• Journal of Advanced Navigation Technology
• /
• v.17 no.2
• /
• pp.247-254
• /
• 2013

The task of 3D gesture recognition for controlling equipments is highly challenging due to the propagation of 3D smart TV recently. In this paper, the AdaBoost algorithm is applied to 3D gesture recognition by using Kinect sensor. By tracking time interval trajectory of hand, wrist and arm by Kinect, AdaBoost algorithm is used to train and classify 3D gesture. Experimental results demonstrate that the proposed method can successfully extract trained gestures from continuous hand, wrist and arm motion in real time.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.101-106
• /
• 2006

The geoidal undulations are needed for determining the orthometric heights from the Global Positioning System GPS-derived ellipsoidal heights. There are several methods for geoidal undulation determination. The paper presents a method employing a simple architecture Two Layer Multiquadric-Biharmonic Artificial Neural Network (TLMB-ANN) to approximate an area of 4200 square kilometres quasigeoid surface with GPS-levelling data. Hardy’s Multiquadric-Biharmonic functions is used as the hidden layer neurons’ activation function and Levenberg-Marquardt algorithm is used to train the artificial neural network. In numerical examples five surfaces were compared: the gravimetric geometry hybrid quasigeoid, Support Vector Machine (SVM) model, Hybrid Fuzzy Neural Network (HFNN) model, Traditional Three Layer Artificial Neural Network (ANN) with tanh activation function and TLMB-ANN surface approximation. The effectiveness of TLMB-ANN surface approximation depends on the number of control points. If the number of well-distributed control points is sufficiently large, the results are similar with those obtained by gravity and geometry hybrid method. Importantly, TLMB-ANN surface approximation model possesses good extrapolation performance with high precision.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2021.11a
• /
• pp.76-77
• /
• 2021

In line with the development of autonomous ships, it is necessary to train professional ship management supervisors to prepare for the transition to the ship's safety management system. Therefore, this study intends to investigate the capabilities required of ship management supervisors in preparation for introduction to autonomously operated ships for ship management supervisors in the field, and to suggest future capability development plans.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2018.11a
• /
• pp.193-199
• /
• 2018

Due to the rapid development of AI, autonomous vessels will be realized in the near future. However, the curriculum of nautical science in maritime university is not prepared for this trend. In addition, after the expiration of the mandatory boarding period, a number of junior merchant marine officers are leaving offshore jobs to find onshore jobs. This is a comparative analysis of curriculum of nautical science in maritime universities. Since most of seafaring countries ratified STCW 2010, nearly all themaritime universities train their cadets by followings the procedures required by STCW. Therefore, it is necessary to examine the curriculum of these marine universities in oder to confirm the appropriateness of our curriculum of nautical science. This will ultimately be used as a reference for the development of an ideal curriculum to prepare for rapid technological development and to prepare for a job on the ground.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2018.11a
• /
• pp.25-26
• /
• 2018

Virtual training is widely used based on safety and cost efficiency as a way to efficiently train based on virtual reality. In this paper, we propose the implementation and validation evaluation of life safety training, life training in closed area training, initial fire extinguishing training as a virtual training in maritime safety training. Specifically, we discuss how to implement virtual training to meet the goals of each training, and we propose training methods for evaluating trainees' effectiveness when implemented in this manner. The proposed evaluation method can be used as a quantitative evaluation index of the trainee's training assessment of the training and the safety contribution of the training to the evaluation of the training efficienc

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.411-414
• /
• 2003

Particle swarm optimization (PSO) is employed to train fuzzy-neural networks (FNN), which can be employed as an important building block in real life robot systems, controlled by voice-based commands. The FNN is also trained to capture the user spoken directive in the context of the present performance of the robot system. The system has been successfully employed in a real life situation for navigation of a mobile robot.

• Journal of Multimedia Information System
• /
• v.8 no.4
• /
• pp.243-250
• /
• 2021

Instructional contents are used to demonstrate a technical process to teach and walkthrough certain procedures to carry out a task. This type of informational content is widely used for teaching and lectures in form of tutorial videos and training videos. Since there are questions and uncertainties for what could be the killer application for the novel wearables, we propose a self-instruction training application on a smart glass to utilize already-available instruction videos as well as public open data in creative ways. We design and implement a prototype application to help users train by wearing smart glasses specifically designed for two concrete and hand-constrained use cases where the user's hands need to be free to operate. To increase the efficiency and feasibility of the self-instruction training, we contribute to the development of a wearable killer application by integrating a voice-based user interface using speech recognizer, public open data APIs, and timestamp-based procedural content navigation structure into our proof-of-concept application.

• ETRI Journal
• /
• v.45 no.2
• /
• pp.329-337
• /
• 2023

For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.3
• /
• pp.141-151
• /
• 1993

For navigation of a mobile robot, it is one of the essential tasks to find out its current position. Dead reckonining is the most frequently used method to estimate its position. Hpwever conventional dead reckoner is prone to give us false information on the robot position especially when the wheels are slipping. This paper proposes an improved dead reckoning scheme using neural networks. The network detects the instance of wheel slopping and estimates the linear velocity of the wheel; thus it calculates current position and heading angle of a mobile robot. The structure and variables of the nerual network are chosen in consideration of slip motion characteristics. A series of experiments are performed to train the networks and to investigate the performance of the improved dead reckoning system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.624-627
• /
• 2023

Unmanned aerial vehicles are gaining in popularity with the development of science and technology, and are being used for a wide range of purposes, including surveillance, rescue, delivery of goods, and data collection. In particular, the ability to avoid obstacles during navigation without human oversight is one of the essential capabilities that a drone must possess. Many works currently have solved this problem by implementing deep reinforcement learning (DRL) model. The essential core of a DRL model is reward function. Therefore, this paper proposes a new reward function with appropriate action space and employs dueling double deep Q-Networks to train a drone to navigate in indoor environment without collision.