• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1307-1312
• /
• 2023

In this paper, we propose a hybrid camera system that combines cameras with different focal lengths and LiDAR (Light Detection and Ranging) sensors to address the core components of autonomous driving perception technology, which include object recognition and distance measurement. We extract objects within the scene and generate precise location and distance information for these objects using the proposed hybrid camera system. Initially, we employ the YOLO7 algorithm, widely utilized in the field of autonomous driving due to its advantages of fast computation, high accuracy, and real-time processing, for object recognition within the scene. Subsequently, we use multi-focal cameras to create depth maps to generate object positions and distance information. To enhance distance accuracy, we integrate the 3D distance information obtained from LiDAR sensors with the generated depth maps. In this paper, we introduce not only an autonomous vehicle platform capable of more accurately perceiving its surroundings during operation based on the proposed hybrid camera system, but also provide precise 3D spatial location and distance information. We anticipate that this will improve the safety and efficiency of autonomous vehicles.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.1
• /
• pp.20-25
• /
• 2022

This paper presents a development of simulation environment for validation of autonomous driving (AD) algorithm based on Robot Operating System (ROS). ROS is one of the commonly-used frameworks utilized to control autonomous vehicles. For the evaluation of AD algorithm, a 3D autonomous driving simulator has been developed based on LGSVL. Two additional sensors are implemented in the simulation vehicle. First, Lidar sensor is mounted on the ego vehicle for real-time driving environment perception. Second, GPS sensor is equipped to estimate ego vehicle's position. With the vehicle sensor configuration in the simulation, the AD algorithm can predict the local environment and determine control commands with motion planning. The simulation environment has been evaluated with lane changing and keeping scenarios. The simulation results show that the proposed 3D simulator can successfully imitate the operation of a real-world vehicle.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.123.1-123
• /
• 2001

For Autonomous navigation of the mobile robots, the robots' capability to recognize 3D environment is necessary. In this paper, an on-line 3D map building method for autonomous mobile robots is proposed. To get range data on the environment, we use an sensor system which is composed of a structured light and a CCD camera based on optimal triangulation. The structured laser is projected as a horizontal strip on the scene. The sensor system can rotate $\pm$ $30{\Circ}$ with a goniometer. Scanning the system, we get the laser strip image for the environments and update planes composing the environment by some image processing steps. From the laser strip on the captured image, we find a center point of each column, and make line segments through blobbing these center poings. Then, the planes of the environments are updated. These steps are done on-line in scanning phase. With the proposed method, we can efficiently get a 3D map about the structured environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.123.5-123
• /
• 2001

For autonomous navigation of the mobile robots, the robots' capability to recognize 3D environment is necessary. In this paper, an on-line 3D map building method for autonomous mobile robots is proposed. To get range data on the environment, we use a sensor system which is composed of a structured light and a CCD camera based on optimal triangulation. The structured laser is projected as a horizontal strip on the scene. The sensor system can rotate$\pm$30$^{\circ}$ with a goniometer. Scanning the system, we get the laser strip image for the environments and update planes composing the environment by some image processing steps. From the laser strip on the captured image, we find a center point of each column, and make line segments through blobbing these center points. Then, the planes of the environments are updated. These steps are done on-line in scanning phase. With the proposed method, we can efficiently get a 3D map about the structured environment.

• International Journal of Ocean System Engineering
• /
• v.2 no.3
• /
• pp.139-150
• /
• 2012

This paper presents an improved guidance algorithm for autonomous underwater vehicles (AUV) in 3D space for generating smoother vehicle turn during the course change at the way-points. The way-point guidance by the line-of-sight (LOS) method has been modified for correcting the reference angles to achieve minimal calculation and smoother transition at the way-points. The algorithm has two phases in which the first phase brings the vehicle to converge to a distance threshold point on the line segment connecting the first two way-points and the next phase generates an angular path with smoother transition at the way-points. Then the desired angles are calculated from the reference and correction angles. The path points are regularly parameterized in the spherical coordinates and mapped to the Cartesian coordinates. The proposed algorithm is found to be simple and can be used for real time implementation. The details of the algorithm and simulation results are presented.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.183-190
• /
• 2022

Image-based 3D object detection is one of the important and difficult problems in autonomous driving and robotics, and aims to find and represent the location, dimension and orientation of the object of interest. It generates three dimensional (3D) bounding boxes with only 2D images obtained from cameras, so there is no need for devices that provide accurate depth information such as LiDAR or Radar. Image-based methods can be divided into three main categories: monocular, stereo, and multi-view 3D object detection. In this paper, we investigate the recent state-of-the-art models of the above three categories. In the multi-view 3D object detection, which appeared together with the release of the new benchmark datasets, NuScenes and Waymo, we discuss the differences from the existing monocular and stereo methods. Also, we analyze their performance and discuss the advantages and disadvantages of them. Finally, we conclude the remaining challenges and a future direction in this field.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.5
• /
• pp.182-189
• /
• 2002

This paper presents a framework of hybrid dynamic control systems for the motion control of wheeled mobile robot systems with nonholonomic constraints. The hybrid control system has the 3-layered hierarchical structure: digital automata for the higher process, mobile robot system for the lower process, and the interface as the interaction process between the continuous dynamics and the discrete dynamics. In the hybrid control architecture of mobile robot, the continuous dynamics of mobile robots are modeled by the switched systems. The abstract model and digital automata for the motion control are developed. In high level, the discrete states are defined by using the sensor-based search windows and the reference motions of a mobile robot in low level are specified in the abstracted motions. The mobile robots can perform both the motion planning and autonomous maneuvering with obstacle avoidance in indoor navigation problem. Simulation and experimental results show that hybrid system approach is an effective method for the autonomous maneuvering in indoor environments

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.149-158
• /
• 2024

This paper presents a robust autonomous navigation and reconnaissance system for tracked robots, designed to handle complex multi-floor indoor environments with stairs. We introduce a localization algorithm that adjusts scan matching parameters to robustly estimate positions and create maps in environments with scarce features, such as narrow rooms and staircases. Our system also features a path planning algorithm that calculates distance costs from surrounding obstacles, integrated with a specialized PID controller tuned to the robot's differential kinematics for collision-free navigation in confined spaces. The perception module leverages multi-image fusion and camera-LiDAR fusion to accurately detect and map the 3D positions of objects around the robot in real time. Through practical tests in real settings, we have verified that our system performs reliably. Based on this reliability, we expect that our research team's autonomous reconnaissance system will be practically utilized in actual disaster situations and environments that are difficult for humans to access, thereby making a significant contribution.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.44-52
• /
• 2019

We implement an educational indoor autonomous mobile robot system that integrates LiDAR sensing information with RGB-D camera image information and exploits the integrated information. This system uses the existing sensing method employing a LiDAR with a small number of scan channels to acquire LiDAR sensing information. To remedy the weakness of the existing LiDAR sensing method, we propose the 3D structure recognition technique using depth images from a RGB-D camera and the deep learning based object recognition algorithm and apply the proposed technique to the system.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2699-2708
• /
• 2020

Helical-coil steam generator (HCSG) technology is a major design candidate for small modular reactors due to its compactness and capability to produce superheated steam with high generation efficiency. In this paper, we investigate the feasibility of the passively autonomous power maneuvering by coupling the 3-D transient multi-physics of a soluble-boron-free (SBF) core with a time-dependent HCSG model. The predictor corrector quasi-static method was used to reduce the cost of the transient 3-D neutronic solution. In the numerical system simulations, the feedwater flow rate to the secondary of the HCSGs is adjusted to extract the demanded power from the primary loop. This varies the coolant temperature at the inlet of the SBF core, which governs the passively autonomous power maneuvering due to the strongly negative coolant reactivity feedback. Here, we simulate a 100-50-100 load-follow operation with a 5%/minute power ramping speed to investigate the feasibility of the passively autonomous load-follow in a 450 MW_th SBF PWR. In addition, the passively autonomous frequency control operation is investigated. The various system models are coupled, and they are solved by an in-house Fortran-95 code. The results of this work demonstrate constant steam temperature in the secondary side and limited variation of the primary coolant temperature. Meanwhile, the variations of the core axial shape index and the core power peaking are sufficiently small.