Figure 1 - uploaded by Ibrahim A. Hameed
Content may be subject to copyright.
Source publication
The objective of this article was to develop an initial approach for a method to combine two recently developed methods related to the field area coverage problem. The first stage generated a field geometrical representation and the second stage aimed to optimize the routing of agricultural vehicles within this geometrically defined world. In the f...
Contexts in source publication
Context 1
... the sequence of these blocks is optimized in terms of minimized travelling distance. A flowchart of the proposed approach is shown in figure 1. ...
Context 2
... order to show the impact of the driving angle on the operational parameters, the resulting parameters from the first stage (i.e., driving angle optimization stage) of the algorithm are given in table 2 (columns 2-6) for the selected driving angles of 0°, 45°, 90°, and 135° (using as reference direction the x-axis, fig. 10). Since these results are derived from the first stage of the algorithm they regard the conventional AB fieldwork pattern. The last row of table 1 gives the operational parameters for the optimized driving angle (with the minimized overlapped area) as it results from the first stage of the algorithm ( fig. ...
Context 3
... as reference direction the x-axis, fig. 10). Since these results are derived from the first stage of the algorithm they regard the conventional AB fieldwork pattern. The last row of table 1 gives the operational parameters for the optimized driving angle (with the minimized overlapped area) as it results from the first stage of the algorithm ( fig. ...
Context 4
... B-patterns sequence within each block is given in table 3. The optimized sequence of the blocks is 1-2-3-4. The course of the total operation is schematically shown in figure 12. 3. The produced optimized sequence of tracks within the four blocks. ...
Context 5
... resulting parameters from the first-stage (i.e., driving angle optimization stage) of the algorithm are given in table 4 (columns 2-6) for the selected driving angles of 0°, 45°, 90°, and 135° ( fig. 13). The last row of table 3 gives the operational parameters for the optimized driving angle ( fig. ...
Context 6
... resulting parameters from the first-stage (i.e., driving angle optimization stage) of the algorithm are given in table 4 (columns 2-6) for the selected driving angles of 0°, 45°, 90°, and 135° ( fig. 13). The last row of table 3 gives the operational parameters for the optimized driving angle ( fig. ...
Context 7
... the sequence of these blocks is optimized in terms of minimized travelling distance. A flowchart of the proposed approach is shown in figure 1. ...
Context 8
... order to show the impact of the driving angle on the operational parameters, the resulting parameters from the first stage (i.e., driving angle optimization stage) of the algorithm are given in table 2 (columns 2-6) for the selected driving angles of 0°, 45°, 90°, and 135° (using as reference direction the x-axis, fig. 10). Since these results are derived from the first stage of the algorithm they regard the conventional AB fieldwork pattern. The last row of table 1 gives the operational parameters for the optimized driving angle (with the minimized overlapped area) as it results from the first stage of the algorithm ( fig. ...
Context 9
... as reference direction the x-axis, fig. 10). Since these results are derived from the first stage of the algorithm they regard the conventional AB fieldwork pattern. The last row of table 1 gives the operational parameters for the optimized driving angle (with the minimized overlapped area) as it results from the first stage of the algorithm ( fig. ...
Context 10
... B-patterns sequence within each block is given in table 3. The optimized sequence of the blocks is 1-2-3-4. The course of the total operation is schematically shown in figure 12. 3. The produced optimized sequence of tracks within the four blocks. ...
Context 11
... resulting parameters from the first-stage (i.e., driving angle optimization stage) of the algorithm are given in table 4 (columns 2-6) for the selected driving angles of 0°, 45°, 90°, and 135° ( fig. 13). The last row of table 3 gives the operational parameters for the optimized driving angle ( fig. ...
Context 12
... resulting parameters from the first-stage (i.e., driving angle optimization stage) of the algorithm are given in table 4 (columns 2-6) for the selected driving angles of 0°, 45°, 90°, and 135° ( fig. 13). The last row of table 3 gives the operational parameters for the optimized driving angle ( fig. ...
Citations
... In this paper, however, we will adopt a sequential track traversing order for simplicity and ease of implementation. Notably, research in the literature demonstrates that the traversing order of tracks within a cell can indeed be optimized for improved efficiency and coverage [16,[36][37][38]. ...
Complete coverage path planning (CCPP) is vital in mobile robot applications. Optimizing CCPP is particularly significant in precision agriculture, where it enhances resource utilization, reduces soil compaction, and boosts crop yields. This work offers a comprehensive approach to CCPP for agricultural vehicles with curvature constraints. Our methodology comprises four key stages. First, it decomposes complex agricultural areas into simpler cells, each equipped with guidance tracks, forming a fixed track system. The subsequent route planning and smooth path planning stages compute a path that adheres to path constraints, optimally traverses the cells, and aligns with the track system. We use the generalized traveling salesman problem (GTSP) to determine the optimal traversing sequence. Additionally, we introduce an algorithm for calculating paths that are both smooth and curvature-constrained within individual cells, as well as paths that enable seamless transitions between cells, resulting in a smooth, curvature-constraint coverage path. Our modular approach allows method flexibility at each step. We evaluate our method on real agricultural fields, demonstrating its effectiveness in minimizing path length, ensuring efficient coverage, and adhering to curvature constraints. This work establishes a strong foundation for precise and efficient agricultural coverage path planning, with potential for further real-world applications and enhancements.
... The core idea of evolutionary algorithm [20] is to simulate the evolutionary change process of biological groups in nature through computer programs to solve complex function optimization problems. With the great success of swarm intelligence evolutionary algorithms in sensor placement [21][22][23], trajectory planning [24][25][26], economic forecasting [27,28], and meteorological forecasting [29,30], especially for the widespread application in the field of A C C E P T E D M A N U S C R I P T Accepted manuscript to appear in FRACTALS 4 machine learning [31][32][33][34], evolutionary algorithms make more and more scholars invest in the study of evolutionary algorithms for swarm intelligence. ...
With the deepening of hospital informatization construction, the electronic health record (EHR) system has been widely used in the clinical diagnosis and treatment process, resulting in a large amount of medical data. Electronic medical records contain a large amount of rich medical information, which is an important resource for disease prediction, personalized information recommendation, and drug mining. However, the medical information contained in electronic medical records cannot be automatically acquired, analyzed and utilized by computers. In this paper, we utilize machine learning algorithms for intelligent analysis of large-scale electronic medical records to explore and develop general methods and tools suitable for electronic medical record analysis in medical databases. This is of great value for summarizing the therapeutic effects of various diagnosis and treatment programs, disease diagnosis, treatment, and medical research. We propose an ECML-based intelligent analysis method for electronic medical records. First, we perform data preprocessing on the electronic medical record. Second, we design an intelligent analysis method for electronic medical records based on a deep learning model. Third, we design a model hyperparameter optimization method based on evolutionary algorithms. Finally, we compare and analyze the performance of the proposed model through experiments, and the experimental results show that the model proposed in this paper has good performance.
... A similar approach to Section 5.2, but with a different motivation, is taken in [35]. Here, it is not the path length that is to be minimized, but overlapping areas, i.e. areas that have been traversed several times. ...
The Complete Coverage Path Planning (CCPP) problem is a sub-field of industrial motion planning that has applications in various domains, ranging from mobile robotics to treatment applications. Especially in precision agriculture with a high level of automation, the use of CCPP techniques is essential for efficient resource utilization, reduced soil compaction, and increased yields. This paper reviews the CCPP problem in the context of machines operating in agricultural fields and proposes a methodological approach consisting of three steps: Generating the Guidance Tracks (i.e. the track system along which the path should be oriented), determining the traversing sequence through these tracks, and planning a smooth and drivable path. This paper provides an in-depth review of optimization-based approaches that deal with the first step, the generation of the guidance track system. Thereby, a comprehensive and pedagogical approach for generation of guidance tracks for arbitrarily-shaped two-dimensional regions of interest is provided, along with an overview and detailed elaboration on different exact cellular decomposition techniques found in literature. Furthermore, cost functions are outlined for the different approaches presented in this work, which are utilized to generate optimal guidance tracks.
... Bechar et al. [5] classify agriculture into the most complex category for robotic applications, which is justified by the spatial and temporal variability of the environment and the objects. The spectrum of AI applications ranges from intelligent individual and collective robotics scenarios in the field [5], through the optimization of irrigation systems [9] and soil sampling patterns [11] or lane planning [2], to the non-destructive recording and monitoring of process and phenological parameters in outdoor agriculture [24]. The use of AI in agriculture relies on the availability of data to train the models. ...
Content Tractor Drive Trains An Analysis of Mixed Hydraulic and Electric Configurations for the Actuation of Tractor Auxiliary and Implement Functions to Reduce Power Consumption 1 The development of a reference working cycles for agricultural tractors 15 Performance optimization of CVT standard tractors in front loading application 21 Numerical simulation of alternative powertrains and fuels in agricultural tractors 29 Fuel Cells A Fuel Cell Tractor in Operation – Concepts and Field Data 39 Fuel cell electric powertrain for the agricultural tractor – FCTRAC: development, performance, and benchmarking 49 Fuel cell electric tractor powered with biogenic hydrogen – Vehicle design and architecture 57 “GrindStar“ – More efficiency, effectiveness, and economy with ultrashallow soil cultivation 63 High Accuracy and High-Speed Crop Root Position Detection for Green-on-Green Mechanical Weeding 69 A comparison between conventional calibration experiments and the Excavator Test for DEM soil calibration 79 Technological and energetic aspects of a transverse pull 87 Sensors and Detection Classifying tractor o...
... One common CPP approach is to generate trajectories parallel to the longest edge of the field, with a spacing equal to the working width, or to simply take a direction as input (Cariou et al., 2017;Hameed, 2017;Hameed et al., 2011;Jeon et al., 2021;Nilsson & Zhou, 2020;Zhou & Bochtis, 2015;Zuo et al., 2010). Extending this approach, Hameed et al. (2010), Jensen et al. (2012), Plessen (2021 proposed to generate parallel trajectories along a curved reference line as well. ...
In the agricultural industry, an evolutionary effort has been made over the last two decades to achieve precise autonomous systems to perform typical in-field tasks including harvesting, mowing, and spraying. One of the main objectives of an autonomous system in agriculture is to improve the efficiency while reducing the environmental impact and cost. Due to the nature of these operations, complete coverage path planning approaches play an essential role to find an optimal path which covers the entire field while taking into account land topography, operation requirements and robot characteristics. The aim of this paper is to propose a complete coverage path planning approach defining the optimal movements of mobile robots over an agricultural field. First, a method based on tree exploration is proposed to find all potential solutions satisfying some predefined constraints. Second, a Similarity check and selection of optimal solutions method is proposed to eliminate similar solutions and find the best solutions. The optimization goals are to maximize the coverage area and to minimize overlaps, non-working path length and overall travel time. In order to explore a wide range of possible solutions, our approach is able to consider multiple entrances for the robot. For fields with a complex shape, different dividing lines to split it into simple polygons are also considered. Our approach also computes the headland zones and covers them automatically which leads to a high coverage rate of the field.
... Jin and Tang (2010) proposed a geometric representation method with similar properties to the potential field, and combined this method with a path planning algorithm to solve the optimal coverage path by decomposing the farmland into sub-regions and separately determining the direction of farm machinery operations within the sub-regions, and establishing a geometric model of the farmland. Hameed et al. (2011) calculated the optimal operating travel direction of farm machinery based on the geometry of farmland to optimize the operating path of farm machinery. Bakhtiari et al. (2013) proposed the use of an ant colony optimization method to generate a combine harvester field mulching scheme with a non-working distance saving of about 18% to 43% compared to the conventional scheme. ...
The stubble crushing caused by the harvester during the first season of ratoon rice harvesting will directly affect the grain yield of the ratoon season. In this work, a harvester path planning method for quadrilateral fields to address the harvester driving path problem of the first season of ratoon rice mechanized harvesting is proposed. This research first analyzes the operational characteristics and requirements of ratoon rice first-season mechanized harvesting, and then models the mechanized harvesting process of ratoon rice in the first season as a capacitated arc routing problem (CARP) considering the fact that the harvester cannot complete the full-coverage harvesting operation at one time due to the limitation of grain bin volume. The genetic algorithm (GA) with strong global search capability is used to solve it, and the selection and variation links of the algorithm are improved. The path planning method proposed in this article can dynamically find the optimal harvester travel route according to the specific conditions of the field and the parameters of harvester implements. The simulation test shows that the CARP method performs better in terms of harvesting path length and crushed area compared to the conventional rectangular detour and foldback reciprocating harvesting paths. The degree of optimization of this method is influenced by various factors such as the width of the cutting table, the turning radius of the harvester, and the size of the grain bin capacity. This research provides a more efficient and flexible path planning method to improve the efficiency of ratoon rice first-season mechanized harvesting operations and optimize the harvester’s operating path, which can well meet the operational requirements.
... To date, most research on ARP has considered only single-field configurations Conesa-Muñoz et al., 2016;Seyyedhasani and Dvorak, 2018a). Most of the ARP research also utilized a single machine without a capacity constraint (Hameed et al., 2011;Edwards et al., 2017). Therefore, ARP with multiple fields and capacitated machines is still a potential research area. ...
... Many of the recent ARP studies focus on a single field. Seyyedhasani and Dvorak (2017), Conesa-Muñoz et al. (2016), Zhou et al. (2014), Bakhtiari et al. (2013), Valente et al. (2013) and Hameed et al. (2011) consider both rectangular and non-convex fields. The rectangular field is the primary type that most researchers use in ARP. ...
... GA has been adapted for machine routing to decrease the total distance traveled in biomass transportation (Gracia et al., 2014). GA was also used for track sequence optimization in a field, and its solutions have proven to be more efficient compared to the conventional fieldwork patterns (Hameed et al., 2011). Recently, GA has been used in optimizing the scheduling of crop cultivation (Aliano Filho et al., 2019). ...
In recent years, operations research in agriculture has improved the harvested yield, reduced the cost and time required for field operations, and maintained economic and environmental sustainability. The heuristics method, named Evolutionary neighborhood discovery algorithm (ENDA), is applied to minimize the inter-field and intra-field distance of the routing planning of machines in multiple agricultural fields. The problem is an extended version of the Agricultural Routing Planning (ARP) that takes into consideration the different capacity of the machines and multiple agricultural fields. This research also describes the mathematical model to represent the proposed problem formulated as an integer program. The experimental results show that ENDA successfully solves ARP instances, giving the best results and the fastest running time compared to those obtained by Genetic Algorithms and Tabu Search. The results also show that ENDA can save an average of 11.72% of the distance traveled by the machines outside the working path (when making maneuvers, going to or from the entrances and going from and returning to the Depot).
... The offline strategies are using a priori known map of the area, where the robot must perform the given task. Different approaches are used for offline coverage path planning, such as: genetic algorithms [10], cellular decomposition-based methods [11] and neural networks [12]. In the online strategies the robot must discover in real time the area using different sensors, such as sonars or tactile sensors [13]. ...
This research considers the design of a sensor system for walking robot which can be used for coverage path planning and precise surface exploration. The paper presents an updated mechanical design of a minimalistic walking robot with a fixed step size. The robot has only two degrees of freedom. The specific mechanical design prevents the accumulation of any odometry error and does not require any external navigation system. The robot is equipped with a variety of distance and tactile sensors which allow precise exploration of the surface and any high or low spots of the surface to be located. This paper proposes an approach for path planning and surface exploration by using the proposed sensor system. Despite that the robot is based on a minimalistic approach, it can move and operate on complex surfaces. Also, by altering its movement direction it can effectively use its sensor system for distant global object scanning or for local exploration of the walking surface. The conducted experiment showed that the presented in this research mechanical design of a walking robot with fixed step can be used for precise surface exploration.
... This problem is computationally difficult to solve in terms of obtaining optimality for fields of a realistic size and has led to many researchers investigating the efficiency and focusing on improving algorithms for various path generation methods [7][8][9]. For instance, [10] investigated the CPP problem in capacitated field operations and compared the calculated plans to real fertilizing applications. ...
... There are many benchmarking functions and datasets which are used for testing and evaluating the optimization algorithms [22][23][24][25]. In the lack of a common benchmarking standard, researchers have applied different agricultural fields to show the performance of their algorithm [7,10,[26][27][28]. Obviously, algorithms can only be compared if they have been tested under similar conditions, notably on a common benchmarking field. ...
... , N. A track can be referred to either by its number, i, or by its endpoints, [2i − 1, 2i]. For a field with 8 tracks, a solution could be noted as a sequence of all 16 track endpoints, e.g., [0,8,7,11,12,6,5,1,2,4,3,9,10,16,15,13,14,0], where 0 is a common starting and ending point of the route. In this solution, the first track to visit is number 4 in the direction from endpoint 8 to 7, then track 6 in the direction from endpoint 11 to 12, and so forth. ...
This study specifies an agricultural field (Latitude = 56 • 30 0.8" N, Longitude = 9 • 35 27.88" E) and provides the absolute optimal route for covering that field. The calculated absolute optimal solution for this field can be used as the basis for benchmarking of metaheuristic algorithms used for finding the most efficient route in the field. The problem of finding the most efficient route that covers a field can be formulated as a Traveling Salesman Problem (TSP), which is an NP-hard problem. This means that the optimal solution is infeasible to calculate, except for very small fields. Therefore, a range of metaheuristic methods has been developed that provide a near-optimal solution to a TSP in a "reasonable" time. The main challenge with metaheuristic methods is that the quality of the solutions can normally not be compared to the absolute optimal solution since this "ground truth" value is unknown. Even though the selected benchmarking field requires only eight tracks, the solution space consists of more than 1.3 billion solutions. In this study, the absolute optimal solution for the capacitated coverage path planning problem was determined by calculating the non-working distance of the entire solution space and determining the solution with the shortest non-working distance. This was done for four scenarios consisting of low/high bin capacity and short/long distance between field and storage depot. For each scenario, the absolute optimal solution and its associated cost value (minimum non-working distance) were compared to the solutions of two metaheuristic algorithms; Simulated Annealing Algorithm (SAA) and Ant Colony Optimization (ACO). The benchmarking showed that neither algorithm could find the optimal solution for all scenarios, but they found near-optimal solutions, with only up to 6 pct increasing non-working distance. SAA performed better than ACO, concerning quality, stability, and execution time.
... Jensen et al. [9] studied the cooperative operation mode of transport units and harvesting units in the process of combined harvesting and studied the planning of internal field coverage path and the scheduling between different fields under this mode. Hameed [10][11][12] engaged in optimization research of CPP problems from the perspective of minimum overlap of operating area, minimum cost of nonworking path, and the presence of obstacles in the field, and developed specific and feasible planning algorithms. In addition, in terms of the details of the two-dimensional farmland CPP algorithm, Jin and Tang [8] and Meng et al. [13], respectively, analysed the cost of various headland turning methods and turning type decisions. ...
The hilly farmland in China is characterized by small farmland areas and dense farmland distribution, and the working environment is three-dimensional topographic farmland, so the working conditions in the field are relatively complex. In this working environment, the coverage path planning technique of a farmland autonomous task is harder than that of 2D farmland autonomous task. Generally, the path planning problem of 2D farmland is to construct the path cost model to realize the planning of agricultural machinery driving route, while for the path planning problem of three-dimensional terrain farmland in the hilly region, this paper proposes a covering path planning scheme that meets the requirements of autonomous work. Based on the energy consumption model, the scheme searches the optimal driving angle of agricultural machinery, prioritizes solutions to the problem of covering path planning within the scattered fields in the working area, and then searches through the genetic algorithm for the optimal order of traversing the paths of each field to complete the coverage path planning in the working area. On the one hand, the scheme optimizes the planning route in the fields from the angle of optimal energy consumption; on the other hand, through the genetic algorithm, the fields are connected in an orderly manner, which solves the comprehensive problems brought by the unique agricultural environment and farming system in China’s hilly areas to the agricultural machinery operation. The algorithm program is developed according to the research content, and a series of simulation experiments are carried out based on the program using actual farmland data and agricultural machinery parameters. The results show that the planned path obtained at the cost of energy consumption has a total energy consumption of 4771897.17J, which is 17.4% less energy consumption than the optimal path found by the path cost search; the optimization effect is evident.
