• International Journal of Ocean System Engineering
• /
• v.1 no.3
• /
• pp.120-135
• /
• 2011

This paper proposes a model based trajectory tracking control scheme for under-actuated underwater robotic vehicles. The difficulty in stabilizing a non-linear system using smooth static state feedback law means that the design of a feedback controller for an under-actuated system is somewhat challenging. A necessary condition for the asymptotic stability of an under-actuated vehicle about a single equilibrium is that its gravitational field has nonzero elements corresponding to non-actuated dynamics. To overcome this condition, we propose a continuous time-varying control law based on the direct estimation of vehicle dynamic variables such as inertia, damping and Coriolis & centripetal terms. This can work satisfactorily under commonly encountered uncertainties such as an ocean current and parameter variations. The proposed control law cancels the non-linearities in the vehicle dynamics by introducing non-linear elements in the input side. Knowledge of the bounds on uncertain terms is not required and it is conceptually simple and easy to implement. The controller parameter values are designed using the Taguchi robust design approach and the control law is verified analytically to be robust under uncertainties, including external disturbances and current. A comparison of the controller performance with that of a linear proportional-integral-derivative (PID) controller and sliding mode controller are also provided.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.12
• /
• pp.1046-1052
• /
• 2016

For the safe driving of autonomous vehicles, accurate position estimation is required. Generally, position error must be less than 1m because of lane keeping. However, GPS positioning error is more than 1m. Therefore, we must correct this error and a map matching algorithm is generally used. Especially, road marking intensity map have been used in many studies. In previous work, 3D LIDAR with many vertical layers was used to generate a local intensity map. Because it can be obtained sufficient longitudinal information for map matching. However, it is expensive and sufficient road marking information cannot be obtained in rush hour situations. In this paper, we propose a localization algorithm using an accumulated intensity local map. An accumulated intensity local map can be generated with sufficient longitudinal information using 3D LIDAR with a few vertical layers. Using this algorithm, we can also obtain sufficient intensity information in rush hour situations. Thus, it is possible to increase the reliability of the map matching and get accurate position estimation result. In the experimental result, the lateral RMS position error is about 0.12m and the longitudinal RMS error is about 0.19m.

• International Journal of Ocean System Engineering
• /
• v.3 no.2
• /
• pp.50-60
• /
• 2013

This paper presents a novel approach to the design of an adaptive fuzzy sliding mode controller for depth control of an autonomous underwater vehicle (AUV). So far, AUV's dynamics are highly nonlinear and the hydrodynamic coefficients of the vehicles are difficult to estimate, because of the variations of these coefficients with different operating conditions. These kinds of difficulties cause modeling inaccuracies of AUV's dynamics. Hence, we propose an adaptive fuzzy sliding mode control with novel fuzzy adaptation technique for regulating vertical positioning in presence of parametric uncertainty and disturbances. In this approach, two fuzzy approximator are employed in such a way that slope of the linear sliding surface is updated by first fuzzy approximator, to shape tracking error dynamics in the sliding regime, while second fuzzy approximator change the supports of the output fuzzy membership function in the defuzzification inference module of fuzzy sliding mode control (FSMC) algorithm. Simulation results shows that, the reaching time and tracking error in the approaching phase can be significantly reduced with chattering problem can also be eliminated. The effectiveness of proposed control strategy and its advantages are indicated in comparison with conventional sliding mode control FSMC technique.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.745-757
• /
• 2019

Road surface deteriorations such as potholes have caused motorists heavy monetary damages every year. However, effective road condition monitoring has been a continuing challenge to road owners. Depth cameras have a small field of view and can be easily affected by vehicle bouncing. Traditional image processing methods based on algorithms such as segmentation cannot adapt to varying environmental and camera scenarios. In recent years, novel object detection methods based on deep learning algorithms have produced good results in detecting typical objects, such as faces, vehicles, structures and more, even in scenarios with changing object distances, camera angles, lighting conditions, etc. Therefore, in this study, a Deep Learning Pothole Detector (DLPD) based on the deep region-based convolutional neural network is proposed for autonomous detection of potholes from images. About 900 images with potholes and road surface conditions are collected and divided into training and testing data. Parameters of the network in the DLPD are calibrated based on sensitivity tests. Then, the calibrated DLPD is trained by the training data and applied to the 215 testing images to evaluate its performance. It is demonstrated that potholes can be automatically detected with high average precision over 93%. Potholes can be differentiated from manholes by training and applying a manhole-pothole classifier which is constructed using the convolutional neural network layers in DLPD. Repeated detection of the same potholes can be prevented through feature matching of the newly detected pothole with previously detected potholes within a small region.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.5
• /
• pp.547-553
• /
• 2021

Dynamic object recognition is an important task for autonomous vehicles. Since dynamic objects exhibit a higher collision risk than static objects, our own trajectories should be planned to match the future state of moving elements in the scene. Time information such as optical flow can be used to recognize movement. Existing optical flow calculations are based only on camera sensors and are prone to misunderstanding in low light conditions. In this regard, to improve recognition performance in low-light environments, we applied a normalization filter and a correction function for Gamma Value to the input images. The low light quality improvement algorithm can be applied to confirm the more accurate detection of Object's Bounding Box for the vehicle. It was confirmed that there is an important in object recognition through image prepocessing and deep learning using YOLO.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.169-177
• /
• 2021

Recently, the use of electric and electronic control systems is increasing in the automobile industry. This increase in the electric and electronic control system greatly increases the complexity of designing a vehicle, which leads to an increase in the malfunction of the system, and a safety problem due to the malfunction is becoming an issue. Based on IEC 61508 relating to the functional safety of electrical/electronic/programmable electronics, the ISO 26262 standard specific to the automotive sector was first established in 2011, and a revision was published in 2018. Malfunctions due to system failure are covered by ISO 26262, but ISO/PAS 21448 is proposed to deal with unintended malfunctions caused by changes in the surrounding environment. ISO 26262 sets out safety-related requirements for the entire life cycle. Functional safety analysis includes FTA (Fault Tree Analysis), FMEA (Failure Mode and Effect Analysis), and HAZOP (Hazard and Operability). These analysis have limitations in dealing with failures or errors caused by complex interrelationships because it is assumed that a failure or error affecting the risk occurs by a specific component. In order to overcome this limitation, it is necessary to apply the STPA (System Theoretic Process Analysis) technique.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.65-70
• /
• 2022

Lane change in urban environments is a challenge for both human-driving and automated driving due to their complexity and non-linearity. With the recent development of deep-learning, the use of the RNN network, which uses time series data, has become the mainstream in this field. Many researches using RNN show high accuracy in highway environments, but still do not for urban environments where the surrounding situation is complex and rapidly changing. Therefore, this paper proposes a lane change possibility decision network by adopting Attention layer, which is an SOTA in the field of seq2seq. By weighting each time step within a given time horizon, the context of the road situation is more human-like. A total 7D vectors of x, y distances and longitudinal relative speed of side front and rear vehicles, and longitudinal speed of ego vehicle were used as input. A total 5,614 expert data of 4,098 yield cases and 1,516 non-yield cases were used for training, and the performance of this network was tested through 1,817 data. Our network achieves 99.641% of test accuracy, which is about 4% higher than a network using only LSTM in an urban environment. Furthermore, it shows robust behavior to false-positive or true-negative objects.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.1
• /
• pp.171-176
• /
• 2023

What we have in common worldwide today is economic difficulties due to high inflation and uncertainty in the financial industry. The root cause of this is the war between Russia and Ukraine. The war between Russia and Ukraine is not simply a war between two countries. The United States and the European Union are providing military aid such as missiles to Ukraine, and Russia is attacking Ukraine by introducing UAVs (unmanned aerial vehicles) from Iran. A prominent weapon in this Russia-Ukraine war is the UAVs used in Russia. It is predicted that the form of war using UAVs will gradually expand in the future based on stealth. In addition, UAVs will continue to be used due to the fact that they can cause serious damage to the other country without harming their own lives, and because they have good cost-effectiveness. In this study, UAVs based on autonomous driving were studied. The target countries of the study include the United States, the European Union, China, and Iran, and the UAVs used in these countries have characteristics that can represent the world. In this study, the main specifications of major UAVs in use in major countries were investigated. In addition, the future technology and development direction were described through specifications and characteristics of UAVs currently in operation in major countries.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.79-91
• /
• 2024

Large warehouses are building automation systems to increase efficiency. However, small warehouses, military bases, and local stores are unable to introduce automated logistics systems due to lack of space and budget, and are handling tasks manually, failing to improve efficiency. To solve this problem, this study designed small loading and unloading equipment that can be mounted on transportation vehicles. The equipment can be controlled remotely and is automatically controlled from the point where pallets loaded with cargo are visible using real-time video from an attached camera. Cargo recognition and control command generation for automatic control are achieved through a newly designed deep learning model. This model is designed to be optimized for loading and unloading equipment and mission environments based on the YOLOv3 structure. The trained model recognized 10 types of palettes with different shapes and colors with an average accuracy of 100% and estimated the state with an accuracy of 99.47%. In addition, control commands were created to insert forks into pallets without failure in 14 scenarios assuming actual loading and unloading situations.

• Journal of the Society of Naval Architects of Korea
• /
• v.61 no.1
• /
• pp.29-43
• /
• 2024

The present study concerns a feasibility study for applying principal component analysis to ship dynamics in maneuver. Using the four degrees of freedom standard modular model for ship dynamics maneuver simulations of large angle zigzag tests with rudder deflection angle variations are conducted. The datasets of ship motion, hydrodynamic force, and moment during the maneuver are acquired to identify the principal modes. The covariance matrix of obtained ship dynamics variables shows a strong linear correlation between the motion, hydrodynamic force, and moment, except the surge force. Four eigenvectors of the covariance matrix are selected as the principal modes of ship dynamics. Using the principal modes, ship motion in turning circle and zigzag tests is reconstructed, showing good agreement with the original data.