• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.14-19
• /
• 2021

This paper presents LiDAR static obstacle map based vehicle dynamic state estimation algorithm for urban autonomous driving. In an autonomous driving, state estimation of host vehicle is important for accurate prediction of ego motion and perceived object. Therefore, in a situation in which noise exists in the control input of the vehicle, state estimation using sensor such as LiDAR and vision is required. However, it is difficult to obtain a measurement for the vehicle state because the recognition sensor of autonomous vehicle perceives including a dynamic object. The proposed algorithm consists of two parts. First, a Bayesian rule-based static obstacle map is constructed using continuous LiDAR point cloud input. Second, vehicle odometry during the time interval is calculated by matching the static obstacle map using Normal Distribution Transformation (NDT) method. And the velocity and yaw rate of vehicle are estimated based on the Extended Kalman Filter (EKF) using vehicle odometry as measurement. The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment, and is verified with data obtained from actual driving on urban roads. The test results show a more robust and accurate dynamic state estimation result when there is a bias in the chassis IMU sensor.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.9
• /
• pp.45-53
• /
• 2006

This paper proposes a method for an effective intelligent route decision for automatic moving robots(AMR) using a 2D spatial map of a stereo camera system. In this method, information about depth and disparity map are detected in the inputting images of a parallel stereo camera. The distance between the automatic moving robot and the obstacle is detected, and a 2D spatial map is obtained from the location coordinates. Then the relative distances between the obstacle and other objects are deduced. The robot move automatically by effective and intelligent route decision using the obtained 2D spatial map. From experiments on robot driving with 240 frames of stereo images, it was found that the error ratio of the calculated distance to the measured distance between objects was very low, 1.52[%] on average.

• International Journal of Internet, Broadcasting and Communication
• /
• v.8 no.4
• /
• pp.54-57
• /
• 2016

In this paper, the method for an effective and intelligent route decision of the automatic ground vehicle (AGV) using a 2D spatial map of the stereo camera system is proposed. The depth information and disparity map are detected in the inputting images of a parallel stereo camera. The distance between the automatic moving robot and the obstacle detected and the 2D spatial map obtained from the location coordinates, and then the relative distance between the obstacle and the other objects obtained from them. The AGV moves automatically by effective and intelligent route decision using the obtained 2D spatial map. From some experiments on robot driving with 480 frames of the stereo images, it is analyzed that error ratio between the calculated and measured values of the distance between the objects is found to be very low value of 1.57% on average, respectably.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.344-351
• /
• 2017

In this paper, we propose the obstacle database management module for obstacle estimation and clustering. The proposed G-eye manager system can create customized walking route for blind people using the UI manager and verify the coordinates of the path. Especially, G-eye management system designed a regional information module. The regional information module can improve the loading speed of the obstacle data by classifying the local information by clustering the coordinates of the obstacle. In this paper, we evaluate the reliability of the walking route generated from the obstacle map. We obtain the coordinate value of the path avoiding the virtual obstacle from the proposed system and analyze the error rate of the path avoiding the obstacle according to the size of the obstacle. And we analyze the correlation between obstacle size and route by classifying virtual obstacles into sizes.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1468-1471
• /
• 2005

This Paper is to find out a solution for the full-coverage algorithm requiring the real-time processing such as mobile home service robots and vacuum cleaner robots. Previous methods are used by adopting based grid approach method. They used lots of sensors, a high speed CPU, expensive ranger sensors and huge memory. Besides, most full-coverage algorithms should have a map before obstacle avoidance. However, if a robot able to recognize the tangent vector of obstacles, it is able to bring the same result with less sensors and simplified hardware. Therefore, this study suggests a topological based approach and a local obstacle voidance method using a few of PSD sensors and ultra sonic sensors. The simulation results are presented to prove its applicability.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.86-96
• /
• 2010

In this paper, we propose stereo vision-based obstacle detection and vehicle verification methods using U-disparity map and bird's-eye view mapping. First, we extract a road feature using maximum frequent values in each row and column. And we extract obstacle areas on the road using the extracted road feature. To extract obstacle areas exactly we utilize U-disparity map. We can extract obstacle areas exactly on the U-disparity map using threshold value which consists of disparity value and camera parameter. But there are still multiple obstacles in the extracted obstacle areas. Thus, we perform another processing, namely segmentation. We convert the extracted obstacle areas into a bird's-eye view using camera modeling and parameters. We can segment obstacle areas on the bird's-eye view robustly because obstacles are represented on it according to ranges. Finally, we verify the obstacles whether those are vehicles or not using various vehicle features, namely road contacting, constant horizontal length, aspect ratio and texture information. We conduct experiments to prove the performance of our proposed algorithms in real traffic situations.

• The KIPS Transactions:PartB
• /
• v.18B no.5
• /
• pp.255-264
• /
• 2011

In this paper, we propose a forward vehicle detection algorithm using column detection and bird's-eye view mapping based on stereo vision. The algorithm can detect forward vehicles robustly in real complex traffic situations. The algorithm consists of the three steps, namely road feature-based column detection, bird's-eye view mapping-based obstacle segmentation, obstacle area remerging and vehicle verification. First, we extract a road feature using maximum frequent values in v-disparity map. And we perform a column detection using the road feature as a new criterion. The road feature is more appropriate criterion than the median value because it is not affected by a road traffic situation, for example the changing of obstacle size or the number of obstacles. But there are still multiple obstacles in the obstacle areas. Thus, we perform a bird's-eye view mapping-based obstacle segmentation to divide obstacle accurately. We can segment obstacle easily because a bird's-eye view mapping can represent the position of obstacle on planar plane using depth map and camera information. Additionally, we perform obstacle area remerging processing because a segmented obstacle area may be same obstacle. Finally, we verify the obstacles whether those are vehicles or not using a depth map and gray image. We conduct experiments to prove the vehicle detection performance by applying our algorithm to real complex traffic situations.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.3
• /
• pp.203-209
• /
• 2010

This paper presents a hierarchical fuzzy motion planner for humanoid robots in 3D uneven environments. First, we define both motion primitives and locomotion primitives of humanoid robots. A high-level planner finds a global path from a global navigation map that is generated based on a combination of 2.5 dimensional maps of the workspace. We use a passage map, an obstacle map and a gradient map of obstacles to distinguish obstacles. A mid-level planner creates subgoals that help the robot efficiently cope with various obstacles using only a small set of locomotion primitives that are useful for stable navigation of the robot. We use a local obstacle map to find the subgoals along the global path. A low-level planner searches for an optimal sequence of locomotion primitives between subgoals by using fuzzy motion planning. We verify our approach on a virtual humanoid robot in a simulated environment. Simulation results show a reduction in planning time and the feasibility of the proposed method.

• The KIPS Transactions:PartA
• /
• v.18A no.2
• /
• pp.75-80
• /
• 2011

Recently, many cleaning robots have been made with various algorithms for efficient cleaning. One of them is a DmaxCoverage algorithm which efficiently clean for the situation when the robot has a time limit. This algorithm uses Rectangle Tiling method for finding the biggest rectangle that doesn't have any obstacle. When the robot uses grid map, Rectangle Tiling method can find the optimal value. Rectangle Tiling method is to find all of the rectangles in the grid map. But when the grid map is big, it has a problem that spends a lot of times because of the large numbers of rectangles. In this paper, we propose Four Direction Rectangle Scanning(FDRS) method that has similar accuracy but faster than Rectangle Tiling method. FDRS method is not to find all of the rectangle, but to search the obstacle's all directions. We will show the FDRS method's performance by comparing of FDRS and Rectangle Tiling methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.7
• /
• pp.36-48
• /
• 2010

This paper is concerned with stereo vision-based approach to detect obstacles and to generate the path of destination from the start. The hexapod robot in the experiment is cable of walking by legs and driving by wheels simultaneously. The hexapod robot operates under the driving mode normally, and it changes driving mode to walking mode to overcome obstacles using its legs. Disparity map, which is the correlation between two images taken by stereo camera, is employed for calculation of the distance between the robot and obstacles. When the obstacles information is extracted from the disparity map, the potential field algorithm is applied to create the obstacle-avoidance path. Simulator, based on OpenGL, is developed to generate the graphical path, and the experimental results are shown for the verification of the proposed algorithm.