TY - JOUR
T1 - Evolutionary Greenhouse Layout Optimization for Rapid and Safe Robot Navigation
AU - Uyeh, Daniel Dooyum
AU - Ramlan, Fitria Wulandari
AU - Mallipeddi, Rammohan
AU - Park, Tusan
AU - Woo, Seungmin
AU - Kim, Junhee
AU - Kim, Yeongsu
AU - Ha, Yushin
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2019
Y1 - 2019
N2 - There has been a rapid increase in demand for premium and safe agricultural products. Protected systems, such as greenhouses, are being adopted to meet demand. Ease in environmental regulation required for optimal plant growth is one of the advantages of protected systems. However, drawbacks such as poor ventilation in greenhouses can be fatal to the human workforce. This has led to the development of robots for hazardous tasks. Considering mobile robots are required to navigate down every aisle to perform a task in a greenhouse, and it is difficult to predict at which point the robot will need to return to the start point, to offload or refill for transportation and spraying schedules, respectively or battery charges. It will be commercially constraining to manufacture robots for every greenhouse specification. Efficient navigation can be done through path planning or layout design. In this paper, the greenhouse layout optimization problem was formulated to find optimal points on each bed to create an access path that would enable a reduction in the total travel time from all points in the greenhouse to the base point. The optimization problem was solved using differential evolution (DE), an evolutionary algorithm. Furthermore, we considered: 1) required space for inter-bed and rotary robot navigation; 2) standard bed specification; 3) area of the greenhouse; and 4) base point for starting and terminating navigation. The applicability of the proposed method was demonstrated by carrying out the experimental simulations on several greenhouse sizes.
AB - There has been a rapid increase in demand for premium and safe agricultural products. Protected systems, such as greenhouses, are being adopted to meet demand. Ease in environmental regulation required for optimal plant growth is one of the advantages of protected systems. However, drawbacks such as poor ventilation in greenhouses can be fatal to the human workforce. This has led to the development of robots for hazardous tasks. Considering mobile robots are required to navigate down every aisle to perform a task in a greenhouse, and it is difficult to predict at which point the robot will need to return to the start point, to offload or refill for transportation and spraying schedules, respectively or battery charges. It will be commercially constraining to manufacture robots for every greenhouse specification. Efficient navigation can be done through path planning or layout design. In this paper, the greenhouse layout optimization problem was formulated to find optimal points on each bed to create an access path that would enable a reduction in the total travel time from all points in the greenhouse to the base point. The optimization problem was solved using differential evolution (DE), an evolutionary algorithm. Furthermore, we considered: 1) required space for inter-bed and rotary robot navigation; 2) standard bed specification; 3) area of the greenhouse; and 4) base point for starting and terminating navigation. The applicability of the proposed method was demonstrated by carrying out the experimental simulations on several greenhouse sizes.
KW - Differential evolution
KW - greenhouse
KW - layout optimization
KW - rapid and safe navigation
KW - robots
UR - http://www.scopus.com/inward/record.url?scp=85069780433&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2019.2926566
DO - 10.1109/ACCESS.2019.2926566
M3 - Article
AN - SCOPUS:85069780433
SN - 2169-3536
VL - 7
SP - 88472
EP - 88480
JO - IEEE Access
JF - IEEE Access
M1 - 8754747
ER -