Semantic mapping and localization improve robot farming tasks indoors

Semantic SLAM in Precision Agriculture using Bayesian Inference

Robotics

Summary

Mapping and navigating fields of crops is tricky, especially without GPS. The authors created a system where a robot can identify plants and their characteristics, then build a detailed map while figuring out its location. It uses a method called Bayesian inference to update its understanding and combines this with a mapping technique. They tested this approach on a robot dog in indoor experiments with fake plants and in simulation, showing it can track at least 400 plants in real time.

What this means in practice

Authors

Ruben Beumer, Sander Doodeman, René van de Molengraft, Duarte Antunes

Abstract

This paper presents a real-time semantic world modeling framework specialized for precision agriculture using autonomous robots. The framework combines probabilistic mapping of objects and their semantic attributes, updated through Bayesian inference, with a graph-based Simultaneous Localization and Mapping (SLAM) approach implemented using $g^2o$, a general framework for graph optimization. This integration enables accurate mapping and localization without relying solely on GPS. By leveraging semantic information such as plant type, size, and health, the robot can perform tasks while mapping and localizing itself within a field of crops. The proposed framework was validated through Gazebo simulations and physical experiments on an indoor field with artificial plants using Boston Dynamics' robot dog Spot. A YOLOv8n object detection model was trained to extract object and semantic data from depth camera observations. These simulations and experiments demonstrate that the system can successfully perform real-time mapping of up to at least 400 plants.