Specification development of robotic system for pesticide spraying in greenhouse

Robotic systems are replacing humans in increasing number of dangerous tasks. Pesticide spraying in greenhouses is one of tasks where a number of robotic systems have been developed and tested. Therefore it is the right time to raise the question about optimisation of the costs efficiency of robot colony. In case of homogenous robotic system only the number of universal robots has to be determined. The drawback is that some subsystems (vision, spraying) might be utilised at a very low rate and the investment may be inefficient. To avoid that it is possible to design a heterogeneous robotic system where the solution space of a robotic system specification is large and optimisation task becomes very complex. Still a good solution can reduce costs. Optimisation of specification of heterogeneous robotic system for pesticide spraying (plant inspection, spraying and pesticide transport functions) in a greenhouse with rectangular layout is performed using genetic algorithms and corresponding open source GAMBot-Eva software. Optimisation results demonstrate three groups of solutions that are within 3% range of lowest possible costs: 1) homogeneous system of universal robots, 2) heterogeneous system with two types of robots (inspection-spraying robots and spraying-transportation robots) and 3) heterogeneous system with two types of robots without duplicating functions (inspection-spraying robots and transportation robots). Applied optimisation approach can be adapted for different robot missions.