Autonomous Navigation of Mobile Robots in Vineyard

抄録

Vineyards which are situated in remote mountainous areas receive weak GPS signals. Mobile robots working in such vineyards needs special algorithms to navigate without using GPS information. In this paper, we propose an algorithm of autonomous mobile robot navigation which uses only the local features of the vineyard. The algorithm only uses data from laser range sensor to accurately detect pillars supporting the grape plants in the presence of noise. Robust detection of these landmarks is important for the autonomous navigation of robot in vineyards. The detected pillars are also used for accurate localization and mapping. We also present an algorithm for smooth obstacle avoidance in vineyard for dynamic obstacles like moving people. Experiments in both simulation and actual vineyard fields are presented.