https://scholar.dgist.ac.kr/handle/20.500.11750/10139 2026-04-24T13:03:17Z https://scholar.dgist.ac.kr/handle/20.500.11750/60267 Title: Stable path planning algorithm for avoidance of dynamic obstacles Author(s): Kang, Won-Seok; Yun, Sanghun; Kwon, Hyung-Oh; Choi, Rock Hyun; Son, Chang-Sik; Lee, Dong Ha Abstract: Previous research of path planning has focused mainly on finding shortest paths or smallest movements. These methods, however, have poor stability characteristics when dynamic obstacles are considered on real-life or in-body map's environments. In this paper, we suggest a stable path planning algorithm for avoidance of dynamic obstacles. The proposed method makes the movement of a mobile robot more stable in a dynamic environment. Our focus is based on finding optimal movements for stability rather than finding shortest paths or smallest movements. The algorithm is based on Genetic Algorithm (GA) and uses k-means clustering to recognize the distribution of dynamics obstacles in various mobile space. Simulation results confirm this method can determine stable paths through environments involving dynamic obstacles. In order to validate our results, we compared the dynamic k values used in k-means clustering and grid-based dynamic cell sizes from several test sets. © 2015 IEEE. 2014-12-31T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/59403 Title: Airborne Acoustic Communication using Inaudible Frequencies Supported by Smart Devices Author(s): Piao, Shiquan Abstract: Aerial acoustic communication enables low-rate data exchange using audible or inaudible acoustic waves and has the advantage of operating on virtually all smart devices without additional hardware, unlike NFC, whose adoption remains limited by hardware and platform constraints. Standard microphones and speakers can therefore be used for both transmission and reception, making the technology an appealing and practical complement to existing wireless methods.However, commodity devices primarily support the audible band, much of which overlaps with speech and ambient noise, leaving only a narrow portion suitable for reliable communication. To address this limitation, the proposed approach utilizes a frequency region that is broadly supported across devices yet minimally influenced by everyday acoustic environments, thereby enhancing overall stability and robustness.Furthermore, this paper introduces a Zoom-FFT-based narrow-band acoustic communication technique that improves robustness and frequency resolution within this constrained spectrum. By exploiting its high-resolution spectral analysis, the system can reliably extract communication signals even in noisy indoor settings, supporting practical short-range data exchange applications across diverse usage scenarios. 2025-11-30T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/59402 Title: VLM 시대의 목표 객체 탐색을 위한 지식 융합 전략 서베이 Author(s): 서보건; 김지선; 손준우; 박명옥; 김기섭 Abstract: The rapid advancement of robotics and deep learning has increasingly accelerated the use of Embodied AI, where robots autonomously explore and reason in complex real-world environments. With the growing demand for domestic service robots, efficient navigation in unfamiliar settings has become even more crucial. Object Goal Navigation (OGN) is a fundamental task for this capability, requiring a robot to find and reach a user-specified object in an unknown environment. Solving OGN demands advanced perception, contextual reasoning, and effective exploration strategies. Recent Vision-Language Models (VLMs) and Large Language Models (LLMs) provide agents with external common knowledge and reasoning capabilities. This paper poses the critical question: “Where should VLM/LLM knowledge be fused into Object Goal Navigation?” We categorize knowledge integration into the three stages adapted from the Perception-Prediction-Planning paradigm to offer a structured survey of Object Goal Navigation approaches shaped by the VLM era. We conclude by discussing current dataset limitations and future directions, including further studies on socially interactive navigation and operation in mixed indoor - outdoor environments. 2025-12-31T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/59388 Title: Comparative Analysis of Base-Width-Based Annotation Box Ratios for Vine Trunk and Support Post Detection Performance in Agricultural Autonomous Navigation Environments Author(s): Lyu, Hong-Kun; Yun, Sanghun; Park, Seung Abstract: AI-driven agricultural automation increasingly demands efficient data generation methods for training deep learning models in autonomous robotic systems. Traditional bounding box annotation methods for agricultural objects present significant challenges including subjective boundary determination, inconsistent labeling across annotators, and physical strain from extensive mouse movements required for elongated objects. This study proposes a novel base-width standardized annotation method that utilizes the base width of a vine trunk and a support post as a reference parameter for automated bounding box generation. The method requires annotators to specify only the left and right endpoints of object bases, from which the system automatically generates standardized bounding boxes with predefined aspect ratios. Performance assessment utilized Precision, Recall, F1-score, and Average Precision metrics across vine trunks and support posts. The study reveals that vertically elongated rectangular bounding boxes outperform square configurations for agricultural object detection. The proposed method is expected to reduce time consumption from subjective boundary determination and minimize physical strain during bounding box annotation for AI-based autonomous navigation models in agricultural environments. This will ultimately enhance dataset consistency and improve the efficiency of artificial intelligence learning. 2025-08-31T15:00:00Z