Towards the Development and Verification of a 3D-Based Advanced Optimized Farm Machinery Trajectory Algorithm

Efforts related to minimizing the environmental burden caused by agricultural activities and increasing economic efficiency are key contemporary drivers in the precision agriculture domain. Controlled Traffic Farming (CTF) techniques are being applied against soil compaction creation, using the on-line optimization of trajectory planning for soil-sensitive field operations. The research presented in this paper aims at a proof-of-concept solution with respect to optimizing farm machinery trajectories in order to minimize the environmental burden and increase economic efficiency. As such, it further advances existing CTF solutions by including (1) efficient plot divisions in 3D, (2) the optimization of entry and exit points of both plot and plot segments, (3) the employment of more machines in parallel and (4) obstacles in a farm machinery trajectory. The developed algorithm is expressed in terms of unified modeling language (UML) activity diagrams as well as pseudo-code. Results were visualized in 2D and 3D to demonstrate terrain impact. Verifications were conducted at a fully operational commercial farm (Rostěnice, the Czech Republic) against second-by-second sensor measurements of real farm machinery trajectories.

[1]  Lukáš Herman,et al.  Deployment and Verifications of the Spatial Filtering of Data Measured by Field Harvesters and Methods of Their Interpolation: Czech Cereal Fields between 2014 and 2018 , 2019, Sensors.

[2]  Mohammad Biglarbegian,et al.  Path planning for data collectors in Precision Agriculture WSNs , 2014, 2014 International Wireless Communications and Mobile Computing Conference (IWCMC).

[3]  Lukáš Herman,et al.  MONITORING OF IN-FIELD VARIABILITY FOR SITE SPECIFIC CROP MANAGEMENT THROUGH OPEN GEOSPATIAL INFORMATION , 2016 .

[4]  M. Kroulík,et al.  The influence of agricultural traffic on soil infiltration rates , 2017 .

[5]  Valery Dimitrov,et al.  The problem of choice of optimal technological decisions on harvester control , 2018 .

[6]  Tomás Rezník,et al.  Machine Learning-Based Processing Proof-of-Concept Pipeline for Semi-Automatic Sentinel-2 Imagery Download, Cloudiness Filtering, Classifications, and Updates of Open Land Use/Land Cover Datasets , 2021, ISPRS Int. J. Geo Inf..

[7]  Alberto Bemporad,et al.  Shortest path computations under trajectory constraints for ground vehicles within agricultural fields , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[8]  Lukás Herman,et al.  Interpolation of Data Measured by Field Harvesters: Deployment, Comparison and Verification , 2020, ISESS.

[9]  W. Royce.  Managing the development of large software systems: concepts and techniques , 2021, ICSE '87.

[10]  Thomas S. Colvin,et al.  Grain Yield Mapping: Yield Sensing, Yield Reconstruction, and Errors , 2002, Precision Agriculture.

[11]  Efthymios Rodias,et al.  Energy Savings from Optimised In-Field Route Planning for Agricultural Machinery , 2017 .

[12]  I. A. Hameed,et al.  Intelligent Coverage Path Planning for Agricultural Robots and Autonomous Machines on Three-Dimensional Terrain , 2014, J. Intell. Robotic Syst..

[13]  Lie Tang,et al.  Headland turning optimisation for agricultural vehicles and those with towed implements , 2019 .

[14]  Jian Jin,et al.  Optimal Coverage Path Planning for Arable Farming on 2D Surfaces , 2010 .

[15]  Arto Visala,et al.  Coverage path planning algorithms for agricultural field machines , 2009 .

[16]  B. Šarapatka,et al.  The role of traditional agricultural landscape structures in changes to green infrastructure connectivity , 2020 .

[17]  Francesco Borrelli,et al.  Predictive control for agile semi-autonomous ground vehicles using motion primitives , 2012, 2012 American Control Conference (ACC).

[18]  W. Anderson,et al.  Soil compaction in cropping systems: A review of the nature, causes and possible solutions , 2005 .

[19]  Claus G. Sørensen,et al.  An Optimized Field Coverage Planning Approach for Navigation of Agricultural Robots in Fields Involving Obstacle Areas , 2013 .

[20]  Jian Jin,et al.  Coverage path planning on three‐dimensional terrain for arable farming , 2011, J. Field Robotics.

[21]  Karel Jedlicka,et al.  Advanced Visualisation of Big Data for Agriculture as Part of Databio Development , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[22]  Arto Visala,et al.  Coverage path planning algorithms for agricultural field machines , 2009, J. Field Robotics.

[23]  Yangzhou Chen,et al.  Path planning based on Constrained Delaunay Triangulation , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[24]  Per Olof Gutman,et al.  Inter-field routes scheduling and rescheduling for an autonomous tractor fleet at the farm , 2013, 2013 18th International Conference on Methods & Models in Automation & Robotics (MMAR).

[25]  Dionysis Bochtis,et al.  A Case-Based Economic Assessment of Robotics Employment in Precision Arable Farming , 2019, Agronomy.

[26]  M. Kroulík,et al.  Field trajectories proposals as a tool for increasing work efficiency and sustainable land management , 2018 .

[27]  Noboru Noguchi,et al.  Path planning of an agricultural mobile robot by neural network and genetic algorithm , 1997 .

[28]  Theresa Marie Driscoll.  Complete coverage path planning in an agricultural environment , 2011 .

[29]  Jiří Pospíšil,et al.  Influence of the Combine Harvester Parameter Settings on Harvest Losses , 2018 .

[30]  Einar Eberhardt,et al.  Best Practice Network GS SOIL Promoting Access to European, Interoperable and INSPIRE Compliant Soil Information , 2011 .

[31]  Alberto Bemporad,et al.  Reference trajectory planning under constraints and path tracking using linear time-varying model predictive control for agricultural machines , 2017 .