• ETRI Journal
• /
• v.45 no.5
• /
• pp.731-734
• /
• 2023

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.2
• /
• pp.95-100
• /
• 2013

Localization is very important for the autonomous navigation of Unmanned Ground Vehicles; however, it is difficult that they have a precise Inertial Navigation System(INS) sensor, especially Small Unmanned Ground Vehicle(SUGV). Moreover, there are some condition such as denial of global position system(GPS), GPS/INS integrated system is not robust. This paper proposes the estimation algorithm with optical flow sensor and INS. Being compared with previous researches, the proposed algorithm is suitable for skid steering vehicles. We revised the measurement model of previous research for the accuracy of side direction position. Experimental results were performed to verify the algorithm, and the result showed an excellent performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.20 no.6
• /
• pp.803-812
• /
• 2017

This paper proposes a local path planning method for stable autonomous driving in rough terrain. There are various path planning techniques such as candidate paths, star algorithm, and Rapidly-exploring Random Tree algorithms. However, such existing path planning has limitations to reflecting the stability of unmanned ground vehicles. This paper suggest a path planning algorithm that considering the stability of unmanned ground vehicles. The algorithm is based on the genetic algorithm and assumes to have probability based obstacle map and elevation map. The simulation result show that the proposed algorithm can be used for real-time local path planning in rough terrain.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.5
• /
• pp.747-752
• /
• 2011

Recently, skid steering methods have been increasingly applied to unmanned ground vehicles since they can provide a narrow turn that general steering methods like ackerman steering may not provide. However, dynamic behaviors of the skid steering vehicles with articulating arms which occur during a steering are very complicated and coupled. This makes it difficult to control vehicles and in severe case vehicles may loose stability. There are two methods to control unmanned ground vehicles. The first one is speed control method generally used with easiness and robustness in remote vehicle control. The next one is torque control allowing the vehicles to get better performance in several cases provided careful application is achieved. This paper addresses dynamic phenomena of skid steering vehicles during steering and compares with vehicle driving control methods between torque(traction force) control and speed control.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.4
• /
• pp.388-395
• /
• 2014

Nowadays unmanned ground systems are used in supporting of surveillance and explosive ordnance disposal. Also, we expect that will be used to remarkably enhance combat capability through network-based cooperative operations with other combat systems. In order to effectively develop those unmanned systems, we needs a systematic method to analyze combat effectiveness and validate required operation capabilities. In this paper, we propose a practical approach to simulate remote-operated unmanned ground systems by using OneSAF, an US-Army simulation framework. First of all, we design a simulation model of unmanned system by integrating with core components for wireless communications and remote control of mobility and fire. Next, we extend OneSAF functionality to create communication links that connects a remote controller with an unmanned vehicle and define a simulated behavior to operate unmanned vehicles via the communication links. Finally, we demonstrate the feasibility of the proposed model within OneSAF and summarize system effectiveness analysis results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.372-378
• /
• 2009

For effective mobility control of unmanned ground vehicles in outdoor off-road environments, terrain cover classification technology using passive sensors is vital. This paper presents a novel method far terrain classification based on color and texture information of off-road images. It uses a neural network classifier and wavelet features. We exploit the wavelet mean and energy features extracted from multi-channel wavelet transformed images and also utilize the terrain class spatial coordinates of images to include additional features. By comparing the classification performance according to applied features, the experimental results show that the proposed algorithm has a promising result and potential possibilities for autonomous navigation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.6
• /
• pp.618-638
• /
• 2020

An unmanned aerial vehicle(UAV) refers to an aircraft that has all or part of its functions to autonomously fly by grasping the surrounding environment by remote control on the ground without a pilot on board. With the development of unmanned aerial technology, civil/military forces are developing unmanned aerial vehicles for various purposes. In order to control unmanned aerial vehicles from the ground, communication protocols between unmanned aerial vehicles and ground control equipment are required, and civil/military forces have developed and used a photocall for different purposes. In this study, the characteristics of the MAVLink protocol used in the private sector and the STANAG 4586 protocol used in the military are compared/analyzed in detail to find elements to complement each other and to draw improvement measures for protocol unification.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.31-43
• /
• 2023

In this paper, we propose a method for generating a global path for an unmanned vehicle using public data of road section information. First, the method of analyzing road section information of the Ministry of Land, Infrastructure and Transport is presented. Second, we propose a method of preprocessing the acquired road section information and processing it into meaningful data that can be used for global routes. Third, we present a method for generating a global path using the preprocessed road section information. The proposed method has proven its effectiveness through actual autonomous driving experiments of unmanned ground vehicles.

• Journal of the Korean Society of Systems Engineering
• /
• v.13 no.2
• /
• pp.18-25
• /
• 2017

The use of unmanned combat systems is of interest for future battlefield. Advanced techniques are being actively studied to build fully autonomous unmanned systems. However, there are technical, ethical and legal limitations for the fully autonomous unmanned combat systems. In addition, a remote controlled system is necessary so far in order to prepare for situations where fully autonomous unmanned systems fail to function properly. Thus, a procedure of developing operational requirements in system level is proposed and interface requirements of unmanned combat vehicles for remote control are described in this study.

• ETRI Journal
• /
• v.45 no.5
• /
• 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.