• ETRI Journal
• /
• v.43 no.4
• /
• pp.580-593
• /
• 2021

When operating in confined spaces or near obstacles, collision-free path planning is an essential requirement for autonomous exploration in unknown environments. This study presents an autonomous exploration technique using a carefully designed collision-free local planner. Using LiDAR range measurements, a local end-point selection method is designed, and the path is generated from the current position to the selected end-point. The generated path showed the consistent collision-free path in real-time by adopting the Euclidean signed distance field-based grid-search method. The results consistently demonstrated the safety and reliability of the proposed path-planning method. Real-world experiments are conducted in three different mines, demonstrating successful autonomous exploration flights in environment with various structural conditions. The results showed the high capability of the proposed flight autonomy framework for lightweight aerial robot systems. In addition, our drone performed an autonomous mission in the tunnel circuit competition (Phase 1) of the DARPA Subterranean Challenge.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.2
• /
• pp.95-101
• /
• 2018

This paper presents a collision free mobile robot navigation based on the fuzzy inference fusion model in unkonown environments using multi-ultrasonic sensor. Six ultrasonic sensors are used for the collision avoidance approach where CCD camera sensors is used for the trajectory following approach. The fuzzy system is composed of three inputs which are the six distance sensors and the camera, two outputs which are the left and right velocities of the mobile robot's wheels, and three cost functions for the robot's movement, direction, obstacle avoidance, and rotation. For the evaluation of the proposed algorithm, we performed real experiments with mobile robot with ultrasonic sensors. The results show that the proposed algorithm is apt to identify obstacles in unknown environments to guide the robot to the goal location safely.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.3
• /
• pp.191-197
• /
• 2021

This study addresses autonomous ship collision avoidance in narrow channels using curvilinear coordinates. Navigation in narrow channels or fairways is known to be much more difficult and challenging compared with navigation in the open sea. It is not straightforward to apply the existing collision avoidance framework designed for use in the open sea to collision avoidance in narrow channels due to the complexity of the problem. In this study, to generalize the autonomous navigation procedure for collision avoidance in narrow channels, we introduce a curvilinear coordinate system for collision-free path planning using a parametric curve, B-spline. To demonstrate the feasibility of the proposed algorithm, ship traffic simulations were performed and the results are presented.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2001.10a
• /
• pp.65-74
• /
• 2001

The rapid development of computer technology and widely application of artificial intelligent provide technology support for realizing navigation automation on the sea. which has achieved great success in shipping advanced countries like japan, England, America, Germany and also in the developing country, China. However, it still remains in the studying Period up to now in aspects of collision avoidance decision-making mathematical model and reasoning mechanism. In this paper, approaches are proposed to establish the collision avoidance automation system. One of them is based on the former studies to realize automation system by make use of finite state machine theory and following the International regulations for Preventing Collision at Sea, 1972. The others are to establish the new idea about automatic collision avoidance system by taking advantage of the free flight idea, hybrid system, game theory used in air traffic management studies in recent years and the common characteristics in both air and sea traffic management.

• Journal of Advanced Navigation Technology
• /
• v.19 no.5
• /
• pp.379-388
• /
• 2015

In the end of 1990's, future free flight technology had been developed and tested in America and government established the plan for free flight until 2017. Aircraft separation assurance must be secured essentially to avoid collision between aircrafts before Free Flight comes true. Now, Civil aircraft has rules about avoidance activity with traffic collision avoidance system (TCAS) but it can't apply to light aircraft. So there is a need about alternative method to apply light-aircraft because it has space and price problem to use TCAS. In this paper, TCAS algorithm has been modified and verified by simulating with LABVIEW program under ADS-B condition to get miniaturization and weight lighting cheaply. By simulating, collision alert algorithm is analyzed and verified with collision situation proposed by ICAO, and 100% checked for performing the alert announciation on all cases by TCAS standards.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.279-282
• /
• 1996

Collision avoidance is a method to direct a mobile robot without collision when traversing the environment. This kind of navigation is to reach a destination without getting lost. In this paper, we use a genetic algorithm for the path planning and collision avoidance. Genetic algorithm searches for path in the entire, continuous free space and unifies global path planning and local path planning. It is a efficient and effective method when compared with traditional collision avoidance algorithm.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.2
• /
• pp.890-903
• /
• 2017

The problem of determining a smooth and collision-free path with maximum possible speed for a Mobile Robot (MR) which is chasing a moving target in a dynamic environment is addressed in this paper. Genetic Network Programming with Reinforcement Learning (GNP-RL) has several important features over other evolutionary algorithms such as it combines offline and online learning on the one hand, and it combines diversified and intensified search on the other hand, but it was used in solving the problem of MR navigation in static environment only. This paper presents GNP-RL based on predicting collision positions as a first attempt to apply it for MR navigation in dynamic environment. The combination between features of the proposed collision prediction and that of GNP-RL provides safe navigation (effective obstacle avoidance) in dynamic environment, smooth movement, and reducing the obstacle avoidance latency time. Simulation in dynamic environment is used to evaluate the performance of collision prediction based GNP-RL compared with that of two state-of-the art navigation approaches, namely, Q-Learning (QL) and Artificial Potential Field (APF). The simulation results show that the proposed GNP-RL outperforms both QL and APF in terms of smooth movement and safer navigation. In addition, it outperforms APF in terms of preserving maximum possible speed during obstacle avoidance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.2
• /
• pp.211-217
• /
• 2014

This paper addresses an algorithm of path planning for autonomous driving of a ground vehicle in waypoint navigation. The proposed algorithm is flexible in utilization under a large GPS positioning error and generates collision-free multiple paths while pursuing minimum traveling time. An optimal path reduces inefficient steering by minimizing lateral changes in generated waypoints along a path. Simulation results compare the proposed algorithm with the A* algorithm by manipulation of the steering wheel and traveling time, and show that the proposed algorithm realizes real-time obstacle avoidance by quick processing of path generation, and minimum time traveling by producing paths with small lateral changes while overcoming the very irregular positioning error from the GPS.

• Journal of Navigation and Port Research
• /
• v.33 no.9
• /
• pp.603-608
• /
• 2009

In this paper, a 3m-class free running model ship will be introduced with its manoeuvring performance experiments. The results of turning circle test and zig-zag test will be explained. The developed system are equipped with GPS, main control computer, wireless LAN, IMU (Inertial Measurement Unit), self-propulsion propeller and driving rudder. Its motion can be controlled by RC (Radio Control) and wireless LAN from land based center. Automatic navigation is also available by pre-programmed algorithm. The trajectory of navigation can be acquired by GPS and it provides us with important data for ship's motion control experiments. The results of manoeuvring performance experiment have shown that the developed free running model ship can be used to verify the test of turning circle and zig-zag. For next step, other experimental researches such as ship collision avoidance system and automatic berthing can be considered in the future.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.2
• /
• pp.53-65
• /
• 2008

This paper proposes the qualitative method for planning the operation of multi-AUVs with environmental disturbances, which is considered to be a very difficult task. In this paper we use an extension collision map as a collision free motion planner. The tool was originally developed for the multiple ground vehicles with no internal/external disturbance. In order to apply the method to a water environment where there are tides and waves, and currents, we analyze the path deviation error of AUVs caused by external disturbances. And we calculate safety margin for the collision avoidance on the extension collision map. Finally, the simulation result proves that the suggested method in this paper make multi-AUVs navigate to the goal point effectively with no collision among them.