• Journal of Navigation and Port Research
• /
• v.43 no.6
• /
• pp.377-383
• /
• 2019

Naval ships that are navigating always have the possibility of colliding, but there is no clear maneuvering procedure for collision avoidance, and there is a tendency to depend entirely on the intuitive judgment of the Officer Of Watch (OOW). In this study, we conducted a questionnaire survey when and how to avoid collision for the OOW in a Constant Bearing, Decreasing Range (CBDR) situation wherein the naval ships encountered obstacles. Using the results of the questionnaire survey, we analyzed the CBDR situation of encountering obstacles, and how to avoid collision in day/night. The most difficult to maneuver areas were Pyeongtaek, Mokpo, and occurred mainly in narrow channels. The frequency appeared on average about once every four hours, and there were more of a large number of ships encountering situations than the 1:1 situation. The method of check of collision course confirmation was more reliable with the eye confirmation results, and priority was given to distance at closest point of approach (DCPA) and time at closest point of approach (TCPA). There was not a difference in DCPA between the give-way ship and stand-on ship, but a difference between day and night. Also, most navigators prefer to use maneuvering & shifting when avoiding collisions, and steering is 10-15°, shifting ±5knots, and the drift course was direction added stern of the obstacles to the direction of it. These results will facilitate in providing officers with standards for collision avoidance, and also apply to the development of AI and big data based unmanned ship collision avoidance algorithms.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.91-99
• /
• 2024

Collision avoidance system is important to improve the robustness and functional safety of autonomous vehicles. This paper proposes an object-level distance estimation method to develop a collision avoidance system, and it is applied to golfcarts utilized in country club environments. To improve the detection accuracy, we continually trained an object detection model based on pseudo labels generated by a pre-trained detector. Moreover, we propose object-aware depth estimation (OADE) method which trains a depth model focusing on object regions. In the OADE algorithm, we generated dense depth information for object regions by utilizing detection results and sparse LiDAR points, and it is referred to as object-aware LiDAR projection (OALP). By using the OALP maps, a depth estimation model was trained by backpropagating more gradients of the loss on object regions. Experiments were conducted on our custom dataset, which was collected for the travel distance of 22 km on 54 holes in three country clubs under various weather conditions. The precision and recall rate were respectively improved from 70.5% and 49.1% to 95.3% and 92.1% after the continual learning with pseudo labels. Moreover, the OADE algorithm reduces the absolute relative error from 4.76% to 4.27% for estimating distances to obstacles.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.12
• /
• pp.583-595
• /
• 2002

Homing operation can be defined as a series of actions which are necessary for a mobile robot to move from the current position with any arbitrary orientation to a desired position with a specified orientation, while avoiding possible obstacles. In this paper, a homing and obstacle avoidance algorithm for nonholonomic mobile robots is proposed. The proposed algorithm consists of a local goal generator, a discrete state controller, and local path tracking controller based on Aicardi's path following algorithm. In the discrete state controller, 4 states are defined according to the environmental conditions and 4 desired high-level command for the states are given as follows: avoid, wander, home and homing zones. The proposed local goal generator is designed to generate the desired local path by using weighted distance transforms which are newly made to satisfy the nonholonomic constraints of mobile robots. Here, subgoals are also found as vertices of the desired local path. To demonstrate result effectiveness and applicability of the proposed algorithm, computer simulations are illustrated and experimental results for a real mobile robot system are also provided.

• International Journal of Automotive Technology
• /
• v.8 no.4
• /
• pp.493-504
• /
• 2007

This paper proposes a stereo vision-based forward obstacle detection and distance measurement method. In general, stereo vision-based obstacle detection methods in automotive applications can be classified into two categories: IPM (Inverse Perspective Mapping)-based and disparity histogram-based. The existing disparity histogram-based method was developed for stop-and-go applications. The proposed method extends the scope of the disparity histogram-based method to highway applications by 1) replacing the fixed rectangular ROI (Region Of Interest) with the traveling lane-based ROI, and 2) replacing the peak detection with a constant threshold with peak detection using the threshold-line and peakness evaluation. In order to increase the true positive rate while decreasing the false positive rate, multiple candidate peaks were generated and then verified by the edge feature correlation method. By testing the proposed method with images captured on the highway, it was shown that the proposed method was able to overcome problems in previous implementations while being applied successfully to highway collision warning/avoidance conditions, In addition, comparisons with laser radar showed that vision sensors with a wider FOV (Field Of View) provided faster responses to cutting-in vehicles. Finally, we integrated the proposed method into a longitudinal collision avoidance system. Experimental results showed that activated braking by risk assessment using the state of the ego-vehicle and measuring the distance to upcoming obstacles could successfully prevent collisions.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.10
• /
• pp.703-713
• /
• 2004

This paper presents the new obstacle avoidance method that is composed of vision and sonar sensors, also a navigation algorithm is proposed. Sonar sensors provide poor information because the angular resolution of each sonar sensor is not exact. So they are not suitable to detect relative direction of obstacles. In addition, it is not easy to detect the obstacle by vision sensors because of an image disturbance. In This paper, the new obstacle direction measurement method that is composed of sonar sensors for exact distance information and vision sensors for abundance information. The modified splitting/merging algorithm is proposed, and it is robuster for an image disturbance than the edge detecting algorithm, and it is efficient for grouping of the obstacle. In order to verify our proposed algorithm, we compare the proposed algorithm with the edge detecting algorithm via experiments. The direction of obstacle and the relative distance are used for the inputs of the fuzzy controller. We design the angular velocity controllers for obstacle avoidance and for navigation to center in corridor, respectively. In order to verify stability and effectiveness of our proposed method, it is apply to a vision and sonar based mobile robot navigation system.

• Journal of KIISE:Information Networking
• /
• v.37 no.2
• /
• pp.157-161
• /
• 2010

Vehicular Ad-hoc NETworks (VANETs) suffer from frequent network disconnections due to obstacles such as buildings even in urban environments with high density of traffic. Thus, in this paper, we propose a routing algorithm that finds optimal end-to-end paths in terms of both traffic density and distance in the urban VANET and selects the next hop with the minimum distance, while maintaining the minimum hop counts over the path. The simulation results show that the proposed algorithm achieves higher throughput and smaller end-to-end delay than Greedy Perimeter Stateless Routing (GPSR) with message carrying.

• Journal of Mechanical Science and Technology
• /
• v.18 no.1
• /
• pp.92-105
• /
• 2004

A new algorithm for planning a collision-free path based on algebraic curve is developed and the concept of collision-free Path Space (PS) is introduced. This paper presents a Geometry Mapping (GM) based on two straight curves in which the intermediate connection point is organized in elliptic locus ($\delta$, $\theta$). The GM produces two-dimensional PS that is used to create the shortest collision-free path. The elliptic locus of intermediate connection point has a special property in that the total distance between the focus points through a point on ellipse is the same regardless of the location of the intermediate connection point on the ellipse. Since the radial distance, a, represents the total length of the path, the collision-free path can be found as the GM proceeds from $\delta$=0 (the direct path) to $\delta$=$\delta$$\_$max/(the longest path) resulting in the minimum time search. The GM of elliptic workspace (EWS) requires calculation of interference in circumferential direction only. The procedure for GM includes categorization of obstacles to .educe necessary calculation. A GM based on rectangular workspace (RWS) using Cartesian coordinate is also considered to show yet another possible GM. The transformations of PS among Circular Workspace Geometry Mapping (CWS GM) , Elliptic Workspace Geometry Mapping (EWS GM) , and Rectangular Workspace Geometry Mapping (RWS GM), are also considered. The simulations for the EWS GM on various computer systems are carried out to measure performance of algorithm and the results are presented.

• Journal of Advanced Navigation Technology
• /
• v.24 no.3
• /
• pp.192-197
• /
• 2020

Recently, the technologies related to autonomous drive has studying the goal for safe operation and prevent accidents of vehicles. There is radar and camera technologies has used to detect obstacles in these autonomous vehicle research. Now a day, the method for using LiDAR sensor has considering to detect nearby objects and accurately measure the separation distance in the autonomous navigation. It is calculates the distance by recognizing the time differences between the reflected beams and it allows precise distance measurements. But it also has the disadvantage that the recognition rate of object in the atmospheric environment can be reduced. In this paper, point cloud data by triangular functions and Line Regression model are used to implement measurement algorithm, that has improved detecting objects in real time and reduce the error of measuring separation distances based on improved reliability of raw data from LiDAR sensor. It has verified that the range of object detection errors can be improved by using the Python imaging library.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.3
• /
• pp.39-46
• /
• 2014

Network RTK positioning, one of GNSS positioning systems, is currently very popular due to its easy operation and low cost. However, the network RTK positioning unquestioningly accepts observation result acquired with an ambiguity fixed-solution regardless of different field conditions and situations, and then it is applied to the practice. This paper, therefore, has investigated the effects of field conditions obtained network RTK survey data for the area with obstacles on the variation of positioning accuracy. Being explained in detail, after conducting survey by GPS-only positioning and combined GPS/GLONASS observations giving changes to the distance from obstacles and elevation angles, and then accuracy results of each positioning method were compared each other. As a result, while GPS-only point positioning method showed more stable results than combined GPS/GLONASS method in the areas with no obstacles, combined method gave better result than GPS-only for the areas with presence of obstacles. Based on the results of this experiment, when the further study is conducted with a variety of different field conditions affecting the survey accuracy, it can be expected that the accuracy of network RTK survey method would become to more popular.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.23 no.3
• /
• pp.250-257
• /
• 2017

This paper investigates minimum safe distances relative to a ship's four cardinal sides, as perceived by Filipino navigators when encountering dangerous elements and in adverse weather conditions when maneuvering in and around harbors. It uses a descriptive research method in the form of a questionnaire survey for experienced Filipino navigators of various ranks. During the course of research, 71 responses were colleted and the resulting data is presented in graphical and tabulated forms. Statistical methods including Pearson-product moment correlations, Cronbach's Alpha and ANOVA were used to identify internal associations, consistencies and significances, respectively. It has been proven that there are no significant differences in minimum safe distances relative to a ship's four cardinal sides, whether maneuvering while approaching a port or within an inner harbor. This study has been deemed significant for training future navigators, managing traffic in fairways, and designing harbors and maneuvering areas in the approaches to ports, among other applications. This work can also be used as a preliminary study for comparison with the well known safe domains presently in use.