Robust semantic navigation in orchards

Many industrial sectors (e.g. automotive) have undergone strong automation in the past decades. However, within the agricultural sector, and more specifically within the fruit industry, this automation has not yet been implemented due to the cost of existing automation solutions. The decreasing number of seasonal workers and increasing cost of manual labour threatens the profitability of the Belgian fruit industry. This PhD wants to support this sector by developing affordable yet robust mobile navigation techniques in the challenging outdoor setting of orchards. The research targets three main objectives: (1) robust outdoor sensing and dataset construction; (2) lifelong localization with respect to trees and orchards using a semantic, adaptable map of the orchard; (3) outdoor navigation and manipulation based on the semantic map.