• 한국군사과학기술학회지
• /
• 제27권3호
• /
• pp.395-405
• /
• 2024

This study provides a thorough examination of Unmanned Ground Vehicles(UGVs), focusing on crucial technologies and trends across major global markets. It includes an in-depth patent analysis revealing the dominant positions of the United States and the European Union in this field. Additionally, it underscores substantial advancements made by China, Japan, and Korea since 2010. Using Latent Dirichlet Allocation(LDA)-based patent text mining, the study identified key technology areas in UGV development, such as advanced control systems, navigation technologies, power supply mechanisms, and sensing and communication tools. Through linear regression analysis, the study predicted the future paths of these technology areas, offering important insights into the evolving world of UGV technology. The findings can provide strategic guidance for stakeholders in the defense, commercial, and academic sectors, pointing out the future directions in UGV advancements.

• ETRI Journal
• /
• 제45권5호
• /
• pp.795-810
• /
• 2023

Unmanned aerial vehicles (UAV) and ground vehicles (UGV) require advanced video analytics for various tasks, such as moving object detection and segmentation; this has led to increasing demands for these methods. We propose a zero-shot video object segmentation method specifically designed for UAV and UGV applications that focuses on the discovery of moving objects in challenging scenarios. This method employs a background memory model that enables training from sparse annotations along the time axis, utilizing temporal modeling of the background to detect moving objects effectively. The proposed method addresses the limitations of the existing state-of-the-art methods for detecting salient objects within images, regardless of their movements. In particular, our method achieved mean J and F values of 82.7 and 81.2 on the DAVIS'16, respectively. We also conducted extensive ablation studies that highlighted the contributions of various input compositions and combinations of datasets used for training. In future developments, we will integrate the proposed method with additional systems, such as tracking and obstacle avoidance functionalities.

• 대한임베디드공학회논문지
• /
• 제17권2호
• /
• pp.115-121
• /
• 2022

This paper proposes a distributed model predictive formation control algorithm for a group of unmanned ground vehicles (UGVs) with guaranteeing collision avoidance between UGVs. Generally, the model predictive control based formation control has a disadvantage in that it takes a long time to compute control inputs when considering collision avoidance between UGVs. In this paper, in order to overcome this problem, the formation control algorithm is implemented in a distributed manner so that it could be individually controlled. Also, a collision-avoidance method considering real-time is proposed. The proposed formation control algorithm is implemented based on robot operating system (ROS), open source-based middleware. Through the various simulation tests, it is confirmed that the formation control of five UGVs is successfully performed while avoiding collisions between UGVs.

• 자동차안전학회지
• /
• 제15권4호
• /
• pp.6-15
• /
• 2023

This paper develops scenarios to evaluate the safety performance of Unmanned Ground Vehicle on military circumstances. The scenarios were created using Pegasus Project 6-layer format. These scenarios consist of straight road, curved road, merging road and crossroad. We adapt these scenarios to unpaved road. The characteristics of unpaved roads were divided into roughness, friction coefficient and road frequency. This adaption is validated via computer simulation. We observe the scan lines of vehicle become tangled of the straight road that make the cognitive abilities of the vehicle low and the lane-keeping is unable when vehicles entering curved off-roads over 40 km/h. The developed scenarios will contribute to enhancing stability from the perspective of introducing autonomous driving technology to Korean military.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2010년도 추계학술발표대회
• /
• pp.1540-1542
• /
• 2010

국방분야의 무인지상무기체계(Unmanned Ground Vehicles)는 소프트웨어 결함 발생시 유인무기체계와 달리 응급 조치를 수행할 수 있는 사람이 탑승하지 않기 때문에 임무 수행에 치명적인 영향을 미칠 수 있다. 따라서, 무인지상무기체계에 탑재되는 내장형 SW의 신뢰성 있는 임무 수행을 위한 방법을 필요로 한다. 본 연구에서는 무선 Ad-hoc 네트워크로 연결된 UGV의 SW 결함을 원격으로 진단하고, 치료하기 위한 방법에 대해 연구하였다. 국방분야의 무인무기체계에 탑재된 내장형 SW의 신뢰성을 높이기 위해 적용가능하다.

• 로봇학회논문지
• /
• 제13권4호
• /
• pp.220-229
• /
• 2018

In the midst of disaster, such as an earthquake or a nuclear radiation exposure area, there are huge risks to send human crews. Many robotic researchers have studied to send UGVs in order to replace human crews at dangerous environments. So far, two-dimensional camera information has been widely used for teleoperation of UGVs. Recently, three-dimensional information based teleoperations are attempted to compensate the limitations of camera information based teleoperation. In this paper, the 3D map information of indoor and outdoor environments reconstructed in real-time is utilized in the UGV teleoperation. Further, we apply the LTE communication technology to endure the stability of the teleoperation even under the deteriorate environment. The proposed teleoperation system is performed at explosive disposal missions and their feasibilities could be verified through completion of that missions using the UGV with the Explosive Ordnance Disposal (EOD) team of Busan Port Security Corporation.

• 한국군사과학기술학회지
• /
• 제18권4호
• /
• pp.432-440
• /
• 2015

UGVs(Unmanned Ground Vehicles) are robots that can substitute humans in reconnaissance operations of potentially dangerous and contaminated sites. Currently, there have been active research on utilizing UGVs in military environments. Much resrach has been focused on exploiting the weakness of topology-based routing and instead utilize location-based routing for the networking of UGVs. It is generally assumed that location-based routing methods can fully utilize the location information gained from GPS. However, this may not be possible in tactical environments due to enemy GPS jamming and LOS(Line of Sight) limitations. To solve this problem, we propose a location-based routing scheme utilizing low control message that can calibrate the location information using GPS information as well as location of neighboring UGV, movement direct and speed information. Also utilizing topology-based routing scheme to solve incorrect location information in GPS jamming region.

• 대한임베디드공학회논문지
• /
• 제6권3호
• /
• pp.124-131
• /
• 2011

There are many researches in unmanned vehicles such as UGV(Unmanned Ground Vehicle), AUV(Autonomous Underwater Vehicle). In these researches, differential wheeled mobile robots are mainly used to develop the experimental stage algorithm because of the simplicity of modeling and control. Usually a commercial product used in the study, but in order to operate a commercial product to the restrictions because there would need to use a fixed protocol. Using the microprocessor makes the internal sensors(encoder and INS) and external sensors(ultrasonic sensors, infrared sensors) operate and to determine commands for robot operation. This paper propose a mobile robot design for suitable purpose.

• 한국컴퓨터정보학회논문지
• /
• 제18권10호
• /
• pp.109-119
• /
• 2013

현대 정보기술의 지속적인 발전은 무인화 및 자율화를 기반으로 한 모의 환경의 급격한 패러다임의 변화를 야기했으며 이로 인해 실 운용을 대비한 새로운 개념의 전장 환경 시뮬레이션 기술과 장치가 요구되고 있다. 그러나 무인 체계 개발은 타 개발과는 차별적으로 다양하고 복잡한 기능을 고려해야함과 동시에 검증 과정이 어렵다는 특징을 가진다. 이를 위해 본 논문에서는 무인체계 개발을 위한 효과적인 시뮬레이터를 보이고 표적탐지/인지성능개선, 표적 위치오차 개선, 그리고 초기 표적 탐지시간 단축의 세 가지 정보융합 기술을 제안한다. 제안하는 탐지/인지 성능 개선기술은 로봇의 감지기 영상을 이용하여 표적을 탐지한 후 인식하고 다수의 로봇 인식결과를 바탕으로 정보 융합하여 인식오차를 보정한다. 또한 표적 위치 정확도 개선은 다수 로봇을 활용하여 탐지한 표적의 위치를 보다 정확하게 산출하기 위한 방법이다. 그리고 초기 표적 탐지시간 단축 기법은 임의의 로봇이 표적을 탐지하는 과정에서 장애물에 의해 가려져 탐지가 불가능 할 경우가 생길 경우 이를 미리 판단하여 표적의 예상 궤적을 예측하고 해당 궤적 값인 위치값과 각도값을 타 로봇에게 전송하여 탐지를 지속적으로 수행할 수 있도록 하는 방법이다. 제안하는 방법을 통해 구현된 시뮬레이터의 활용을 통해 무인로봇의 주된 역할인 정보 융합 임무를 충실히 수행함을 확인한다.

• 대한공간정보학회지
• /
• 제22권3호
• /
• pp.79-85
• /
• 2014

지상무인로봇의 성공적 운용을 위해서는 작전지역에 대한 가동성 분석, 위협도 분석 등의 사전분석 결과를 반영하여 최적의 경로계획을 수행하여야 한다. 그 중에서도 가동성 분석 결과는 차량의 안전 보장과 관련성이 높으며, 특히 비포장로, 초지 등 야지 주행시 차량의 안전에 지대한 영향을 미칠 수 있다. 지형정보는 가동성 분석을 위한 특정 관심영역의 데이터 추출과 비용산출 과정에서 중추적인 역할을 한다. 본 논문에서는 새로운 기반 데이터로서 토지피복도의 활용성을 분석하고, 이를 기반으로 지상무인로봇의 주행을 위한 가동맵 생성방안을 제시한다. 시뮬레이션을 통하여 제안된 토지피복도의 단독 활용방법과 타 지형정보체계와의 혼합 활용방법이 기존 방법과 비교해 가동성 표현과 최적 경로계획에 있어 개선 효과를 보임을 확인한다.