Human-Robot Interaction in Agriculture: A Systematic Review.

In the pursuit of optimizing the efficiency, flexibility, and adaptability of agricultural practices, human-robot interaction (HRI) has emerged in agriculture. Enabled by the ongoing advancement in information and communication technologies, this approach aspires to overcome the challenges originating from the inherent complex agricultural environments. Τhis paper systematically reviews the scholarly literature to capture the current progress and trends in this promising field as well as identify future research directions. It can be inferred that there is a growing interest in this field, which relies on combining perspectives from several disciplines to obtain a holistic understanding. The subject of the selected papers is mainly synergistic target detection, while simulation was the main methodology. Furthermore, melons, grapes, and strawberries were the crops with the highest interest for HRI applications. Finally, collaboration and cooperation were the most preferred interaction modes, with various levels of automation being examined. On all occasions, the synergy of humans and robots demonstrated the best results in terms of system performance, physical workload of workers, and time needed to execute the performed tasks. However, despite the associated progress, there is still a long way to go towards establishing viable, functional, and safe human-robot interactive systems.

Orchard Mapping with Deep Learning Semantic Segmentation.

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.