• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.156-161
• /
• 2003

An overview of our approach to autonomous navigation is presented showing how motion information can be integrated into existing navigation schemes. Particular attention is given to our short range motion estimation scheme which utilises a number of unique assumptions regarding the nature of the visual environment allowing a direct fusion of visual and range information. Graduated non-convexity is used to solve the resulting non-convex minimisation problem. Experimental results show the advantages of our fusion technique.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.04a
• /
• pp.43-48
• /
• 2004

RTP that is proposed supplement of real-time services on internet environment, as Real-time Transport Protocol, is the protocol that for the purpose of sending data of stream type. RTP and RTCP(Real-time Transport Control Protocol) basically work at the same time, RTCP serves with state information of network at present. RTP has important properties of a transport protocol that runs on end-to-end systems and provides demultiplexing. It also offer reliability and protocol-defined flow／congestion control that transport protocol like TCP can not provides. In this paper, we look around concept and construction of Differentiated sen1ice tint run on RTP and by setting parameters of packet transfer method be used CBQ(Class-Based Queuing) for packet transfer on Differentiated service, each service queue controls properly through packet scheduling method, such as WRR(Weighted Round Robin) and PRR(Packet-by-packet Round Robin) all service classes do not experience the starvation and confirm the performance through computer simulation to achieve fairly scheduling.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.16 no.6
• /
• pp.719-725
• /
• 2013

In this paper, we propose a local path planning method based on RANGER algorithm and autonomy manager for autonomous navigation of UGV in urban environment. LPP method is designed to generate the local path in sensing area by using lane and curb of pavement and autonomy manager is designed to make a decision which transit the status of LPP component to a proper status for current navigation environment. A field test is conducted with scenarios in real urban environment in which crossroad, crosswalk and pavement are included and the performance of proposed method is validated.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.47-48
• /
• 2015

VTSO make a decision which one will be danger and what to expect ship's actions due to each encountering situation with CPA(Closest Point of Approach) and TCPA(Time to Closest Point of Approach) by monitoring ship's vectors(Course & Speeds) in real-time through the VTS system. This study is the fundamental research for developing algorithm and system that does not decide the collision risk in one's own ship's viewpoints, but it identifies the related ships into danger through the third party(VTS ) in real time.

• Journal of Navigation and Port Research
• /
• v.42 no.6
• /
• pp.395-405
• /
• 2018

Seakeeping safety module in Korean e-Navigation system is one of the ship remote monitoring services that is employed to ensure the safety of ships by monitoring the ship's real time performance and providing a warning in advance when the abnormal conditions are encountered in seakeeping performance. In general, seakeeping performance has been evaluated by simulating ship motion analysis under specific conditions for its design. However, due to restriction of computation time, it is not realistic to perform simulations to evaluate seakeeping performance under real-time operation conditions. This study aims to introduce a reasonable and faster method to predict a ship's roll motion which is one of the factors used to evaluate a ship's seakeeping performance by using a machine learning-based surrogate model. Through the application of various learning techniques and sampling conditions on training data, it was observed that the difference of roll motion between a given surrogate model and motion analysis was within 1%. Therefore, it can be concluded that this method can be useful to evaluate the seakeeping performance of a ship in real-time operation.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.4
• /
• pp.399-406
• /
• 2020

In this paper, we propose a time-varying proportional navigation guidance law that determines the proportional navigation gain in real-time according to the operating situation. When intercepting a target, an unidentified evasion strategy causes a loss of optimality. To compensate for this problem, proper proportional navigation gain is derived at every time step by solving an optimal control problem with the inferred evader's strategy. Recently, deep reinforcement learning algorithms are introduced to deal with complex optimal control problem efficiently. We adapt the actor-critic method to build a proportional navigation gain network and the network is trained by the Proximal Policy Optimization(PPO) algorithm to learn an evasion strategy of the target. Numerical experiments show the effectiveness and optimality of the proposed method.

• Journal of Navigation and Port Research
• /
• v.32 no.3
• /
• pp.245-250
• /
• 2008

Recently the numerical prediction technique is applied to many fields, because numerical models are developed so much for last decades. The real-time ocean prediction system is one of them and is capable of providing the real-time marine information for users to promote the safety af maritime traffic and preservation of marine resources. The system is composed of observing system, data distribution system and modelling system. In this study authors develop the modelling system and show the results as preliminary study for establishing the real-time ocean prediction system in Busan port. The system test is performed only for M2 tidal modelling due to the lack qf observation data, thus a full-scale test is required in future if enough data are provided Also observing system and data distribution system will be constructed continuously in future, then service for real-time data for users will be initiated.

• Journal of Positioning, Navigation, and Timing
• /
• v.8 no.4
• /
• pp.209-214
• /
• 2019

Precise point positioning (PPP) requires precise orbit and clock products. International GNSS service (IGS) real-time service (RTS) data can be used in real-time for PPP, but it may not be possible to receive these corrections for a short time due to internet or hardware failure. In addition, the time required for IGS to combine RTS data from each analysis center results in a delay of about 30 seconds for the RTS data. Short-term orbit prediction can be possible because it includes the rate of correction, but the clock correction only provides bias. Thus, a short-term prediction model is needed to preidict RTS clock corrections. In this paper, we used a long short-term memory (LSTM) network to predict RTS clock correction for three minutes. The prediction accuracy of the LSTM was compared with that of the polynomial model. After applying the predicted clock corrections to the broadcast ephemeris, we performed PPP and analyzed the positioning accuracy. The LSTM network predicted the clock correction within 2 cm error, and the PPP accuracy is almost the same as received RTS data.

• Journal of Advanced Navigation Technology
• /
• v.19 no.4
• /
• pp.305-310
• /
• 2015

A controlling system for airport refueling facilities is connected to sensors which collect various informations. Informations which are transmitted at a high speed in various sensors are processed by a dedicated software in the controlling system. The problems of system maintenance and network traffic caused by the use of dedicated software reduce the efficiency of the system operation. Therefore, a web-based system that can be accessed using the Internet environment is required. In this paper, we propose a system showing web-based real-time informations. To do this, we change the function of the communication by each sensor to a facade structure, and design a system for transferring web-based real-time informations. Also we propose data-driven infographics for displaying the real-time big data information at a high speed on the web. Finally, we compare and analyse the proposed system between the existing system and show that our system can effectively display the real-time information on the web.