• The Journal of Korea Robotics Society
• /
• v.7 no.2
• /
• pp.92-100
• /
• 2012

A map of complex environment can be generated using a robot carrying sensors. However, representation of environments directly using the integration of sensor data tells only spatial existence. In order to execute high-level applications, robots need semantic knowledge of the environments. This research investigates the design of a system for recognizing objects in 3D point clouds of urban environments. The proposed system is decomposed into five steps: sequential LIDAR scan, point classification, ground detection and elimination, segmentation, and object classification. This method could classify the various objects in urban environment, such as cars, trees, buildings, posts, etc. The simple methods minimizing time-consuming process are developed to guarantee real-time performance and to perform data classification on-the-fly as data is being acquired. To evaluate performance of the proposed methods, computation time and recognition rate are analyzed. Experimental results demonstrate that the proposed algorithm has efficiency in fast understanding the semantic knowledge of a dynamic urban environment.

• Korean Journal of Optics and Photonics
• /
• v.29 no.5
• /
• pp.204-214
• /
• 2018

Since LIDAR is advantageous for accurate information acquisition and realization of a high-resolution 3D image based on characteristics that can be precisely measured, it is essential to autonomous navigation systems that require acquisition and judgment of accurate peripheral information without user intervention. Recently, as an autonomous navigation system applying LIDAR has been utilized in human living space, it is necessary to solve the eye-safety problem, and to make reliable judgment through accurate obstacle recognition in various environments. In this paper, we construct a single-shot LIDAR system (SSLs) using a 1550-nm eye-safe light source, and report the analysis method and results of LIDAR signals for various measurement environments, reflective materials, and material angles. We analyze the signals of materials with different reflectance in each measurement environment by using a 5% Al reflector and a building wall located at a distance of 25 m, under indoor, daytime, and nighttime conditions. In addition, signal analysis of the angle change of the material is carried out, considering actual obstacles at various angles. This signal analysis has the merit of possibly confirming the correlation between measurement environment, reflection conditions, and LIDAR signal, by using the SNR to determine the reliability of the received information, and the timing jitter, which is an index of the accuracy of the distance information.

• Journal of Ocean Engineering and Technology
• /
• v.17 no.6
• /
• pp.83-90
• /
• 2003

This paper presents an underwater hybrid navigation system for a semi-autonomous underwater vehicle (SAUV). The navigation system consists of an inertial measurement unit (IMU), and a Doppler velocity log (DVL), accompanied by a magnetic compass. The errors of inertial measurement units increase with time, due to the bias errors of gyros and accelerometers. A navigational system model is derived, to include the scale effect and bias errors of the DVL, of which the state equation composed of the navigation states and sensor parameters is 20. The conventional extended Kalman filter was used to propagate the error covariance, update the measurement errors, and correct the state equation when the measurements are available. Simulation was performed with the 6-d.o,f equations of motion of SAUV, using a lawn-mowing survey mode. The hybrid underwater navigation system shows good tracking performance, by updating the error covariance and correcting the system's states with the measurement errors from a DVL, a magnetic compass, and a depth sensor. The error of the estimated position still slowly drifts in the horizontal plane, about 3.5m for 500 seconds, which could be eliminated with the help of additional USBL information.

• Journal of Biosystems Engineering
• /
• v.34 no.6
• /
• pp.391-396
• /
• 2009

The percentage of those aged 60 and over is 43.5% among our country's 3,186 thousands farming population, so farm village is getting aging society rapidly. Moreover agricultural competitiveness has being weakened due to labor shortage by degradation in quality of labor configuration from elderly porson. For realisms easy workability, we developed a motor vehicle for agricultural activity. The vehicle has an automatic guidance system which could follows a track of magnetic tape on the floor for easy moving to given working position. We collected data from two guidance sensors, located on front and rear end of the vehicle and calculated displacement and angle deviation from the track. This traveling system was stably controlled with processing information deflection S, angle of deviation, D and angle velocity, Vt = $k_1D$ - $k_2S$ from two guidance sensors attached on front and rear of th motor vehicle. Also this system have been tested under various condition of $k_1$, $k_2$ for comparison on both stepped and turning routes. The results show that traveling performance is best at $k_1$=0.7, $k_2$=3.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.5
• /
• pp.259-266
• /
• 2022

In this study, we developed a deep learning and vision sensor-based assembly performance evaluation method isfor prefabricated steel structures. The assembly parts were segmented using a modified version of the receptive field block convolution module inspired by the eccentric function of the human visual system. The quality of the assembly was evaluated by detecting the bolt holes in the segmented assembly part and calculating the bolt hole positions. To validate the performance of the evaluation, models of standard and defective assembly parts were produced using a 3D printer. The assembly part segmentation network was trained based on the 3D model images captured from a vision sensor. The sbolt hole positions in the segmented assembly image were calculated using image processing techniques, and the assembly performance evaluation using the k-nearest neighbor algorithm was verified. The experimental results show that the assembly parts were segmented with high precision, and the assembly performance based on the positions of the bolt holes in the detected assembly part was evaluated with a classification error of less than 5%.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.945-953
• /
• 2018

In this paper, we use 3-D LIDAR for obstacle detection and avoidance maneuver for autonomous unmanned operation. It is aimed to avoid obstacle avoidance in unmanned water under marine condition using only single sensor. 3D lidar uses Quanergy's M8 sensor to collect surrounding obstacle data and includes layer information and intensity information in obstacle information. The collected data is converted into a three-dimensional Cartesian coordinate system, which is then mapped to a two-dimensional coordinate system. The data including the obstacle information converted into the two-dimensional coordinate system includes noise data on the water surface. So, basically, the noise data generated regularly is defined by defining a hypothetical region of interest based on the assumption of unmanned water. The noise data generated thereafter are set to a threshold value in the histogram data calculated by the Vector Field Histogram, And the noise data is removed in proportion to the amount of noise. Using the removed data, the relative object was searched according to the unmanned averaging motion, and the density map of the data was made while keeping one cell on the virtual grid map. A polar histogram was generated for the generated obstacle map, and the avoidance direction was selected using the boundary value.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.1029-1035
• /
• 2013

This paper proposes a real time lane detection algorithm using LRF (Laser Range Finder) for autonomous navigation of a mobile robot. There are many technologies for safety of the vehicles such as airbags, ABS, EPS etc. The real time lane detection is a fundamental requirement for an automobile system that utilizes outside information of automobiles. Representative methods of lane recognition are vision-based and LRF-based systems. By the vision-based system, recognition of environment for three dimensional space becomes excellent only in good conditions for capturing images. However there are so many unexpected barriers such as bad illumination, occlusions, and vibrations that the vision cannot be used for satisfying the fundamental requirement. In this paper, we introduce a three dimensional lane detection algorithm using LRF, which is very robust against the illumination. For the three dimensional lane detections, the laser reflection difference between the asphalt and lane according to the color and distance has been utilized with the extraction of feature points. Also a stable tracking algorithm is introduced empirically in this research. The performance of the proposed algorithm of lane detection and tracking has been verified through the real experiments.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.

• Journal of the Korea Convergence Society
• /
• v.8 no.4
• /
• pp.9-18
• /
• 2017

UAVs began to be actively applied to so-called 3D jobs, including the autonomous exploration, investigation, mapping, search and rescue, etc. since the mid-2000s. With this global trend, having a precise controllability of the UAV will certainly revolutionize the life of the modern human in the aspect of tremendous applications of the UAV. In the first part, a simplified dynamic model of the UAV identified using system identification techniques is compared with the previously built time-discrete linear model. In the second part, the three parameters of the dynamic model are estimated using the batch and RLS methods. Angular acceleration data of the quadrotor UAV at the hovering maneuver are analyzed and shown to be converging at all time. Also, according to the quadrotor flight data from both experiments and MATLAB simulations, the batch estimation method turns out to be more accurate than the RLS estimation method based on the comparison of final parameter values.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.910-917
• /
• 2020

In fire suppression, continuous delivery of water or foam to the fire source is essential. The present study concerns fire suppression in a ship under sea condition, by introducing reinforcement learning technique to aiming of fire extinguishing nozzle, which works in a ship compartment with six degrees of freedom movement by irregular waves. The physical modeling of the water jet and compartment motion was provided using Unity 3D engine. In the reinforcement learning, the change of the nozzle angle during the scenario was set as the action, while the reward is proportional to the ratio of the water particle delivered to the fire source area. The optimal control of nozzle aiming for continuous delivery of water jet could be derived. Various algorithms of reinforcement learning were tested to select the optimal one, the proximal policy optimization.