Evolutionary Greenhouse Layout Optimization for Rapid and Safe Robot Navigation

Abstract

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.

Developing a Modern Greenhouse Scientific Research Facility—A Case Study

“…Wu et al [41] proposed a sensor placement model to maximize target coverage without occlusion. As an alternative to fixed positioning, multiple papers propose mobile sensor placement in greenhouses [13,[42][43][44][45].…”

“…When using an autonomous sensor carrier vehicle, significant attention must be paid to layout optimization for rapid and safe navigation [45]. In paper [46], an obstacle detection system using Kinect sensor is proposed.…”

“…Besides horizontal and vertical positioning, there are also hybrid solutions such as shelves, boxes, tier-based and master-slave solutions. These solutions try to eliminate the microclimate effect by excluding it from the experiment (plants near the greenhouse walls are not included in the measurement results) or by measuring the microclimate effect in each position [13,[42][43][44][45]].…”

Optimization of the Biofuel Supply Chain With Capital-Constrained Farmers Under Government Subsidies

“…The quadratic input cost functions that capture the increasing marginal cost of input have been used in agricultural models [15], [18], [28]. Agricultural production is very susceptible to weather [40]- [42]. Therefore, we assume that the yield ε(ε ∈ (A,B)) is random with a continuous probability density function f (ε) and a cumulative distribution function F(ε) and that ε satisfies IFG.…”

A Decision Support Tool for the Optimal Monitoring of the Microclimate Environments of Connected Smart Greenhouses

“…Reference [33] presented and implemented a management system for a greenhouse considering humidity, CO2, soil moisture, and indoor temperature. A layout optimization system for rapid and safe robot navigation in a greenhouse is presented in [34]. Reference [35] proposed an automated system to control a greenhouse.…”