Explainability is essential for users to effectively understand, trust, and manage powerful artificial intelligence applications.

We present one approach to achieve safe navigation in an indoor dynamic environment. So far, there have been various useful collision avoidance algorithms and path planning schemes. However, those algorithms possess fundamental limitations in that the robot can avoid only ldquovisiblerdquo ones among surrounded obstacles. In a real environment, it is not possible to detect all the dynamic obstacles around the robot. There are many occluded regions due to the limited field of view. In order to avoid collisions, it is desirable to exploit visibility information. This paper proposes a safe navigation scheme to reduce collision risk considering occluded dynamic obstacles. The robot's motion is controlled by the hybrid control scheme. The possibility of collision is dually reflected to path planning and speed control. The proposed scheme clearly indicates the structural procedure on how to model and to exploit the risk of navigation. The proposed scheme is experimentally tested in a real office building. The experimental results show that the robot moves along the safe path to obtain sufficient field of view. In addition, safe speed constraints are applied in motion control. It is experimentally verified that a robot safely navigates in dynamic indoor environment by adopting the proposed scheme.

In recent years, the application of transformer-based models in time-series forecasting has received significant attention. While often demonstrating promising results, the transformer architecture encounters challenges in fully exploiting the temporal relations within time series data due to its attention mechanism. In this work, we design eXponential Patch (xPatch for short), a novel dual-stream architecture that utilizes exponential decomposition. Inspired by the classical exponential smoothing approaches, xPatch introduces the innovative seasonal-trend exponential decomposition module. Additionally, we propose a dual-flow architecture that consists of an MLP-based linear stream and a CNN-based non-linear stream. This model investigates the benefits of employing patching and channel-independence techniques within a non-transformer model. Finally, we develop a robust arctangent loss function and a sigmoid learning rate adjustment scheme, which prevent overfitting and boost forecasting performance.

Cheongwoong Kang, Jaesik Choi. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.