• Journal of Electrical Engineering and Technology
• /
• 제7권2호
• /
• pp.171-177
• /
• 2012

The autonomous microgrid is a system that is autonomously operated depending on the grid and internal load condition, without the operator's intervention. In this study, a control algorithm for the microsource and an operation algorithm for the microgrid are proposed to realize the autonomous microgrid system. In addition, a microgrid operation system based on the operation algorithm is proposed. The electromagnetic transient program is used by the proposed microsource control algorithm for simulation, and the validity of the algorithm is verified. The proposed operation system is verified based on a case study using a simulator and test devices.

• IEMEK Journal of Embedded Systems and Applications
• /
• 제6권5호
• /
• pp.303-309
• /
• 2011

In this paper, an intelligent force control technique is applied to an autonomous helicopter. Although most research on the autonomous helicopter system is about navigation and control, force control of an autonomous helicopter system is quite new and not presented yet. After controlling the position of the helicopter by the LQR method, force control is applied. The adaptive impedance force control algorithm is introduced and tested to regulate the desired force under unknown location and stiffness of the environment. To compensate for uncertainty from outer disturbance, a neural network is added to form an intelligent force control framework. Simulation studies show that the proposed force control algorithm works well.

• Journal of Auto-vehicle Safety Association
• /
• 제13권4호
• /
• pp.123-128
• /
• 2021

This paper present box feature estimation from LiDAR point cluster using maximum likelihood Method. Previous LiDAR tracking method for autonomous driving shows high accuracy about velocity and heading of point cluster. However, Assuming the average position of a point cluster as the vehicle position has a lower accuracy than ground truth. Therefore, the box feature estimation algorithm to improve position accuracy of autonomous driving perception consists of two procedures. Firstly, proposed algorithm calculates vehicle candidate position based on relative position of point cluster. Secondly, to reflect the features of the point cluster in estimation, the likelihood of the particle scattered around the candidate position is used. The proposed estimation method has been implemented in robot operating system (ROS) environment, and investigated via simulation and actual vehicle test. The test result show that proposed cluster position estimation enhances perception and path planning performance in autonomous driving.

• ETRI Journal
• /
• 제43권6호
• /
• pp.1013-1023
• /
• 2021

In this study, we propose a practical path planning method that combines the A^* search algorithm and minimum snap trajectory generation. The A^* search algorithm determines a set of waypoints to avoid collisions with surrounding obstacles from a starting to a destination point. Only essential waypoints (waypoints necessary to generate smooth trajectories) are extracted from the waypoints determined by the A^* search algorithm, and an appropriate time between two adjacent waypoints is allocated. The waypoints so determined are connected by a smooth minimum snap trajectory, a dynamically executable trajectory for the quadrotor. If the generated trajectory is invalid, we methodically determine when intermediate waypoints are needed and how to insert the points to modify the trajectory. We verified the performance of the proposed method by various simulation experiments and a real-world experiment in a forested outdoor environment.

• Journal of the Korean Society of Industry Convergence
• /
• 제26권2_2호
• /
• pp.359-370
• /
• 2023

For a vehicle to follow a reference path accurately, its position must be estimated accurately and reliably. In this paper, we propose a lateral control algorithm for autonomous navigation of a vehicle via USAT(Ultrasonic Satellite System), which is an absolute position measurement system using an ultrasonic wave and INS(Inertial Navigation System) integration. In order to estimate the vehicle's parameters, a J-turn test is used. And the autonomous navigation performances of proposed lateral control algorithm and validity of proposed lateral control algorithm are verified and evaluated by simulation and experiments.

• Journal of the Korean Society for Precision Engineering
• /
• 제12권1호
• /
• pp.58-67
• /
• 1995

A path planning algorithm using a laser range finder are presented for real-tiem navigation of an autonomous guided vehicle. Considering that the laser range finder has the excellent resolution with respect to angular and distance measurements, a sophisticated local path planning algorithm is achieved by using the human's heuristic method. In the case of which the man knows not rhe path, but the goal direction, the man forwards to the goal direction, avoids obstacle if it appears, and selects the best pathway when there are multi-passable ways between objects. These heuristic principles are applied to the path decision of autonomous guided vehicle such as forward open, side open and no way. Also, the effectiveness of the established path planning algorithm is estimated by computer simulation in complex environment.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.63-71
• /
• 2024

Deep reinforcement learning (RL) significantly influences autonomous vehicle development by optimizing decision-making and adaptation to complex driving environments through simulation-based training. In deep RL, an activation function is used, and various activation functions have been proposed, but their performance varies greatly depending on the application environment. Therefore, finding the optimal activation function according to the environment is important for effective learning. In this paper, we analyzed nine commonly used activation functions for RL to compare and evaluate which activation function is most effective when using deep RL for autonomous vehicles to learn highway merging. To do this, we built a performance evaluation environment and compared the average reward of each activation function. The results showed that the highest reward was achieved using Mish, and the lowest using SELU. The difference in reward between the two activation functions was 10.3%.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제18권2호
• /
• pp.129-143
• /
• 2019

As the importance of autonomous vehicle safety is emphasized, the application of ISO-26262, a development verification guideline for improving safety and reliability, and the safety verification of autonomous vehicles are becoming increasingly important, in particular, SAE standard level 3 or higher level autonomous vehicles detect and decision the surrounding environment instead of the human driver. Therefore, if there is and failure or malfunction in the autonomous driving function, safety may be seriously affected. So autonomous vehicles, it is essential to apply and verity the safety concept against failure and malfunctions. In this study, we study the fault injection scenarios for safety evaluation and verification of autonomous vehicles using ISO-26262 part3 process and STPA were studied and safety measures for safety concept design were studied through simulation bases fault injection test.

• Journal of the Korea Society for Simulation
• /
• 제17권2호
• /
• pp.49-61
• /
• 2008

Most battleship warfare M&S systems run relatively slow and the simulation results are often unfair since the system should interact with human operators(controller and/or gamer). To deal with these problems, we have proposed the agent-based battleship warfare M&S system which interact with multiple agent systems instead of human operators. Agent-based M&S system may be able to efficiently support the analysis of effectiveness and/or the operational tactics development of given warfare by providing autonomous reasoning capabilities without the intervention of human controller. To do this, the paper propose the design concept and methodology using the advanced modeling and simulation framework as well as autonomous agent design principle. Several simulation tests performed on the battleship warfare case study on Korea Yellow sea will illustrate our techniques.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제22권1호
• /
• pp.276-290
• /
• 2023

Several efforts in Korea are currently underway with the goal of commercializing autonomous vehicles. Hence, various studies are emerging on autonomous vehicles that drive safely and quickly according to operating guidelines. The current study examines the path search of an autonomous vehicle from a microscopic viewpoint and tries to prove the efficiency required by learning the lane change of an autonomous vehicle through Deep Q-Learning. A SUMO was used to achieve this purpose. The scenario was set to start with a random lane at the starting point and make a right turn through a lane change to the third lane at the destination. As a result of the study, the analysis was divided into simulation-based lane change and simulation-based lane change applied with Deep Q-Learning. The average traffic speed was improved by about 40% in the case of simulation with Deep Q-Learning applied, compared to the case without application, and the average waiting time was reduced by about 2 seconds and the average queue length by about 2.3 vehicles.