Coverage path planning for an autonomous robot specific to agricultural operations

Acute labor shortage and an increase in daily wages are forcing farm owners to move towards automated machinery. While the industrial revolution in India has significantly induced the shift towards machinery from indigenous equipment, we are still lagging behind in the field of automated equipment for agriculture. The key component for such systems is the path planning methodology used. A specific class of such an algorithm known as coverage path planning (CPP) is utilized for covering farmlands to perform various operations such as seeding, tilling, ploughing or spraying fertilizers and pesticides. This paper presents a novel CPP algorithm for automated machinery intended for usage in agriculture. In order to reduce the directional constraints, the proposed algorithm utilizes a high-resolution grid map representation of the environment. Free space is covered by distinguishing the grid cells as covered, unexplored, partial obstacle and obstacle cell. A distance transformation function is used to determine the order of covering unexplored cells as well as the shortest path to them, in the given environment. The performance of the proposed algorithm is evaluated with metrics such as completeness of coverage, time efficiency and also robustness to changes in the environment. Robotic Operating System (ROS) and Gazebo were used for simulating the proposed algorithm. The results prove the feasibility of the proposed algorithm to be implemented for automated systems to perform efficient coverage in agricultural operations.