Path Planning for On-Farm Machinery in Rectangular Fields using Genetic Algorithm

ماشین های کشاورزی

Article 8, Volume 8, Issue 1 - Serial Number 15, 2018, Pages 93-104   

Document Type: Research Article

DOI: 10.22067/jam.v8i1.55463

Authors

T. Mesri Gundoshmian^* ; F. Keyhani Nasab; Gh. Shahgholi; E. Abdollahi

Biosystems Engineering Department, University of Mohaghegh Ardabili, Ardabil, Iran

Abstract

Introduction
Today, most of the agricultural machines for doing agricultural operations and covering the entire farm, must move in the farm, and travel a certain distance without doing anything useful. Common agricultural machines are controlled by human beings using habits, machinery models, and personal experiences without using computer-based tools. This trend leads to repetitive patterns and affect farm efficincy. Therefore, applying optimization techniques in determining the optimum pattern and track for on-farm machinery would be very effective.
One of the main problems of conventional movement patterns on farms is the time wasted on moving towards the end of the field, which will have a big impact on field efficiency. The purpose of this study is to reduce the useless distance traveled by agricultural machines using genetic algorithm while moving on the farm and going from one track to the next, and, consequently, increase farm efficiency.
Materials and Methods
In this study, the rectangle farm that was 80 meters wide and had an arbitrary length was selected for simulation, and different types of turning methods were tested. The calculations and simulation were based on genetic algorithm using the MATLAB 2013 software. In this case, the minimum traveled distance was set as solution evaluation criterion. The solutions were applied and simulated according to these assumptions: Each gene was considered a track number, and the algorithm’s chromosomes were produced by connecting all the tracks to each other,. The width of each track was considered equal to the width of the machine, and based on reproduction parameters such as population size and the number of repetitions, a percentage of the children were produced through point intersection and another percentage were produced through mutation. In determining the distance between the tracks, Ω or T or U were used for two adjacent tracks, U was used for two tracks that had a track between them, and a longer U was used for tracks that had more than one track between them.
Based on the number of the initial population, the chromosomes that were supposed to be parents at the beginning were selected. The children produced new population was created and the above steps were repeated. During the last repetition, the best child chromosome was introduced as the answer.
In order to calculate the effects of different methods of turning on the non-working distance covered during agricultural operations, the non-working distance traveled during 5 orders of movement, including 4 traditional orders (continuous, spiral, all-around, and blocked) and 1 smart order were compared to each other.
In the continuous pattern, because movement continues in the next track at the end of each track, all the turnings are inevitably done in the Ω way, and thus a greater distance is travelled compared to the U way. In the spiral pattern, the distance travelled in turnings between different tracks on the farm is equal. In the all-around pattern, movements are done from the sides and the operation is concluded at the center of the farm; therefore, the long U method of movement is used at the end of all the tracks, and Ω turning is used for the last track at the center of the farm. In the blocked pattern, the farm is devided into two or more blocks, and the all-around movement pattern is used in each block as an independent farm. In the smart movement pattern, the beginning and ending of the agricultural operations are considered in the vicinity of the hypothetical road which, in addition to facilitating access to the road, had a significant impact on reducing the useless distance traveled on the farm.

Results and Discussion
The final optimum pattern was compared to traditional patterns in the form of charts. The optimum pattern of movement which uses smart genetic algorithm and avoids long turning methods (such as, Ω and T) leads to reduced wasted time and distance traveled by agricultural machines and increased field efficiency and also, decreasing the non-working traveled distance and waste time approximately, 45 % and 47 % respectively. This is due to avoiding turning methods of Ω and T (compared to the U method). Also, the fatigue resulting from these approaches and their wasted time is greater than U method used in the genetic algorithm pattern.
Conclusion
The optimum pattern of movement which uses smart genetic algorithm was compared to conventional patterns that showed significant saving in non- working distance and waste time in farm. This optimum pattern can be implemented in automatic navigation but there is the possibility of its implementation by operators in common navigation.

Keywords

Field efficiency; Genetic algorithm; Pattern of traffic; Route planning

References

1. Bakhtiari, A. A., H. Navid, J. Mehri, and D. D. Bochtis. 2011. Optimal route planning of agricultural field operations using ant colony optimization. Agricultural Engineering International: CIGR Journal 13 (4), Manuscript No.1939.

2. Bochtis, D. D., and S. G. Vougioukas. 2008. Minimising the non-working distance travelled by machines operating in a headland field pattern. Biosystem Engineering 101 (1): 1-12.

3. Bochtis, D. D., S. G. Vougioukas, H. W. Griepentrog, and N. A. Anderson. 2008. Effect of capacity constrates on the motion pattern of an autonomous orchard sprayer. In proceeding of agricultural and biosystems engineering for a sustainable world, EuAgEng, Crete, Greece. 8pp.

4. Bochtis, D. D., S. G. Vougioukas, and H. W. Griepentrog. 2009. A mission planner for an autonomous tractor, Transactions of ASABE, 52 (5): 1429-1440.

5. Bryant, K. 2000. Genetic algorithm and the traveling salesman problem. Department of mathematics. Hervey Mudd college. Claremont, California, United States.

6. Choset, H., and P. Pignon. 1997. Coverage path planning: The Boustrophedon cellular decomposition. International conference on field and service robotics. Canberra, Australia.

7. Jin, J., and L. Tang. 2010. Optimal coverage path planning for arable farming on 2D surfaces. Transactions of the ASABE 53 (1): 283-295.

8. Keicher, R., and H. Seufert. 2000. Automatic guidance for agricultural vehicles in Europe. Computers and Electronics in Agriculture 25: 169-194.

9. Mazidi, M., M. H. Abbaspour-Fard, and M. H. Aghkhani. 2014. Checking the guidance possibility of unmanned tractor based on wireless transmission of video image. Journal of Agricultural Machinery 4 (2): 166-175. (In Farsi).

10. Mesri Gundoshmian, T. 2016. Mechanization of agricultural industries (Strategies and approaches in biosystem industries ). University of Mohaghegh Ardabili Press, Ardabil, Iran.

11. Moghimi, A., M. H. Aghkhani, M. R. Golzarian, A. Rouhani, and Ce. Yang. 2015. A robo-vision algorithm for automatic harvesting of green bell pepper. ASABE annual international meeting, New Orleans, Louisiana.

12. Ryerson, A. E., and Q. Zhang. 2006. Vehicle path planning for complete field coverage using genetic algorithms. In proceedings of the automation technology for off-road equipment (ATOE) 2006 conference, Bonn, Germany (pp. 309–317).

13. Sivanandam, S. N., ans S. N. Deepa. 2008. Introduction to Genetic Algorithm. Publisher: Springer-Verlag. Berlin Heidelberg, Germany.