Fig 1 - uploaded by Jan Tommy Gravdahl
Content may be subject to copyright.
Source publication
![Fig. 6. With the system initialized at [x, y] = [0 0.1] the NMPC...](profile/Jan-Gravdahl/publication/274010435/figure/fig3/AS:614067806933009@1523416582234/With-the-system-initialized-at-x-y-0-01-the-NMPC-controller-use-the-first-to_Q320.jpg)
![Fig. 9. The position xy plot for the robot, when initialized at [x, y]...](profile/Jan-Gravdahl/publication/274010435/figure/fig5/AS:614067806945289@1523416582293/The-position-xy-plot-for-the-robot-when-initialized-at-x-y-0-017-This-initial_Q320.jpg)
Vehicles which operate in agricultural row crops, need to strictly follow the established wheel tracks. Errors in navigation where the robot sways of its path with one or more wheels may damage the crop plants. The specific focus of this paper is on an agricultural robot operation in row cultures. The robot performs machine vision detecting weeds w...
Context in source publication
Context 1
... review by Slaughter 2008 presents an overview of the field [2]. The robotic platform has two front wheels with electro motors and two rear castor wheels, Figure 1. The robot has a monocular downward facing RGB camera primarily used for two purposes: Classification of crop and weed plants as part of the spray-on-demand system [3], and for visual odometry measurements as input to the localization filter and crop-row detection. ...
Citations
... Precision spraying systems adapt specific types of spray nozzles or fertilizer dispensers according to ambient conditions to provide optimal coverage and dosage efficiency while minimizing chemical use [78]. Precision spraying and fertilization play a crucial role in modernizing farming practices by maximizing input Fig. 4 Robotics weeder and herbicide applicator arm in operations [64] effectiveness, reducing environmental impact, and lowering operational costs with safety, thus enhancing sustainability and productivity [79]. ...
Enhancing agricultural productivity with current farming technologies depends greatly on improvements in agricultural vehicle technology, especially in precision farming. This analysis thoroughly examines the incorpora- tion of autonomous all-terrain vehicles (AATVs) in preci- sion agriculture, emphasizing their technological progress, uses, and future potential. AATVs revolutionize farming methods through the use of sophisticated sensors, artificial intelligence, and robotics, allowing for accurate and self- governing performance in a range of agricultural activities. They improve the management of resources, reduce environ- mental footprint, and boost effectiveness through the use of real-time data analysis to apply chemical fertilizers, insec- ticides, and other inputs precisely. Yet, obstacles including technological complexities, legislative obstacles, and wor- ries regarding accessibility and affordability hinder broad acceptance. The future shows appealing developments, such as the incorporation of AATVs with advanced technologies like blockchain and IoT, suggesting enhanced capabilities. Although facing obstacles, AATVs represent innovation, offering a future where agriculture can be more sustainable, efficient, and productive. The shift towards precision agri- culture represents a progression marked by technological advancements and a dedication to influencing a more sus- tainable future for farming practices worldwide. AATVs are evolving and playing a key role in transforming agricultural landscapes, envisioning a future where technology enhances efficient, sustainable, and responsible farming operations.
... Their robot was able to navigate autonomously through speed control and path tracking by calculating the deviation between a reference straight line and the available path. A very similar approach is used in [54] where the authors performed kinematic and dynamic modeling and simulation of their robot in which the navigation is performed by minimizing the camera offset with respect to a crop field track using the nonlinear model predictive control (NMPC). Gao et al. [55] developed a path planning algorithm for spraying in orchards having an accuracy of 97.5%. ...
High cost, time intensive work, labor shortages and inefficient strategies have raised the need of employing mobile robotics to fully automate agricultural tasks and fulfil the requirements of precision agriculture. In order to perform an agricultural task, the mobile robot goes through a sequence of sub operations and integration of hardware and software systems. Starting with localization, an agricultural robot uses sensor systems to estimate its current position and orientation in field, employs algorithms to find optimal paths and reach target positions. It then uses techniques and models to perform feature recognition and finally executes the agricultural task through an end effector. This article, compiled through scrutinizing the current literature, is a step-by-step approach of the strategies and ways these sub-operations are performed and integrated together. An analysis has also been done on the limitations in each sub operation, available solutions, and the ongoing research focus.
... To achieve highly accurate tracking performance for constrained navigation in row crops, nonlinear RHC approaches have been widely used, particularly in agricultural applications as they are capable of taking constraints on states and inputs into account and can be designed for nonlinear models [Backman et al., 2012, Utstumo et al., 2015, Kayacan et al., 2018. Additionally, an accurate online estimation of traction parameters in a system model is crucial as the tiresoil interactions change throughout operations in varying, slippery conditions. ...
Accurate steering through crop rows that avoids crop damage is one of the most important tasks for agricultural robots utilized in various field operations, such as monitoring, mechanical weeding, or spraying. In practice, varying soil conditions can result in off-track navigation due to unknown traction coefficients so that it can cause crop damage. To address this problem, this paper presents the development, application, and experimental results of a real-time receding horizon estimation and control (RHEC) framework applied to a fully autonomous mobile robotic platform to increase its steering accuracy. Recent advances in cheap and fast microprocessors, as well as advances in solution methods for nonlinear optimization problems, have made nonlinear receding horizon control (RHC) and receding horizon estimation (RHE) methods suitable for field robots that require high frequency (milliseconds) updates. A real-time RHEC framework is developed and applied to a fully autonomous mobile robotic platform designed by the authors for in-field phenotyping applications in Sorghum fields. Nonlinear RHE is used to estimate constrained states and parameters, and nonlinear RHC is designed based on an adaptive system model which contains time-varying parameters. The capabilities of the real-time RHEC framework are verified experimentally, and the results show an accurate tracking performance on a bumpy and wet soil field. The mean values of the Euclidean error and required computation time of the RHEC framework are respectively equal to $0.0423$ m and $0.88$ milliseconds.
... Optimal control software packages that implement directcollocation methods are used in a number of off-line [1], [2], [3], [4], [5], [6] and on-line [7], [8] applications as summarized in Table I. The primary function of these packages is to directly transcribe a human modeler's formulation of an optimal control problem (OCP) into a nonlinear programming problem (NLP). ...
... As seen in Table I, GPOCS, GPOPS-ii, and custom MATLAB software are not fast enough for NMPC applications in aircraft [18], robot [17], and UGV [19], [20] systems, respectively. On the other hand, CasADi, which is written in C++, is fast enough for an NMPC application in a robot system [7]. Given this practical limitation, this paper will now discuss why some direct-collocation-based optimal control packages are fast while others are slow. ...
Current direct-collocation-based optimal control software is either easy to use or fast, but not both. This is a major limitation for users that are trying to formulate complex optimal control problems (OCPs) for use in on-line applications. This paper introduces NLOptControl, an open-source modeling language that allows users to both easily formulate and quickly solve nonlinear OCPs using direct-collocation methods. To achieve these attributes, NLOptControl (1) is written in an efficient, dynamically-typed computing language called Julia, (2) extends an optimization modeling language called JuMP to provide a natural algebraic syntax for modeling nonlinear OCPs; and (3) uses reverse automatic differentiation with the acrylic-coloring method to exploit sparsity in the Hessian matrix. This work explores the novel design features of NLOptControl and compares its syntax and speed to those of PROPT. The syntax comparisons shows that NLOptControl models OCPs more concisely than PROPT. The speeds of various collocation methods within PROPT and NLOptControl are benchmarked over a range of collocation points using performance profiles; overall, NLOptControl's single, two, and four interval pseudospectral methods are roughly $14$, $26$, and $36$ times faster than PROPT's, respectively. NLOptControl is well-suited to improve existing off-line and on-line control systems and to engender new ones.
... Because of that, some researchers have proposed dynamic controllers that generate linear and angular velocities as commands [15,16]. In some works, the dynamic model is divided in to two parts, allowing the design of independent controllers for the robot kinematics and dynamics [17][18][19][20]. Finally, to reduce performance degradation in applications in which the robot dynamic parameters may vary (such as load transportation) or when the knowledge of the dynamic parameters is imprecise, adaptive controllers can also be considered [7,21]. ...
... To sum up, by using a control structure as shown in Figure 2 with a dynamic compensation controller given by Eq. (25), different motion controllers can be applied. In our example, the trajectory tracking controller given by Eq. (20) was used. This is the system that we have implemented and for which we present some experimental results in Section 5. ...
... We have implemented the control structure shown on Figure 2 using the control laws given by Eqs. (20) and (25). In total, we have executed 10 experiments for each controller, from now on referred to as KC (kinematics controller) and DC (dynamic compensation). ...
The design of motion controllers for wheeled mobile robots is often based only on the robot's kinematics. However, to reduce tracking error it is important to also consider the robot dynamics, especially when high-speed movements and/or heavy load transportation are required. Commercial mobile robots usually have internal controllers that accept velocity commands, but the control signals generated by most dynamic controllers in the literature are torques or voltages. In this chapter, we present a velocity-based dynamic model for differential-drive mobile robots that also includes the dynamics of the robot actuators. Such model can be used to design controllers that generate velocity commands, while compensating for the robot dynamics. We present an explanation on how to obtain the parameters of the dynamic model and show that motion controllers designed for the robot's kinematics can be easily integrated with the velocity-based dynamic compensation controller. We conclude the chapter with experimental results of a trajectory tracking controller that show a reduction of up to 50% in tracking error index IAE due to the application of the dynamic compensation controller.
... We have previously presented a non-linear model predictive control algorithm for row following Utstumo et al. (2015). The purpose of the controller is to prevent the rear castor wheel from damaging the crop, by limiting the steering control input. ...
Vegetables and other row-crops represent a large share of the agricultural production. There is a large variation in crop species, and a limited availability in specialized herbicides. The robot presented here utilizes systematic growing techniques to navigate and operate in the field. By the use of machine vision it separates seeded vegetable crops from weed. Each weed within the row is treated with individual herbicide droplets, without affecting the crop. This results in a significant reduction in herbicide use, and allows for the use of herbicides that would otherwise harm the crop.
The robot is tailored to this purpose with cost, maintainability, efficient operation and robustness in mind. The three-wheeled design is unconventional, and the design maintains maneuverability and stability with the benefit of reduced weight, complexity and cost.
Indoor pot trials with four weed species demonstrated that the Drop-on-Demand system (DoD) could control the weeds with as little as 7.6 μg glyphosate or 0.15 μg iodosulfuron per plant. The results also highlight the importance of liquid characteristics for droplet stability and leaf retention properties. The common herbicide glyphosate had no effect unless mixed with suitable additives. A field trial with the robot was performed in a carrot field, and all the weeds were effectively controlled with the DoD system applying 5.3 μg of glyphosate per droplet. The robot and DoD system represent a paradigm shift to the environmental impact and health risks of weed control, while providing a valuable tool to the producers.
... In robotics research, applications include control of agricultural robots [124], remote sensing of icebergs with UAVs [7,68], time-optimal control of robots [132], motion templates for robot-human interaction [133], motion planning of robotic systems with contacts [49,98], and multi-objective control of complex robots [84]. ...
We present CasADi, an open-source software framework for numerical optimization. CasADi is a general-purpose tool that can be used to model and solve optimization problems with a large degree of flexibility, larger than what is associated with popular algebraic modeling languages such as AMPL, GAMS, JuMP or Pyomo. Of special interest are problems constrained by differential equations, i.e. optimal control problems. CasADi is written in self-contained C++, but is most conveniently used via full-featured interfaces to Python, MATLAB or Octave. Since its inception in late 2009, it has been used successfully for academic teaching as well as in applications from multiple fields, including process control, robotics and aerospace. This article gives an up-to-date and accessible introduction to the CasADi framework, which has undergone numerous design improvements over the last 7 years.
... To achieve highly accurate tracking performance for constrained navigation in row crops, nonlinear RHC approaches have been widely used, particularly in agricultural applications as they are capable of taking constraints on states and inputs into account and can be designed for nonlinear models [Backman et al., 2012, Utstumo et al., 2015, Kayacan et al., 2018. Additionally, an accurate online estimation of traction parameters in a system model is crucial as the tiresoil interactions change throughout operations in varying, slippery conditions. ...
Accurate steering through crop rows that avoids crop damage is one of the most important tasks for agricultural robots utilized in various field operations, such as monitoring, mechanical weeding, or spraying. In practice, varying soil conditions can result in off‐track navigation due to unknown traction coefficients so that it can cause crop damage. To address this problem, this paper presents the development, application, and experimental results of a real‐time receding horizon estimation and control (RHEC) framework applied to a fully autonomous mobile robotic platform to increase its steering accuracy. Recent advances in cheap and fast microprocessors, as well as advances in solution methods for nonlinear optimization problems, have made nonlinear receding horizon control (RHC) and receding horizon estimation (RHE) methods suitable for field robots that require high‐frequency (milliseconds) updates. A real‐time RHEC framework is developed and applied to a fully autonomous mobile robotic platform designed by the authors for in‐field phenotyping applications in sorghum fields. Nonlinear RHE is used to estimate constrained states and parameters, and nonlinear RHC is designed based on an adaptive system model that contains time‐varying parameters. The capabilities of the real‐time RHEC framework are verified experimentally, and the results show an accurate tracking performance on a bumpy and wet soil field. The mean values of the Euclidean error and required computation time of the RHEC framework are equal to 0.0423 m and 0.88 ms, respectively.
... The adaptive NN acts as a compensator for a controller to improve system performance when it is affected by variations in its structure. Finally, [31] deals with the Nonlinear Model Predictive Control of an agricultural robot to precisely follow a trajectory operating in row cultures in order to perform high precision drop-on-demand application of herbicide. ...
An important issue in the field of motion control of wheeled mobile robots is that the design of most controllers is based only on the robot’s kinematics. However, when high-speed movements and/or heavy load transportation are required, it becomes essential to consider the robot dynamics as well. The control signals generated by most dynamic controllers reported in the literature are torques or voltages for the robot motors, while commercial robots usually accept velocity commands. In this context, we present a velocity-based dynamic model for differential drive mobile robots that also includes the dynamics of the robot actuators. Such model has linear and angular velocities as inputs and has been included in Peter Corke’s Robotics Toolbox for MATLAB, therefore it can be easily integrated into simulation systems that have been built for the unicycle kinematics. We demonstrate that the proposed dynamic model has useful mathematical properties. We also present an application of such model on the design of an adaptive dynamic controller and the stability analysis of the complete system, while applying the proposed model properties. Finally, we show some simulation and experimental results and discuss the advantages and limitations of the proposed model.
... An agricultural robot for high precision drop-ondemand herbicide application for row crops is under development. The robot uses a downward facing camera to identify weeds and a nozzle array applies the herbicide as the robot passes over them, (Urdal et al., 2014;Utstumo and Gravdahl, 2013;Utstumo et al., 2015). ...
Visual Odometry (VO) is increasingly a useful tool for robotic navigation in a variety of applications, including weed removal for agricultural robotics. The methods of evaluating VO are often computationally expensive and can cause the VO measurements to be significantly delayed with respect to a compass, wheel odometry, and GPS measurements. In this paper we present a Bayesian formulation of fusing delayed displacement measurements. We implement solutions to this problem based on the unscented Kalman filter (UKF), leading to what we term an unscented multi-point smoother. The proposed methods are tested in simulations of an agricultural robot. The simulations show improvements in the localization RMS error when including the VO measurements with a variety of latencies.
