Survey and navigation in agricultural environments using robotic technologies

Abstract

In this paper, a novel approach for outdoor survey and navigation is presented using a skid-steering vehicle. In the agricultural field, intelligent farming robotic units able to report the plant health or the terrain conditions are very useful and can help farmers save money on labor and improve the harvest results. This work is based on collecting multiple sensor input data to produce more accurate vehicle position estimates and by associating them to the visual information in order to build a 3D map of the environment. The vehicle is able to autonomously return to specified sites at different time intervals to identify changes in plants or in specific terrain areas. Experimental results are presented to validate the system and showing its effectiveness in relevant agricultural settings.