Managing a Mobile Agricultural Robot Swarm for a seeding task

Abstract

Mobile Agricultural Robot Swarms (MARS) is an approach for autonomous farming operations by a coordinated group of robots. One key aspect of the MARS concept is the low individual intelligence, meaning that each robot is equipped with only a minimum of sensor technology in order to achieve a low cost and energy efficient system that provides scalability and reliability for field tasks. The robot swarms are coordinated by a centralized entity (OptiVisor) which is responsible for path planning, optimization and supervision. It also serves as a mediator between the robots and different cloud services responsible for the documentation of the procedure. This paper focuses on the architecture and function of OptiVisor within the overall MARS system. An OptiVisor in combination with a simulation environment for a robot swarm is presented and shows the feasibility of the general concept and the current state of the algorithms. Furthermore, the paper shows results about the current progress of OptiVisor integration using real robots.