• ETRI Journal
• /
• v.45 no.5
• /
• pp.847-861
• /
• 2023

Dynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distance, they lack texture or color information and have a lower resolution than conventional cameras. In addition, performance degradation occurs when a LiDAR-based object detection model is applied to different driving environments or when sensors from different LiDAR manufacturers are utilized owing to the domain gap phenomenon. To address these issues, a sensor-fusion-based object detection and classification method is proposed. The proposed method operates in real time, making it suitable for integration into autonomous vehicles. It performs well on our custom dataset and on publicly available datasets, demonstrating its effectiveness in real-world road environments. In addition, we will make available a novel three-dimensional moving object detection dataset called ETRI 3D MOD.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.7 s.184
• /
• pp.7-13
• /
• 2006

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.3
• /
• pp.341-347
• /
• 2022

This paper presents a comparison result of two simultaneous localization and mapping (SLAM) algorithms for navigation that have been proposed in literature. The performances of Extended Kalman Filter (EKF) SLAM under Gaussian condition, FastSLAM algorithms using Rao-Blackwellised method for particle filtering are compared in terms of accuracy of state estimations for localization of a robot and mapping of its environment. The algorithms were run using the same type of robot on indoor environment. The results show that the Particle filter based FastSLAM has the better performance in terms of accuracy of localization and mapping. The experimental results are discussed and compared.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1054-1059
• /
• 2005

To support the expansion of the autonomous robot market, the establishment of evaluation standards of the robot performance are essential. In this paper, to venture the standardization of the performance evaluation of the autonomous robot, the authors take the autonomous cleaning robot(ACR) as the initial stepping stone. Recently, the ACR has been being developed and marketed actively in many countries including Korea and it believes to be the fore-runner among various types of autonomous robot products. Standards of the performance evaluation for the ACR could be easily modified and applied to other autonomous robots. This paper formulates and suggests a group of standards for the performance evaluation based on a evaluation platform for the ACR. The newly developed performance evaluation platform has been designed to include all the important aspects of living environments in reality. In the platform the performance of the ACR is measured in terms of mobility, cleaning performance, avoidance of obstruction(safety), and operation noise. A few commercially available ACR products are collected and tested in the evaluation platform and compared against the performance evaluation standards formulated.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.5
• /
• pp.480-488
• /
• 2006

Industrial and economical importance of CP(Cellular Phone) is growing rapidly. Combined with IT technology, CP is one of the most attractive technologies of today. However, unless we find a new breakthrough in the technology, its growth may slow down soon. RT(Robot Technology) is considered one of the most promising next generation technologies. Unlike the industrial robot of the past, today's robots require advanced features, such as soft computing, human-friendly interface, interaction technique, speech recognition object recognition, among many others. In this paper, we present a new technological concept named RCP (Robotic Cellular Phone) which integrates RT and CP in the vision of opening a combined advancement of CP, IT, and RT, RCP consists of 3 sub-modules. They are $RCP^{Mobility}$(RCP Mobility System), $RCP^{Interaction}$, and $RCP^{Integration}$. The main focus of this paper is on $RCP^{Mobility}$ which combines an autonomous navigation system of the RT mobility with CP. Through $RCP^{Mobility}$, we are able to provide CP with robotic functions such as auto-charging and real-world robotic entertainment. Ultimately, CP may become a robotic pet to the human beings. $RCP^{Mobility}$ consists of various controllers. Two of the main controllers are trajectory controller and self-localization controller. While the former is responsible for the wheel-based navigation of RCP, the latter provides localization information of the moving RCP With the coordinates acquired from RFID-based self-localization controller, trajectory controller refines RCP's movement to achieve better navigation. In this paper, a prototype of $RCP^{Mobility}$ is presented. We describe overall structure of the system and provide experimental results on the RCP navigation.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1166-1171
• /
• 2004

In this study, the concept of autonomous mobility is applied to a gait support mobile robot. The aim of the development of the service robot is to assist the elderly with gait rehabilitation. This study proposes an ergonomic service robot design parameter. The gait assistant path pattern is derived from analysis of the elderly gait. A lever is installed in the AMR in order to measure both the pulling force and the leading force of the elderly. The path generation of the mobile robot is developed through consideration and analysis of elderly gait patterns. The ergonomic design parameters (dimensions, action scope and working space) are determined based on moving scope of the elderly. The gait assistant mobile robot was offered the elderly guide service and internet service based on the ergonomic design parameters.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.3
• /
• pp.1-9
• /
• 2007

A major concern for Autonomous Military Robot in the rough terrain is the problem of moving robot from an initial configuration to goal configuration. In this paper, We generate a local path to looking for the best route to move an goal configuration while avoiding known obstacle from world model, not violating the mobility constraints of robot. Trough a Simulator for Unmanned Autonomous Vehicle, We can simulate a traversability of unmanned autonomous vehicle based on steering, acceleration, braking command obtained from local path planning.

• Journal of the Ergonomics Society of Korea
• /
• v.33 no.5
• /
• pp.407-422
• /
• 2014

Objective: The purpose of the study is to develop quantitative usability evaluation criteria for senior-friendly autonomous transportation robot. Background: The Republic of Korea has become the most rapidly aging society, and is anticipated to enter the post-aged society in 2026. To raise the quality of life of a senior with limited mobility and to reduce the burden of caregivers, many high-tech assistive products with information technologies are developed nowadays. The senior-friendly autonomous transportation robot is one person robot vehicle to move a senior to the destination for hospitals, nursing homes or silver town complex. With built-in navigation system and environmental monitoring censors, it automatically seeks the path to the destination and avoids collision to obstacles and pedestrians on the way. Due to the early stage of the product, few usability studies in this field have been done, mostly on general service robots to assist seniors, power wheelchairs and delivery robots. ISO and KS standards for the service robots are focused on safety. Method: Based on the reference usability index, the early draft of the usability evaluation questionnaires was developed. After small group tests and interviews, the experts modified the initial draft to the Usability Evaluation Criteria for Senior-Friendly Autonomous Transportation Robot (UEC-SFATR). Result: UEC-SFATR consisted of 4 subscales - Safety, Controllability, Efficiency and Satisfaction. All of the 4 subscales of UEC-SFATR were passed the reliability criteria by 4 groups of seniors, divided by gender and familiarity of smart-devices. Conclusion: UEC-SFATR covers wider area of user experiences of the SFATR and is a good measurement tool to help both the users and developers of the robot. Application: This study provides guide to the future product development and product competitiveness evaluation by quantifying user experiences for the SFATR.

• Journal of Drive and Control
• /
• v.19 no.4
• /
• pp.97-103
• /
• 2022

Low fertility rates and increased life expectancy further exacerbate the process of an aging society. This is also reflected in the gradual increase in the proportion of vulnerable groups in the social population. The demand for improved mobility among vulnerable groups such as the elderly or the disabled has greatly driven the growth of the electric-assisted mobility device market. However, such mobile devices generally require a certain operating capability, which limits the range of vulnerable groups who can use the device and increases the cost of learning. Therefore, autonomous driving technology needs to be introduced to make mobility easier for a wider range of vulnerable groups to meet their needs of work and leisure in different environments. This study uses mini PC Odyssey, Velodyne Lidar VLP-16, electronic device and Linux-based ROS program to realize the functions of working environment recognition, simultaneous localization, map generation and navigation of electric powered mobile devices for vulnerable groups. This autonomous driving mobility device is expected to be of great help to the vulnerable who lack the immediate response in dangerous situations.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.221-222
• /
• 2023

The purpose of this study is to analyze the applicability and limitations of SPOT robots in the construction industry. The SPOT robot, which is being introduced to construction sites for smart construction with the progress of the 4th industrial revolution, is shaped like a four-legged dog and is equipped with various sensors for data collection and autonomous driving. In this study, hardware and software were analyzed, such as the size of the SPOT robot, mobility on slopes and heights, operating environment, and software functions that can collect data with a sensor weighing up to 14 kg. In addition, while the SPOT robot operates in a construction environment, performance such as stability, accuracy, signal connection distance, and obstacle avoidance are evaluated, and the applicability and limitations of the SPOT robot in the construction industry are analyzed. Based on this analysis, the purpose of this study is to evaluate when and how SPOT robots can be effectively used at construction sites, identify limitations, and derive contributions and improvements for the construction industry.