This article presents a novel approach for generating a three‐dimensional radiation map using data collected by mobile robots, aimed at monitoring radiation distribution in environments such as nuclear power plants. The proposed approach leverages Gaussian process regression with a novel adaptation of the inverse square law as a kernel function, which accurately reflects the physical characteristics of radiation, enabling precise mapping from uncertain data. Additionally, a method is proposed for constructing a comprehensive radiation map in 3D environments by estimating the radiation source and project the radiation data from sparse data. The effectiveness of the methodology is validated through simulations and experiments. Utilizing Octomap, a 3D spatial mapping tool, the study not only successfully visualizes radiation distribution in complex settings with multiple sources but also quantitatively demonstrates the enhanced accuracy of our approach compared to other existing methods. This research offers contributions in managing radiation risks, providing essential insights into the field.

For the logistics environment, multi-UAV algorithms have been studied for the purpose of order picking in warehouses. However, modern order picking adopts static order picking methods that struggle to cope with increasing volumes of goods because the algorithms receive orders for a certain period of time and pick only those orders. In this paper, by using the modified interventionist method and dynamic path planning, we aim to assign orders received in real-time to multi-UAVs in the warehouse, and to determine the order picking sequence and path of each UAV. The halting and correcting strategy is proposed to assign orders to UAVs in consideration of the similarity between the UAV’s picking list and the orders. A UAV starts picking orders by using the ant colony optimization algorithm for the orders initially assigned. For additional orders, the UAV modifies the picking sequence and UAV’s path in real time by using the k-opt-based algorithm. We evaluated the proposed method by changing the parameters in a simulation of a general warehouse layout. The results show that the proposed method not only reduces completion time compared to the previous algorithm but also reduces UAV’s travel distance and the collapsed time.

As mobile robots perform long-term operations in large-scale environments, coping with perceptual changes becomes an important issue recently. This paper introduces a stochastic variational inference and learning architecture that can extract condition-invariant features for visual place recognition in a changing environment. Under the assumption that a latent representation of the variational autoencoder can be divided into condition-invariant and condition-sensitive features, a new structure of the variation autoencoder is proposed and a variational lower bound is derived to train the model. After training the model, condition-invariant features are extracted from test images to calculate the similarity matrix, and the places can be recognized even in severe environmental changes. Experiments were conducted to verify the proposed method, and the experimental results showed that our assumption was reasonable and effective in recognizing places in changing environments.