Multi-objective pathfinding for autonomous robot in agriculture.

Abstract

This paper enhanced the autonomy of a mobile agricultural robot in a structured environment to find an optimal path to perform selective and variable spraying of pesticides. To materialize these, a robust VRP (Vehicle Routing Problem) scheme with deterministic variable demand and nonlinear travel time is designed to navigate the robot while making decisions to fulfill the pesticide demand at each node. The nonlinear time function obtained from experiments necessitates the consideration of three objectives simultaneously. The NSGA (non-dominated sorting genetic algorithm)-III algorithm is adopted to determine the optimal path for the robot. To achieve this, the mixed integer algorithm is modified to handle the full integer complex routing problem to optimize three test case scenarios. Finally, the NSGA-III has shown the capability to solve the full integer constraint problem based on the proposed modifications.