Probabilistic-Based Robotic Radiation Mapping Using Sparse Data

摘要

This paper presents a novel methodology for generating radiation intensity maps using a mobile robotic platform and an integrated radiation model. The radiation intensity mapping approach consists of two stages. First, radiation intensity samples are collected using a radiation sensor mounted on a mobile robotic platform, reducing the risk of exposure to humans from an unknown radiation field. Next, these samples, which need only to be taken from a subsection of the entire area being mapped, are then used to calibrate a radiation model of the area. This model is then used to predict the radiation intensity field throughout the rest of the area that could not be directly measured. The performance of the approach is evaluated through experiments. The results show that the developed system is effective at achieving the goal of generating radiation maps using sparse data.