• ETRI Journal
• /
• v.44 no.4
• /
• pp.641-653
• /
• 2022

In the process of autonomous vehicle motion planning and to create comfort for vehicle occupants, factors that must be considered are the vehicle's safety features and the road's slipperiness and smoothness. In this paper, we build a mathematical model based on the combination of a genetic algorithm and a neural network to offer lane-change solutions of autonomous vehicles, focusing on human vehicle control skills. Traditional moving planning methods often use vehicle kinematic and dynamic constraints when creating lane-change trajectories for autonomous vehicles. When comparing this generated trajectory with a man-generated moving trajectory, however, there is in fact a significant difference. Therefore, to draw the optimal factors from the actual driver's lane-change operations, the solution in this paper builds the training data set for the moving planning process with lane change operation by humans with optimal elements. The simulation results are performed in a MATLAB simulation environment to demonstrate that the proposed solution operates effectively with optimal points such as operator maneuvers and improved comfort for passengers as well as creating a smooth and slippery lane-change trajectory.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.175-178
• /
• 2015

최근 모바일 장비 및 시스템의 발달로 위치정보와 이동 객체에 관련된 많은 서비스들이 연구되고 있다. 궤적은 이동 객체가 시간에 따라 변하는 위치정보들의 모음이다. 기존의 데이터베이스 시스템에서는 이동 객체 데이터 타입을 지원하지 않는다. 이 논문에서는 공간 데이터베이스로 많이 활용되고 있는 PostgreSQL/PostGIS 상에서 궤적 데이터의 연산 및 질의 처리가 가능한 확장형 모듈로써 PostTrajectory를 제안하고 있다. 또한, 궤적 데이터에 대한 다양한 질의 요구 조건들을 충족시킬 수 있는 함수들을 구현하여 궤적 데이터의 효율적인 질의 처리를 가능하게 하였다.

• Journal of Power Electronics
• /
• v.13 no.1
• /
• pp.51-58
• /
• 2013

This paper proposes the power conversion mechanism of a bailer-charge-transfer zero-current-switching (CT-ZCS) circuit. The operation modes are analyzed and researched using state trajectory equations. The topology of CT-ZCS based on soft-switching inverters offers some merits such as: tracking the input reference signal dynamically, bearing load shock and short circuit, multiplying inverter N+1 redundancy parallel, coordinating power balance for easy control, and soft-switching commutation for high efficiency and large capacity. These advantages are distinctive from conventional inverter topologies and are especially demanded in AC drives: new energy generation and grid, distributed generation systems, switching power amplifier, active power filter, and reactive power compensation and so on. Prototype is manufactured and experiment results show the feasibility and dynamic voltage-tracking characteristics of the topology.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.18 no.2
• /
• pp.80-85
• /
• 2014

Side jet thruster using nozzle closure separation device provides a solid rocket with a trajectory shift function. Side jet thruster consists of low combustion temperature propellant, neutral type propellant grain and nozzle closure separation device. If a trajectory shift is required, side jet thrust is generated on the rocket by separating some nozzle closures located in the opposite direction to thrust. After completing trajectory shift, the other nozzle closures located in the thrust direction are separated to cease side jet thrust. The operation process is verified through ground static test. The result in this study can be applied to changing rocket trajectory by controlling side jet thrust through nozzle closure separation.

• Journal of Advanced Navigation Technology
• /
• v.19 no.5
• /
• pp.403-410
• /
• 2015

ADS-B can provide high accurate position information and faster update rate than Radar system and it is a technique that can supplement or replace the Radar. Recently ADS-B has been applied to the actual aircraft operation because to increase air transportation traffic and required to high accurate surveillance. In this study, we surveyed analysis of position deviation distribution analysis and received actual ADS-B trajectory data for conformed precise surveillance on the near airport area using ADS-B message. For that, we received the precision instrument approach ADS-B trajectory data using instrument landing system, and can analyse about target deviation distribution on the final approach segment about precision instrument approach. The result of analysis is mean distance of target deviation -0.04 m and standard deviation 6.71 m on between ADS-B target and extended runway centerline. Also that is to conformed the ADS-B message trajectory available to provide relatively exact surveillance information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• International Journal of Automotive Technology
• /
• v.5 no.3
• /
• pp.201-208
• /
• 2004

Response characteristics of the CVT system for a parallel hybrid electric vehicle (HEV) are investigated. From the experiment, CVT ratio control algorithm for the optimal engine operation is obtained. To investigate the effect of the CVT system dynamic characteristics on the HEV performance, a hardware in the loop simulation (HILS) is performed. In the HILS, hardwares of the CVT belt-pulley and hydraulic control valves are used. It is found that the engine performance by the open loop CVT ratio control shows some deviation from the OOL in spite of the RCVs open loop control ability. To improve the engine performance, a closed loop control of the CVT ratio is proposed with variable control gains depending on the shift direction and the CVT speed ratio range by considering the nonlinear characteristics of the RCV and CVT belt-pulley dynamics. The HILS results show that the engine performance is improved by the closed loop control showing the operation trajectory close to the OOL.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.249-252
• /
• 2004

The automatic determination of vehicle operation status as well as continuous tracking of vehicle location with intelligent management is one of major elements to achieve the goals. Especially, vehicle operation status can only be analyzed in terms of expert experiences with real-time location data with scheduling information. However the scheduling information of individual vehicle is very difficult to be interpreted immediately because there are hundreds of thousand vehicles are run at the same time in the national wide range workplace. In this paper, we propose the location-based knowledge management system(LKMs) using the active trajectory analysis method with routing and scheduling information to cope with the problems. This system uses an inference technology with dispatching and geographic information to generate the logistics knowledge that can be furnished to the manager in the central vehicle monitoring and controlling center.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1085-1090
• /
• 1989

In this paper, an adaptive control method is presented to guarantee the ultimate boundedness of uncertain systems with partially known uncertainty bounds. This method, with a conventional linear compensator, is used to improve the performance of the trajectory tracking of a robotic manipulator with uncertainties. The proposed method is simulated under several different environments, and its performance is compared with the computed torque method. The simulation results show that the proposed method is well suited for high-performance operation of uncertain robotic systems.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.35-48
• /
• 2018

The study of air defense against North Korean tactical ballistic missiles (TBM) should consider the rapidly changing battlefield environment. The study for target re-designation for intercept missiles enables effective operation of friendly defensive assets as well as responses to dynamic battlefield. The researches that have been conducted so far do not represent real-time dynamic battlefield situation because the hit probability for the TBM, which plays an important role in the decision making process, is fixed. Therefore, this study proposes a target re-designation algorithm that makes decision based on hit probability which considers real-time field environment. The proposed method contains a trajectory prediction model that predicts the expected trajectory of the TBM from the current position and velocity information by using random forest and moving window. The predicted hit probability can be calculated through the trajectory prediction model and the simulator of the intercept missile, and the calculated hit probability becomes the decision criterion of the target re-designation algorithm for the missile. In the experiment, the validity of the methodology used in the TBM trajectory prediction model was verified and the superiority of using the hit probability through the proposed model in the target re-designation decision making process was validated.