• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.115-122
• /
• 2018

The purpose of this study is to investigate the effect of technology acceptance model (TAM) on behavioral intention in order to grasp the degree of technology acceptance on autonomous driving among the various factors that consumers perceive as unmanned vehicle system becomes commercialized. In addition to the mediating effect of perceived usefulness proposed by the existing TAM, this study proposed the perceived trust (PT) and hypothesized its mediating effect on behavioral intention to use the self-driving. Path anlaysis is adopted to investigate our hypothesis using the structural equation model. The sample used for the analysis was 149 valid data among 160 responses. The effects of total effect, direct effect, and indirect effect were confirmed by hypothesis test on mediating effect. Non-parametric bootstrapping analysis was also performed to confirm the robustness. All the hypotheses were significant and we found a partial indirect effect, which implies that mediation effect of PT on behavioral intention.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.332-340
• /
• 2013

This paper reports a programming toolkit for implementing localization and navigation of a mobile robot both in real world and simulation. Many of the previous function libraries are difficult to use because of their complexity or lack of usability. The proposed toolkit consist of functions for dead reckoning, motion model, measurement model, and operations on directions or heading angles. The dead reckoning and motion model deals with differential drive robot and bicycle type robot driven by front wheel or rear wheel. The functions can be used for navigation in both real environment and simulation. To prove the feasibility of the toolkit, simulation results are shown along with the results in real environment. It is expected the proposed toolkit is used for test of algorithms for mobile robot navigation such as localization, map building, and obstacle avoidance.

• Journal of Engineering Education Research
• /
• v.1 no.1
• /
• pp.57-79
• /
• 1998

In this paper, I advocate interactive model which treats science and technology as distinguishable subcultures each with their own bodies of lore and competence against the traditonal hierachical model which treats technology as applied science. For engineering science which is a component in technology as knowledge, I count design as the core part of engineering and discuss the characteristic of engineering design. I also critically assess the models of technological knowledge change, Khunian model and variation-selection model to understand the relation between science and technology. I propose a model that science and technology interaction is mediated interaction. I only outline the plausibility of this model. Industrial research is a modern form of the interaction between science and technology. I discuss Reich who focused on the broad background of industrial research and MeyerThurow who has microperspective in industrial research. The conclusion I draw from the discussion, is that through industiral research, the science-technology interaction become more structured and autonomous, and the scientists and engineers become simply patrs of the structure of industrial research rather than the personal subject.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.11-12
• /
• 2024

건설 현장에서 자율주행 로봇의 안전한 주행을 위해 동적 장애물의 정확한 인식 및 추적이 중요하다. 본 논문에서는 실시간 3D 객체 인식 및 추적을 위한 방법을 제안한다. Complex-YOLOv4 모델을 이용한 객체 인식, SORT 알고리즘 확장을 통한 객체 추적을 구현하였다. Jetson AGX Orin 보드의 ROS2 환경에서 시스템을 구축하여, 실시간 3D 객체 인식 및 추적이 가능함을 확인하였다.

• Journal of Navigation and Port Research
• /
• v.38 no.4
• /
• pp.343-348
• /
• 2014

A routing scheme called MCS-NLTC using a self-configuration marine network model and the diversity and heterogeneity of broadband wireless access technologies is newly proposed. The MCS-NLTC algorithm selects optimal nodes and carriers for every hop in optimal routes based on not conventional hop counts but normalized distances to destination ships (location information of destination ships). Normalized transmission characteristics of applications and carriers are considered to get optimal routes as well. The location information enhances convergence speed to get destinations, which makes the route search time faster. Evaluated performances are compared with those of the schemes based on max-win (OMH-MW), and normalized transmission characteristics (MCS-NTC).

• Journal of the Korea Society for Simulation
• /
• v.20 no.3
• /
• pp.101-109
• /
• 2011

M&S in the field of national defense is a battle system has been highly spotlighted for obtaining weapon systems, analyzing and experimentation of battle effects to reduce costs, time, and risks. It is classified as Campaign, Mission, Engagement, and Engineering levels by detail of description. In engagements, many situations on the battle field which are really unpredictable are required to be considered on the view of diverse tactics. Thus, engagement simulation is in demand to use for forecasting real-world battle situations by inserting various components which consists of real engaging situations into virtual local battle field. While developing the engagement simulation, adopting the concept of agent-based simulation gives it benefits which are improved autonomy, composability, and reusability of entities. It means reducing the time, cost and effort to develop the simulations. This paper concentrates on the framework of multi-agent based engagement simulation using Cougaar Architecture.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.368-376
• /
• 2021

Artificial intelligence clouds help to efficiently develop the autonomous things integrating artificial intelligence technologies and control technologies by sharing the learned models and providing the execution environments. The existing autonomous things development technologies only take into account for the accuracy of artificial intelligence models at the cost of the increment of the complexity of the models including the raise up of the number of the hidden layers and the kernels, and they consequently require a large amount of computation. Since resource-constrained computing environments, could not provide sufficient computing resources for the complex models, they make the autonomous things violate time criticality. In this paper, we propose a digital twin software development framework that selects artificial intelligence models optimized for the computing environments. The proposed framework uses a load estimation DNN model to select the optimal model for the specific computing environments by predicting the load of the artificial intelligence models with digital twin data so that the proposed framework develops the control software. The proposed load estimation DNN model shows up to 20% of error rate compared to the formula-based load estimation scheme by means of the representative CNN models based experiments.

• Journal of Internet Computing and Services
• /
• v.22 no.4
• /
• pp.13-28
• /
• 2021

Reinforcement Learning (RL) is a machine learning algorithm that repeat the closed-loop process that agents perform actions specified by the policy, the action is evaluated with a reward function, and the policy gets updated accordingly. The key benefit of RL is the ability to optimze the policy with action evaluation. Hence, it can effectively be applied to developing advanced intelligent systems and autonomous systems. Conventional RL incoporates a single policy, a reward function, and relatively simple policy update, and hence its utilization was limited. In this paper, we propose an extended RL model that considers multiple instances of RL elements. We define a formal model of the key elements and their computing model of the extended RL. Then, we propose design methods for applying to system development. As a case stud of applying the proposed formal model and the design methods, we present the design and implementation of an advanced car navigator system that guides multiple cars to reaching their destinations efficiently.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.545-549
• /
• 2007

The Bio-Inspired System focuses on the creation of an effective system model for massive network applications and is being widely developed. However, the system has a problem-difficulty implementing three features in the system, which includes scalability, adaptability and survivability. To solve this problem, we designed an Ecogent as a multiple intelligence agent, and a Bio-platform to address the three features of scalability, adaptability and survivability. The Bio-Inspired System Platform consists of an ERS (Ecogent Runtime Services) Platform and a Bio-Platform. The ERS platform serves the basic functions of mobile agents, such as Registration, Life Cycle, Migration, Communication, Location and Fault Tolerance. The Bio-Platform includes the functions of Evolution Control and Stigmergy Control to address evolution and adaptation.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.45 no.6
• /
• pp.10-15
• /
• 2008

This paper describes virtual environment and sensor modeling to analyze and verify the performance of autonomous navigation system. Virtual synthetic environment is constructed with 6 subgroups which cover from virtual environment construction to virtual sensor modeling of real systems. This research is applied to validate and assess performance of concerned algorithms and complex functions for autonomous navigation system based on virtual environment.