore, this laser-based landmark detection and navigation system can be adapted to an autonomous navigation system to reduce the vehicle`s sensor cost and improve the accuracy of the positioning.

Towards agrobots: Identification of the yaw dynamics and trajectory tracking of an autonomous tractor

More efficient agricultural machinery is needed as agricultural areas become more limited and energy and labor costs increase. To increase their efficiency, trajectory tracking problem of an autonomous tractor, as an agricultural production machine, has been investigated in this study. As a widely used model-based approach, model predictive control is preferred in this paper to control the yaw dynamics of the tractor which can deal with the constraints on the states and the actuators in a system. The yaw dynamics is identified by using nonlinear least squares frequency domain system identification. The speed is controlled by a proportional–integral–derivative controller and a kinematic trajectory controller is used to calculate the desired speed and the desired yaw rate signals for the subsystems in order to minimize the tracking errors in both the longitudinal and transversal directions. The experimental results show the accuracy and the efficiency of the proposed control scheme in which the euclidean error is below 40cm for time-based straight line trajectories and 60cm for time-based curved line trajectories, respectively.

Leader-Follower Tracking System for Agricultural Vehicles: Fusion of Laser and Odometry Positioning Using Extended Kalman Filter

The aim of this research was to develop a safe human-driven and autonomous leader-follower tracking system for an autonomous tractor. To enable the tracking system, a laser range finder (LRF)-based landmark detection system was designed to observe the relative position between a leader and a follower used in agricultural operations. The virtual follower-based formation-tracking algorithm was developed to minimize tracking errors and ensure safety. An extended Kalman filter (EKF) was implemented for fusing LRF and odometry position to ensure stability of tracking in noisy farmland conditions. Simulations were conducted for tracking the leader in small and large sinusoidal curved paths. Simulated results verified high accuracy of formation tracking, stable velocity, and regulated steering angle of the follower. The tracking method confirmed the follower could follow the leader with a required formation safely and steadily in noisy conditions. The EKF helped to improve observation accuracy, velocity, and steering angle stability of the follower. As a result of the improved accuracy of observation and motion action, the tracking performance for lateral, longitudinal, and heading were also improved after the EKF was implemented in the tracking system.

Towards Agrobots: Trajectory Control of an Autonomous Tractor Using Type-2 Fuzzy Logic Controllers

Provision of some autonomous functions to an agricultural vehicle would lighten the job of the operator but in doing so, the accuracy should not be lost to still obtain an optimal yield. Autonomous navigation of an agricultural vehicle involves the control of different dynamic subsystems, such as the yaw angle dynamics and the longitudinal speed dynamics. In this study, a proportional-integral-derivative controller is used to control the longitudinal velocity of the tractor. For the control of the yaw angle dynamics, a proportional-derivative controller works in parallel with a type-2 fuzzy neural network. In such an arrangement, the former ensures the stability of the related subsystem, while the latter learns the system dynamics and becomes the leading controller. In this way, instead of modeling the interactions between the subsystems prior to the design of a model-based control, we develop a control algorithm which learns the interactions online from the measured feedback error. In addition to the control of the stated subsystems, a kinematic controller is needed to correct the errors in both the x- and the y- axis for the trajectory tracking problem of the tractor. To demonstrate the real-time abilities of the proposed control scheme, an autonomous tractor is equipped with the use of reasonably priced sensors and actuators. Experimental results show the efficacy and the efficiency of the proposed learning algorithm.

Wi-Fi and satellite-based location techniques for intelligent agricultural machinery controlled by a human operator.

In the new agricultural scenarios, the interaction between autonomous tractors and a human operator is important when they jointly perform a task. Obtaining and exchanging accurate localization information between autonomous tractors and the human operator, working as a team, is a critical to maintaining safety, synchronization, and efficiency during the execution of a mission. An advanced localization system for both entities involved in the joint work, i.e., the autonomous tractors and the human operator, provides a basis for meeting the task requirements. In this paper, different localization techniques for a human operator and an autonomous tractor in a field environment were tested. First, we compared the localization performances of two global navigation satellite systems’ (GNSS) receivers carried by the human operator: (1) an internal GNSS receiver built into a handheld device; and (2) an external DGNSS receiver with centimeter-level accuracy. To investigate autonomous tractor localization, a real-time kinematic (RTK)-based localization system installed on autonomous tractor developed for agricultural applications was evaluated. Finally, a hybrid localization approach, which combines distance estimates obtained using a wireless scheme with the position of an autonomous tractor obtained using an RTK-GNSS system, is proposed. The hybrid solution is intended for user localization in unstructured environments in which the GNSS signal is obstructed. The hybrid localization approach has two components: (1) a localization algorithm based on the received signal strength indication (RSSI) from the wireless environment; and (2) the acquisition of the tractor RTK coordinates when the human operator is near the tractor. In five RSSI tests, the best result achieved was an average localization error of 4 m. In tests of real-time position correction between rows, RMS error of 2.4 cm demonstrated that the passes were straight, as was desired for the autonomous tractor. From these preliminary results, future work will address the use of autonomous tractor localization in the hybrid localization approach.

Comparison of Positional Accuracy betweenRTK and RTX GNSS Based on the Autonomous Agricultural Vehicles under Field Conditions

<abstract> <bold><sc>Abstract. </sc></bold>Currently, many systems (machine vision, high resolution remote sensing, global positioning systems, and odometry techniques) have been integrated into agricultural equipment to increase the efficiency, productivity, and safety of the individual in all field activities. This study focused upon assessing a satellite-based localization solution used in straight path guidance of an autonomous vehicle developed for agricultural applications. The autonomous agricultural vehicle was designed and constructed under RHEA (Robot fleets for highly effective agriculture and forestry management) project and is part of a three-unit fleet of similar vehicles. Static tests showed that 99% of all positions are placed within a circle with a 2.9 cm radius centered at the geo-position using real-time satellite corrections (RTX). Dynamic tests between rows demonstrated a mean (N=610) of the standard deviation for real-time base station corrections (RTK) of 1.43 cm and for real-time satellite corrections (RTX) of 2.55 cm. These results demonstrate that the tractor was able to track each straight line with high degree of accuracy. The integration of a Global Navigation Satellite System (GNSS) with sensors (e.g., inertial sensor, altimeters, odometers, etc.) within the vehicle showed the potential of autonomous tractors for expanding agricultural applications utilizing this technology.

Nonlinear modeling and identification of an autonomous tractor–trailer system

This paper presents the nonlinear modeling of the yaw and longitudinal dynamics of a tractor–trailer system. First, the yaw dynamic models of both the tractor and trailer are derived considering the lateral forces and side-slip angles. In order to be able to calculate the side-slips precisely, the relaxation length approach is preferred. Since the obtained yaw dynamic models are nonlinear, a constrained nonlinear optimization problem is formulated for the parameter estimation. Second, the longitudinal dynamic model for the system is derived based-on the static and dynamic responses. The static model consist of two inputs, the hydrostat position and the diesel engine speed, and one output, the longitudinal speed of the system. Afterwards, a dynamic model is proposed to define the dynamic effect between the output of the static model and the actual longitudinal speed. Third, the mathematical models of the steering mechanisms both for the tractor and trailer are identified. Consequently, a complete nonlinear dynamic model for the tractor–trailer system is obtained. The overall resulting model is thought to provide useful physical insight on such a complex mechatronic system, and can serve as the input for model based controller design.

Distributed nonlinear model predictive control of an autonomous tractor–trailer system

This paper addresses the trajectory tracking problem of an autonomous tractor–trailer system by using a fast distributed nonlinear model predictive control algorithm in combination with nonlinear moving horizon estimation for the state and parameter estimation in which constraints on the inputs and the states can be incorporated. The proposed control algorithm is capable of driving the tractor–trailer system to any desired trajectory ensuring high control accuracy and robustness against environmental disturbances.

Effect of standardized management of hypertension in the community on vascular function

This paper addresses the trajectory tracking problem of an autonomous tractor–trailer system by using a fast distributed nonlinear model predictive control algorithm in combination with nonlinear moving horizon estimation for the state and parameter estimation in which constraints on the inputs and the states can be incorporated. The proposed control algorithm is capable of driving the tractor–trailer system to any desired trajectory ensuring high control accuracy and robustness against environmental disturbances.

Steering Characteristics of an Autonomous Tractor with Variable Distances to the Waypoint

Autonomous agricultural machines that are operated in small-scale farmland frequently experience turning and changes in direction. Thus, unlike when they are operated in large-scale farmland, the steering control systems need to be controlled precisely so that travel errors can be minimized. This study aims to develop a control algorithm for improving the path tracking performance of a steering system by analyzing the effect of the setting of the waypoint, which serves as the reference point for steering when an autonomous agricultural machine moves along a path or a coordinate, on control errors. A simulation was performed by modeling a 26-hp tractor steering system and by applying the equations of motion of a tractor, with the use of a computer. Path tracking errors could be reduced using an algorithm which sets the waypoint for steering on a travel path depending on the radius of curvature of the path and which then controls the speed and steering angle of the vehicle, rather than by changing the steering speed or steering ratio which are dependent on mechanical performance.

Optimal working time distribution and routing for autonomous tractors based on heuristic algorithms

We consider the operation planning problem for autonomous tractors serving spatially distributed objects (farms). The working time distribution and routing are optimized in the sense of non-working time minimization. Task controller performs control within the framework of the information system on a farm. Two heuristic algorithms based on the continuoustime knapsack problem are described. A constraint on route duration is taken into account. Operation of the algorithms is illustrated by numerical examples.

High-Speed Adaptive Nonlinear Predictive Control for Autonomous Tractor Navigation

In the presented paper a Moving Horizon Estimation(MHE)/Model Predictive Control(MPC) framework is employed to allow for the autonomous navigation of a small-scale tractor being equipped with a Real-Time Kinetic Global Positioning System(RTK-GPS). In the real-time experiments the objective is to manipulate a velocity and a steering actuator such that the tractor follows a curved trajectory on a wet and bumpy grass field. The nonlinear model is adaptive in a sense that slip parameters have to be identified online for longitudinal and side slipping respectively. Feedback times within 0.6-2.8 ms have been obtained with the code generation tool of the ACADO toolkit.

English

The study was carried out to automate the operation of the 'Bobcat' tractor for the farming purpose. Bobcat tractor is a hydrostatic tractor that uses levers for steering, breaking and the forward and backward movements. Two set of screw shaft driven by car power window motor were used to move the two levers. The computer program was written to automate the movement of each lever. Bobcat tractor move straight forward when both levers move forward and vice versa. Bobcat tractor will turn left when only the left lever is moved forward and vice versa. The friction between the levers and the attachment was a major concern in this project. The bearing was introduced and the existence space between the levers and the attachment can solve the friction problem. Autonomous tractor increases the effectiveness of the field with little or no help of supervision. Keywords; Bobcat Tractor, Autonomous Tractor, Bio-Production Vehicle, Hydrostatic drive, Lever steering, Master-Slave Tractor

Navigation Using a Laser Range Finder for Autonomous Tractor (Part 1)

Navigation Using a Laser Range Finder for Autonomous Tractor (Part 1)

Navigation Using a Laser Range Finder for Autonomous Tractor (Part 2)

Navigation Using a Laser Range Finder for Autonomous Tractor (Part 2)

Editorial: Special issue on agricultural robotics

It can be argued that one of the earliest forms of robotics is agricultural automation, now undergoing a great revival in its activities. Its importance in the productivity of the agricultural crops is well established, but recent advancements in agricultural robotics seek not only to improve farming capacity with minimal human interference, but also to improve the efficiency of the tasks and the quality of the resulting crops through greater precision of the handling of the agricultural processes. This has seen the development in agricultural robotics centred around two main key phrases: autonomous agriculture and precision agriculture. The former is aimed at developing a capability to operate large farming facilities withminimumhumanmanpower, such as by the development of autonomous tractors or coordinated teams of tractors and sensor networks to monitor a large farming area. The latter aims at developing precise data-gathering as well as crop or produce handling, such as selective spraying on plants as opposed to the traditionalmethod of non-selectively spraying the entire field. Obviously, many applications also fall within both key phrases. This special issue of Springer Journal of Intelligent Service Robotics on Agricultural Robotics seeks to present the latest developments in this exciting field of robotics research. The agricultural environment today serves not only as a client to which existing fundamental techniques of robotics are applied, but also as the source of challenges to the invention

Development of Steering Control System based on CAN for Autonomous Tractor System

A steering control system based on CAN(Controller Area Network) for autonomous tractor was developed to reduce duty of a central processing computer and to improve performance of steering control in terms of reduced control interval and error. The steering control system consisted of a SCU (Steering Control Unit), an EHPS system, and a potentiometer. The SCU consisted of an MCU (Micro Controller unit), an A/D converter, and a DC-DC converter, and a PID controller was used to control steering angle. The steering control system was communicated with the computer by CAN-bus. Each actuator and implement was connected to a multi-function board interfacing with the computer through a USB cable. Without CAN, control interval of the autonomous tractor was 1.5 seconds. When the CAN-based steering control system was combined with the autonomous tractor, however, control interval of the integrated system was reduced to those less than 0.05 seconds. When the autonomous tractor was operated with 1.5-s and 0.05-s control cycles at a 0.63-m/s travelling speed, the trajectories were close to straight lines for both of the control cycles. For a 1.34-m/s traveling speed, tractor trajectory was close to sine wave with a 1.5-s control cycle, but was straight line with a 0.05-s control cycle.