• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.30-42
• /
• 2023

Various studies have been conducted using microtraffic simulation (VISSIM) to analyze the safety of traffic flow when introducing autonomous vehicles. However, no studies have analyzed traffic safety in mixed traffic while considering the driving behavior of general vehicles as a parameter in VISSIM. Therefore, the aim of this study was to optimize the input variables of VISSIM for non-autonomous vehicles through genetic algorithms to obtain realistic behavior. A traffic safety analysis was then performed according to the penetration rate of autonomous vehicles. In a 640 meter section of US highway I-101, the number of conflicts was analyzed when the trailing vehicle was a non-autonomous vehicle. The total number of conflicts increased until the proportion of autonomous vehicles exceeded 20%, and the number of conflicts decreased continuously after exceeding 20%. The number of conflicts between non-autonomous vehicles and autonomous vehicles increased with proportions of autonomous vehicles of up to 60%. However, there was a limitation in that the driving behavior of autonomous vehicles was based on the results of the literature and did not represent actual driving behavior. Therefore, for a more accurate analysis, future studies should reflect the actual driving behavior of autonomous vehicles.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1557-1565
• /
• 2016

The UAV systems working in difficult environment should be able to performs various actions autonomously required to achieve the given mission without the human interventions. However, the actual tests for such UAV system will take heavy cost. Thus, the simulation test in advance before the actual test is important. This paper proposes a 3D visual simulation environment for autonomous agent-based UAV systems. The several simulation tests performed on the rescue scenarios will demonstrate our techniques.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.5
• /
• pp.619-627
• /
• 2024

As AI technology advances, interest in performing multi-robot autonomous missions for manned-unmanned teaming (MUM-T) is increasing. In order to develop autonomous mission performance technology for multiple robots, simulation technology that reflects the characteristics of real robots and can flexibly apply various missions is needed. Additionally, in order to solve complex non-linear tasks, an API must be provided to apply multi-robot reinforcement learning technology, which is currently under active research. In this study, we propose the campaign model to flexibly simulate the missions of multiple robots. We then discuss the results of developing a simulation environment that can be edited and run and provides a reinforcement learning API including acceleration performance. The proposed simulated control module and simulated environment were verified using an enemy infiltration scenario, and parallel processing performance for efficient reinforcement learning was confirmed through experiments.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.2
• /
• pp.130-137
• /
• 2013

In this paper, decoupled controller design for Autonomous Underwater Vehicle(AUV) and its simulated performance test results and Hardware In the Loop Simulation(HILS) results are presented. Control system design is done using the PD control scheme. Stability analysis and step response of closed loop system under uncertain parameter condition are also presented. The results of full coupled nonlinear model simulation show the well applicability of the designed controller. From the results of HILS, we can verify performance of real time processing and implemented hardware for AUV.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.19 no.6
• /
• pp.67-79
• /
• 1982

The stability of general pulse-width modulation system with Gaussian random disturbance was discussed . General system is divided into nonlinear and linear elements using the conventional describing function method. The concept of the equivalent admittance was used to find the transfer characteristic of the nonlinear element of the system. In this paper the self-sustained oscillation condition in the autonomous system was derived and the results was analyzed with computer simulation.

• Journal of Positioning, Navigation, and Timing
• /
• v.5 no.2
• /
• pp.97-107
• /
• 2016

Military Autonomous Underwater Vehicle (AUV) is utilized to search a mine under the sea. This paper presents design and performance verification of real-time hybrid navigation system for AUV. The navigation system uses Doppler Velocity Log (DVL) integration method to correct INS error in underwater. When the AUV is floated on the water, the accumulated error of navigation algorithm is corrected using position/velocity of GPS. The navigation algorithm is verified using 6 Degree Of Freedom (DOF) simulation, Program In the Loop Simulation (PILS). Finally, the experiments are performed in real sea environment to prove the reliability of real-time hybrid navigation algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.9 no.3
• /
• pp.213-218
• /
• 2009

This paper describes a classical algorithm carrying out dynamic 3D obstacle recognition for autonomous underwater vehicles (AUVs), Support Vector Machines (SVMs). SVM is an efficient algorithm that was developed for recognizing 3D object in recent years. A recognition system is designed using Support Vector Machines for applying the capabilities on appearance-based 3D obstacle recognition. All of the test data are taken from OpenGL Simulation. The OpenGL which draws dynamic obstacles environment is used to carry out the experiment for the situation of three-dimension. In order to verify the performance of proposed SVMs, it compares with Back-Propagation algorithm through OpenGL simulation in view of the obstacle recognition accuracy and the time efficiency.

• Journal of IKEEE
• /
• v.14 no.4
• /
• pp.324-331
• /
• 2010

본 논문에서는 무인자동차의 자율주행을 위한 알고리즘을 제시하고 3차원 그래픽 시뮬레이션을 통하여 안정성 기반 자율주행 알고리즘의 성능을 검증하고자 한다. 제안된 자율주행 알고리즘은 주변 인접 차량의 위치, 속도, 가속도, 주행 차로 정보를 바탕으로 자율주행 차량과의 충돌가능성 및 충돌예측시간을 계산하여 최적의 안정 주로를 선택하고 이러한 주행 차로에 대한 주행 궤적을 생성하여 추종토록 함으로써 자율주행이 이루어지도록 한다. 본 논문에서는 제안된 자율주행 알고리즘을 검증하기 위하여 3차원 그래픽 시뮬레이션 환경을 구축하였으며 다차로, 다차량 주행 환경에서 몇 가지 가상 도로 환경을 구축하여 시뮬레이션 하였고 자율주행 차량의주행 궤적을 인접 주행차량의 주행 궤적과 비교 확인함으로써 알고리즘의 타당성을 검증하였다. 시뮬레이션 결과 제시된 안정성 기반 자율주행 알고리즘은 다차로, 다차량 주행 환경에서 주변 차량과 충돌 없이 안정적인주행 성능을 보여주는 것을 확인할 수 있었다.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.1
• /
• pp.61-67
• /
• 1999

There has been an ever increasing interest in mobile robot for home services. However, issues currently being investigated for path planning of the mobile robot is concentrated to solving the problem of finding the optimal path from the initial location to the final location under the given performance index. In this study, we newly present a sweeping algorithm for autonomous mobile robot to cover the whole closed area under the unknown environment. And we verify the validity the validity of the formalized algorithm by computer simulation with the changing environment conditions. In addition to this, we analyse the effect of real system implementation of the proposed algorithm to a experimental miniature mobile robit(Khepera).

• Convergence Security Journal
• /
• v.18 no.3
• /
• pp.3-9
• /
• 2018

The Deep Deterministic Policy Gradient (DDPG) algorithm is an algorithm that learns by using artificial neural network s and reinforcement learning. Among the studies related to reinforcement learning, which has been recently studied, the D DPG algorithm has an advantage of preventing the cases where the wrong actions are accumulated and affecting the learn ing because it is learned by the off-policy. In this study, we experimented to control the bicycle autonomously by applyin g the DDPG algorithm. Simulation was carried out by setting various environments and it was shown that the method us ed in the experiment works stably on the simulation.