• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.11a
• /
• pp.34-36
• /
• 2011

In recent years, shipping at the sea has been rapidly grown in marine nations and vessel's collisions are increasing as well. The collision avoidance is one of issues maritime safety. To reduce vessels' collisions, the fuzzy inference system is one of popular algorithms for collision avoidance. In this paper we aim to implement Matlab. Fuzzy logic toolbox software for collision avoidance algorithm. For this we used an original Matlab fuzzy logic toolbox and customized the toolbox for the collision avoidance algorithm.

• Journal of Navigation and Port Research
• /
• v.32 no.6
• /
• pp.447-452
• /
• 2008

In this paper, the automatic depth control system and the collision avoidance system of the Manta UUV have been established in vertical and horizontal plane. The PID control theory and the Fuzzy theory are adopted in this system. The 6-DOF MMG model had been established by theoretical calculations and captive model test results. The depth control simulation results have been fully presented. The collision risks of the UUV had calculated by the fuzzy theory with the virtual sonar system. Finally, the automatic depth control system and the collision avoidance simulation system of Manta UUV have been fully developed and simulated.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2001.10a
• /
• pp.81-87
• /
• 2001

In this article, we have done some analysis about the collision-avoidance specialty of “pressing complexion” and “pressing danger”in the meet process of two boats, and offered a mathematic model of differential coefficient countermeasure decision for collision-avoidance, which adapt to the right complexion. The basal idea is, in the right condition whatever do the coming boat do, and our boat will always adept dynamic, continuous and the best countermeasure. When both the controlling capabilities of two boats have advantage and inferior position, we can working-out with the qualitative differential coefficient countermeasure.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.393-397
• /
• 2006

Significant increase of container flows in marine terminals requires more efficient automatic port systems. This paper presents a novel routing and collision avoidance algorithm of linear motor based shuttle cars using dynamic programming (DP). The proposed DP is accomplished online for determining optimal paths for each shuttle car. We apply our algorithm to Agile port terminal in USA.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.4
• /
• pp.57-61
• /
• 2002

We design Collision Avoidance System using model vehicle. The purpose of this system(Collision Avoidance System) is to maintain continuously constant distance between a forward running vehicle and a following automatic guided vehicle(AGV). For this system, we design modeling of vehicle and observe this through simulation. By sing super sonic sensors to measure the distance between vehicles and controller using 80c196kc for changing velocity of motor, we design Collision Avoidance System as maintaining continuously constant distance between vehicles.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.1
• /
• pp.58-65
• /
• 2019

The stability, reliability and efficiency of a smart ship are important issues as the interest in an autonomous ship has recently been high. An automatic collision avoidance system is an essential function of an autonomous ship. This system detects the possibility of collision and automatically takes avoidance actions in consideration of economy and safety. In order to construct an automatic collision avoidance system using reinforcement learning, in this work, the sequential decision problem of ship collision is mathematically formulated through a Markov Decision Process (MDP). A reinforcement learning environment is constructed based on the ship maneuvering equations, and then the three key components (state, action, and reward) of MDP are defined. The state uses parameters of the relationship between own-ship and target-ship, the action is the vertical distance away from the target course, and the reward is defined as a function considering safety and economics. In order to solve the sequential decision problem, the Deep Deterministic Policy Gradient (DDPG) algorithm which can express continuous action space and search an optimal action policy is utilized. The collision avoidance system is then tested assuming the $90^{\circ}$intersection encounter situation and yields a satisfactory result.

• Journal of Navigation and Port Research
• /
• v.26 no.1
• /
• pp.8-14
• /
• 2002

The collisions of vessel at sea show high among the whole marine accidents. Especially, the accidents of fishing vessels take the largest portion of the collisions. Therefore, a technique to reduce these accidents should be developed. The automatic control for avoiding collision suggested in this study consists of two steps. The first is recognizing collision risk with fuzzy Theory and the other is maneuvering the model ship on the basis of collision risk calculated from the first step. The information form the position and estimated time of collision point(DCPA and TCPA) is used to assess the collision risk. To verify this system, a fishing vessel was simulated according to MMG mathematical model. The simulations result shows quite good application in avoiding the collision of ship.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.2
• /
• pp.54-60
• /
• 2018

In this paper, we propose an efficient automatic control method for the collision avoidance of drones. In general, the drones are controlled by transmitting to the flight control (FC) module the received PWM signals transmitted from a RC controller which transduce movements of the knob into PWM signal. We implemented the collision avoidance module in-between receiver and FC module to monitor and change the throttle, pitch and roll control signals to avoid drone collision. In order to avoid the collision, a LiDAR distance sensor and a servo-motor are installed and periodically measure the obstacle distance within -45 degrees from 45 degrees in flight direction. If the collision is predicted, the received PWM signal is changed and transmitted to the FC module to prevent the collision. We applied our proposed method to a hexacopter and the experimental results show that the safety is improved because it can prevent the collision caused by the inadvertency or inexperienced maneuver.

• Journal of Korea Ship Safrty Technology Authority
• /
• s.38
• /
• pp.69-77
• /
• 2015

If we don't know the intention of altering course of a target ship when being in a head-on or a crossing situation, we may be confused about our decision making to change our course for collision avoidance and be in a danger of collision. In order to solve these problems, we need to develop an automatic detection system on altering course of a target ship for efficient collision avoidance. In this paper, we proposed an early detection system on altering course of a target ship using the steering wheel signal. This system will contribute to the reduction of collision accidents and also be used to the VTS system and the analysis of marine accidents.

• Journal of Korea Ship Safrty Technology Authority
• /
• s.36
• /
• pp.71-78
• /
• 2014

If we don't know the intention of altering course of a target ship when being in a head-on or a crossing situation, we may be confused about our decision making to change our course for collision avoidance and be in a danger of collision. In order to solve these problems, we need to develop an automatic detection system on altering course of a target ship for efficient collision avoidance. In this paper, we proposed an early detection system on altering course of a target ship using the steering wheel signal. This system will contribute to the reduction of collision accidents and also be used to the VTS system and the analysis of marine accidents.