• Journal of Auto-vehicle Safety Association
• /
• v.11 no.4
• /
• pp.39-49
• /
• 2019

Autonomous vehicle is a car which drives itself without any human interaction. SAE provides technical definitions for autonomous and international standards for test evaluation. Accordingly, automobile industry is actively researching development and evaluation of various ADAS (Advanced Driver Assistance Systems), : representative technology of autonomous technology. Recently, ADAS is in the commercialization level such as ACC, LKAS, AEB, and HDA etc. And it also has issues about safety evaluation. The purpose of HDA in ADAS is reduced the driving load on highway. It has a function which can maintain lane keeping and control distance from forward vehicle. This function is evaluated to be useful for accident prevention. Therefore, this paper proposes the safety evaluation scenario of HDA, considering the domestic highway design criteria and the situation that may arise on the actual highway. We compared and analyzed the data acquired through simulation and actual vehicle test. And verified the reliability of the proposed safety evaluation scenario. The verified result is expected safety evaluation of HDA is possible even under the bad condition, which cannot be tested.

• Journal of Auto-vehicle Safety Association
• /
• v.11 no.3
• /
• pp.30-36
• /
• 2019

This paper suggests a car-following algorithm for urban environment, with multiple target candidates. Until now, advanced driver assistant systems (ADASs) and self-driving technologies have been researched to cope with diverse possible scenarios. Among them, car-following driving has been formed the groundwork of autonomous vehicle for its integrity and flexibility to other modes such as smart cruise system (SCC) and platooning. Although the field has a rich history, most researches has been focused on the shape of target trajectory, such as the order of interpolated polynomial, in simple single-lane situation. However, to introduce the car-following mode in urban environment, realistic situation should be reflected: multi-lane road, target's unstable driving tendency, obstacles. Therefore, the suggested car-following system includes both in-lane preceding vehicle and other factors such as side-lane targets. The algorithm is comprised of three parts: path candidate generation and optimal trajectory selection. In the first part, initial guesses of desired paths are calculated as polynomial function connecting host vehicle's state and vicinal vehicle's predicted future states. In the second part, final target trajectory is selected using quadratic cost function reflecting safeness, control input efficiency, and initial objective such as velocity. Finally, adjusted path and control input are calculated using model predictive control (MPC). The suggested algorithm's performance is verified using off-line simulation using Matlab; the results shows reasonable car-following motion planning.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.4
• /
• pp.27-34
• /
• 2022

In the development of automated driving, interest in the interior parts of vehicle is to become more significant in terms of the occupant safety and comfort. This study proposed an optimal design of front seat according to the design requirements for frame stiffness and seat comfort. For the seat comfort, the appropriate foam thickness was obtained using the structural analysis under reclined occupant loadings. While the strength and stiffness analyses were performed to evaluate the seat frame structure. Topology optimization was carried out based on the simulation results and the derived optimal model and baseline seat design was updated. The conceptual seat design for the autonomous vehicle in this study showed that the model development process is appropriate for the design parameters in both frame stiffness and seat comfort.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.222-234
• /
• 2020

Autonomous vehicles are equipped with a wide rage of sensors such as GPS, RADAR, LIDAR, camera, IMU, etc. and are driven by recognizing and judging various transportation systems at intersections in the city. The accident ratio of the intersection of the autonomous vehicles is 88% of all accidents due to the limitation of prediction and judgment of an area outside the sensing distance. Not only research on non-signalized intersection collision avoidance strategies through V2V and V2I is underway, but also research on safe intersection driving in failure situations is underway, but verification and fragments through simple intersection scenarios Only typical V2V failures are presented. In this paper, we analyzed the architecture of the V2V module, analyzed the causal factors for each V2V module, and defined the failure mode. We presented intersection scenarios for various road conditions and traffic volumes. we used the ISO-26262 Part3 Process and performed HARA (Hazard Analysis and Risk Assessment) to analyze the risk of autonomous vehicle based on the simulation. We presented ASIL, which is the result of risk analysis, proposed a monitoring concept for each component of the V2V module, and presented monitoring coverage.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.6
• /
• pp.614-619
• /
• 2015

In this study, a dynamics model was developed to predict the motion performance of an Autonomous Underwater Vehicle (AUV). The dynamics model includes basic dynamic state variables of the hull and force terms to determine the motion of the AUV. The affecting terms for the forces are hydrostatic force, added mass, hydrodynamic damping, lift and drag forces. The force terms can be calculated using analytical and Computational Fluid Dynamics methods. For the underwater motion simulation, a simple PD controller was used. Also, the AUV was tested in a water tank and near sea for the partial verification of the fluid drag force coefficients and way-point tracking motions.

• Journal of Ocean Engineering and Technology
• /
• v.22 no.4
• /
• pp.106-113
• /
• 2008

This paper presents an underwater navigation system based on range measurements from a known reference station fixed on the sea bottom or floated at surface with a buoy, for which the system is extended to 3-dimensional coordinates. We formulated a state equation in polar coordinates and constituted an extended Kalman filter for discrete-time implementation of the navigation algorithm. The autonomous underwater vehicle, lSiMl, cruising with a constant speed can estimate its trajectory using just range measurements and additional depth, heading and pitch sensors. Simulation studies were performed to evaluate the underwater navigation of the maneuvering AUV with range measurements. We modulated the sample rate of range measurements to evaluate the effect of the update rate, and changed the initial position error of the AUV to check the robustness to estimation errors. Simulation results illustrates that the extended navigation system provides convergence of the state estimates. The navigation system was conditionally stable when it had initial position errors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.251-257
• /
• 2022

Self-driving vehicles are a type of smart vehicle with the help of ICT technology, which means a vehicle that operates without the intervention of a driver.Vehicles with vehicle safety communication technology (V2X) applied use information detected from various sensors or other vehicles/infrastructures to enable the smart vehicle to accurately and quickly predict the driver's potential danger situation, contributing to more stable autonomous driving. In this paper, among V2X communication technologies, a vehicle-to-vehicle communication (V2V) simulation communication technology is used to present a scenario for preventing collisions in autonomous vehicles. A vehicle collision prevention system based on V2V simulated communication was implemented and the suggested collision prevention application scenario was demonstrated. The suggested collision prevention utilization scenario can be considered as one application case of V2V communication technologies that are currently being developed/applied.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• 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%.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.3
• /
• pp.132-138
• /
• 2011

This paper presents an intelligent control approach for lateral position control of an autonomous four wheel steered snowplowing robotic vehicle. The vehicle is built for removing snow on the highway. Dynamics of the vehicle is derived and linearized for LQR control. Lateral position is controlled by the LQR method first, then the neural network control technique is introduced to improve tracking performances under the presence of load. The feasibility of using four wheel steering control is investigated by simulation studies of lateral position tracking of the Ford F-250 truck model. Performances of a LQR control method and a neural network control method under virtual snowplowing situation are compared.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.758-771
• /
• 2021

This paper presents a novel control scheme for the three-dimensional (3D) path following of underactuated Autonomous Underwater Vehicle (AUVs) subject to unknown internal and external disturbances, in term of the time scale decomposition method. As illustration, two-time scale motions are first artificially forced into the closed-loop control system, by appropriately selecting the control gain of the integrator. Using the singular perturbation theory, the integrator is considered as a fast dynamical control law that designed to shape the space configuration of fast variable. And then the stabilizing controller is designed in the reduced model independently, based on the time scale decomposition method, leading to a relatively simple control law. The stability of the resultant closed-loop system is demonstrated by constructing a composite Lyapunov function. Finally, simulation results are provided to prove the efficacy of the proposed controller for path following of underactuated AUVs under internal and external disturbances.