One of the most important aspects of agriculture is the ability to accurately estimate the expected yield. This is usually done by means of a manual count of all the fruit from a sample of trees – a time-consuming and inaccurate process. Although the use of a robot for this job seems obvious, agricultural robots still lack the necessary abilities. In an unusual study conducted by Itamar Elyakim, an MSc student in the School of Mechanical Engineering, under the supervision of Dr Yossi Yovel from the School of Zoology and Director of the Zoological Garden, the researchers are seeking to develop agricultural technology using bio-inspired sonar. Bats use sonar for orientation and can easily navigate through dense vegetation and distinguish between fruit and foliage. In this study, which was partially conducted in the Botanical Garden, the researchers successfully developed the robot’s ability to identify and classify different plants and estimate the mass of fruit they bear. The project focuses on the robotic orientation aspects of the Agrirobot initiative, aiming to develop a sonar-based method for robotic-mapping, obstacle avoidance and path planning in a greenhouse or an orchard. This will allow the yield-assessment robot to autonomously navigate at the requisite site based on bio-sonar only. Such an ability is an essential step on the way to developing a fully automatic yield assessment approach, which will be far cheaper and more accurate than all the measurement means currently in use.

Developing such a sonar-based method for robotic-mapping will enable obstacle avoidance and path planning in a greenhouse or an orchard, and thus contribute to a breakthrough in the ability to correctly estimate the expected fruit yield.