AGRIDS: an Advanced Multi-Modal Mapping Architecture for Robotics and Agriculture

Jonathan Cox, Marc Hanheide, Riccardo Polvara

Abstract: In this paper, we address the lack of standardisation in mapping and data storage in robotics and agriculture, aiming to effectively represent and store spatial, semantic, and temporal data for both applications. We propose a novel approach that integrates data from various sources, such as robotic and static sensors, to create comprehensive maps crucial for precision agriculture. Our architecture bridges the gap between robotics and agriculture domains, managing the storage of robotics sensor data and structured data. We combine technologies from context brokers, databases and object storage to integrate multi-modal data to enable more context-aware decision-making, paving the way for advancements in robotics and precision agriculture. Our proposed framework is open-source and available on our repository 1

External IDs:dblp:conf/case/CoxHP24