• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2840-2842
• /
• 2000

This paper describes sensor-based occupancy grid map construction method through complete coverage navigation algorithm in unknown environment. In this paper, we use the updated Baysian model for probabilistic grid map. For map construction, complete coverage navigation method in which mobile robot can navigate complete field through as short path as possible in unknown environment, is used. The computer simulations result show that map construction method using complete coverage algorithm is efficient.

• Journal of IKEEE
• /
• v.9 no.1 s.16
• /
• pp.7-18
• /
• 2005

A key component of an autonomous mobile robot is to localize itself accurately and build a map of the environment simultaneously. In this paper, we propose a vision-based mobile robot localization and mapping algorithm using scale-invariant features. A camera with fisheye lens facing toward to ceiling is attached to the robot to acquire high-level features with scale invariance. These features are used in map building and localization process. As pre-processing, input images from fisheye lens are calibrated to remove radial distortion then labeling and convex hull techniques are used to segment ceiling region from wall region. At initial map building process, features are calculated for segmented regions and stored in map database. Features are continuously calculated from sequential input images and matched against existing map until map building process is finished. If features are not matched, they are added to the existing map. Localization is done simultaneously with feature matching at map building process. Localization. is performed when features are matched with existing map and map building database is updated at same time. The proposed method can perform a map building in 2 minutes on $50m^2$ area. The positioning accuracy is ${\pm}13cm$, the average error on robot angle with the positioning is ${\pm}3$ degree.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.3955-3971
• /
• 2020

Due to the significant increase in the use of autonomous car technology, it is essential to integrate this technology with high-precision digital map data containing more precise and accurate roadway information, as compared to existing conventional map resources, to ensure the safety of self-driving operations. While existing map technologies may assist vehicles in identifying their locations via Global Positioning System, it is however difficult to update the environmental changes of roadways in these maps. Roadway vision algorithms can be useful for building autonomous vehicles that can avoid accidents and detect real-time location changes. We incorporate a hybrid architectural design that combines unsupervised classification of vision data with supervised joint fusion classification to achieve a better noise-resistant algorithm. We identify, via a deep learning approach, an intelligent hybrid fusion algorithm for fusing multimodal vision feature data for roadway classifications and characterize its improvement in accuracy over unsupervised identifications using image processing and supervised vision classifiers. We analyzed over 93,000 vision frame data collected from a test vehicle in real roadways. The performance indicators of the proposed hybrid fusion algorithm are successfully evaluated for the generation of roadway digital maps for autonomous vehicles, with a recall of 0.94, precision of 0.96, and accuracy of 0.92.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.328-330
• /
• 2001

이 논문에서는 이동 로봇을 위하여 퍼지 이론과 Dempster-Shafer 이론을 이용한 불확실한 환경에서의 센서기반 네비게이션 방법을 제안한다. 제안된 제어기는 장애물 회피 동작과 목적지 찾기 동작을 위한 2개의 행동 모듈로 구성되어 있다. 특히, 실험 환경내에서 안전하게 움직이기 위해서 로봇이 목적지를 찾기 전에 자동으로 지도를 구축(map building) 하도록 하였다. 이 실험에서 구성된 지도는 평면상의 격자를 중심으로 작성되었다. 로봇의 센서에서 읽어들인 센서 값은 Dempster-Shaper 이론을 이용하여 기존의 지도와 혼합된다. 즉, 로봇이 움직일때마다 실험 환경내에서 새로운 정보를 읽어 들이고, 그 정보로 인하여 기존의 지도가 새로운 지도로 갱신되는 것이다. 이러한 작업을 거치면서 로봇은 장애물과 충돌없이 네비게이션하는 것 뿐 아니라 정해진 목적지까지도 쉽게 찾아갈 수 있다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.7
• /
• pp.693-699
• /
• 2006

An accurate and compact map is essential to an autonomous mobile robot system. For navigation, it is efficient to use an occupancy grid map because the environment is represented by probability distribution. But it is difficult to apply it to the large environment since it needs a large amount of memory proportional to the environment size. As an alternative, a topological map can be used to represent it in terms of the discrete nodes with edges connecting them. It is usually constructed by the Voronoi-like graphs, but in this paper the topological map is incrementally built based on the local grid map using the thinning algorithm. This algorithm can extract only meaningful topological information by using the C-obstacle concept in real-time and is robust to the environment change, because its underlying local grid map is constructed based on the Bayesian update formula. In this paper, the position probability is defined to evaluate the quantitative reliability of the end nodes of this thinning-based topological map (TTM). The global TTM can be constructed by merging each local TTM by matching the reliable end nodes determined by the position probability. It is shown that the proposed TTM can represent the environment accurately in real-time and it is readily extended to the global TTM.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.9
• /
• pp.898-904
• /
• 2010

Unmanned autonomous forklifts have a great potential to enhance the productivity of material handling in various applications because these forklifts can pick up and deliver loads without an operator and any fixed guide. There are, however, many technical difficulties in developing such forklifts including localization, map building, sensor fusion, control and so on. Implementation, which is often neglected, is one of practical issues in developing such an autonomous device. This is because the system requires numerous sensors, actuators, and controllers that need to be connected with each other, and the number of connections grows very rapidly as the number of devices grows. Another requirement on the integration is that the system should allow changes in the system design so that modification and addition of system components can be accommodated without too much effort. This paper presents a network-based distributed approach where system components are connected to a shared CAN network, and control functions are divided into small tasks that are distributed over a number of microcontrollers with a limited computing capacity. This approach is successfully applied to develop an unmanned forklift.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.10
• /
• pp.1051-1058
• /
• 2011

Unmanned autonomous forklifts have a great potential to enhance the productivity of material handling in various applications because these forklifts can pick up and deliver loads without an operator and any fixed guide. Especially, automation of pallet loading and unloading technique is useful for enhancing performance of logistics and reducing cost for automation system. There are, however, many technical difficulties in developing such forklifts including localization, map building, sensor fusion, control, and so on. This is because the system requires numerous sensors, actuators, and controllers that need to be connected with each other, and the number of connections grows very rapidly as the number of devices grows. This paper presents a vision sensorbased autonomous loading and unloading for network-based unmanned forklift where system components are connected to a shared CAN network. Functions such as image processing and control algorithm are divided into small tasks that are distributed over a number of microcontrollers with a limited computing capacity. And the experimental results show that proposed architecture can be an appropriate choice for autonomous loading in the unmanned forklift.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.10a
• /
• pp.400-403
• /
• 2005

The sonar sensors can be divided into a piezo type and an electrostatic type according to a principle of an operating system. The electrostatic type of a sonar sensor is used for map building in this paper. If we know the characteristics of sonar sensor, we can derive the ultrasonic pressure equation from an acoustics theory. We, therefore, developed Ultrasonic Pressure Probabilistic Model (UPPM) to consider the sound pressure in the probability updating process. In this paper, we found that the quality of the resulting probability map is considerably improved, through combining the UPPM with the grid-based mapping algorithm.

• Journal of Sensor Science and Technology
• /
• v.32 no.2
• /
• pp.118-123
• /
• 2023

This study presents sensor system for autonomous mobile robot capable of floor-to-floor self-navigation. The robot was modified using the Turtlebot3 hardware platform and ROS2 (robot operating system 2). The robot utilized the Navigation2 package to estimate and calibrate the moving path acquiring a map with SLAM (simultaneous localization and mapping). For elevator boarding, ultrasonic sensor data and threshold distance are compared to determine whether the elevator door is open. The current floor information of the elevator is determined using image processing results of the ceiling-fixed camera capturing the elevator LCD (liquid crystal display)/LED (light emitting diode). To realize seamless communication at any spot in the building, the LoRa (long-range) communication module was installed on the self-navigating autonomous mobile robot to support the robot in deciding if the elevator door is open, when to get off the elevator, and how to reach at the destination.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.5
• /
• pp.235-242
• /
• 2024

In the context of urban autonomous driving, where various types of traffic lights are encountered, traffic light recognition technology is of paramount importance. We have designed a high-performance traffic light recognition module tailored to scenarios encountered in domestic urban driving and devised a dataset construction process. In this paper, we focus on minimizing the camera's dependency to enhance traffic light recognition performance. The camera is used solely to distinguish the color information of traffic lights, while accurate location information of the traffic lights is obtained through localization and a map. Based on the information from these components, camera RoIs (Region of Interest) are extracted and transmitted to the embedded board. The transmitted images are then sent back to the main system for autonomous driving control. The processing time for one traffic light RoI averages 43.2 ms. We achieve processing times of average 93.4 ms through batch inference to meet real-time requirements. Additionally, we design a data construction process for collecting, refining, and storing traffic light datasets, including semi-annotation-based corrections.