• Journal of Drive and Control
• /
• v.19 no.4
• /
• pp.110-116
• /
• 2022

Recently, various studies have been conducted to apply deep learning and AI to various fields of autonomous driving, such as recognition, sensor processing, decision-making, and control. This paper proposes a controller applicable to path following, static obstacle avoidance, and pedestrian avoidance situations by utilizing reinforcement learning in autonomous vehicles. For repetitive driving simulation, a reinforcement learning environment was constructed using virtual environments. After learning path following scenarios, we compared control performance with Pure-Pursuit controllers and Stanley controllers, which are widely used due to their good performance and simplicity. Based on the test case of the KNCAP test and assessment protocol, autonomous emergency steering scenarios and autonomous emergency braking scenarios were created and used for learning. Experimental results from zero collisions demonstrated that the reinforcement learning controller was successful in the stationary obstacle avoidance scenario and pedestrian collision scenario under a given condition.

• Journal of Drive and Control
• /
• v.18 no.4
• /
• pp.77-83
• /
• 2021

With the progress in virtual reality technology, various virtual objects can be displayed using head-mounted displays (HMD). However, force feedback sensations such as pushing against a virtual object are not possible with an HMD only. Focusing on force feedback, desktop-type devices are generally used, but the user cannot move in a virtual space because such devices are fixed on a desk. With a wearable force feedback device, users can move around while experiencing force feedback. Therefore, the authors have developed a wearable force feedback device using a magnetorheological fluid clutch and pneumatic rubber artificial muscle, aiming at presenting the elasticity, friction, and viscosity of an object. To date, we have developed a wearable four-degree-of-freedom (4-DOF) force feedback device and have quantitatively evaluated that it can present commanded elastic, frictional, and viscous forces to the end effector. However, sensory evaluation with a human has not been performed. In this paper, therefore, we conduct a sensory evaluation of the proposed method. In the experiment, frictional and viscous forces are rendered in a virtual space using a 4-DOF force feedback device. Subjects are asked to answer questions on a 1- to 7-point scale, from 1 (not at all) to 4 (neither) to 7 (strongly). The Wilcoxon signed rank test was used for all data, and answer 4 (neither) was used as compared standard data. The experimental results confirmed that the user could feel the presence or absence of viscous and frictional forces. However, the magnitude of those forces was not sensed correctly.

• Korean Journal of Construction Engineering and Management
• /
• v.5 no.2 s.18
• /
• pp.47-54
• /
• 2004

Recently, many high-rise buildings have been constructed, and are under construction. And a high-rise building with more than 100 floors is under planning. From site logistics management point of view, it is very important to manage vertical transportation of resource (e.g., material, equipment and construction labors) in high-rise building construction. The higher the building is constructed, the more important it is to manage for vertical transportation of it. In case of labors, vertical movement needs longer time in high-rise building construction than in low-rise. This results in low productivity and work efficiency of the construction. Therefore, this study presents a process of a vertical movement plan for labors using discrete-event simulation. And then the process applies to MT 130 project, which is a virtual high-rise building construction project.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.5
• /
• pp.1609-1623
• /
• 2014

A number of studies have been conducted recently regarding the development of automation systems for the construction sector. Much of this attention has focused on earthwork because it is highly dependent on construction machines and is regarded as being basic for the construction of buildings and civil works. For example, technologies are being developed in order to enable earthwork planning based on construction site models that are constructed by automatic systems and to enable construction equipment to perform the work based on the plan and the environment. There are many problems that need to be solved in order to enable the use of automatic earthwork systems in construction sites. For example, technologies are needed for enabling collaborations between similar and different kinds of construction equipment. This study aims to develop a construction system that imitates collaborative systems and decision-making methods that are used by humans. The proposed system relies on the multi-agent concept from the field of artificial intelligence. In order to develop a multi-agent-based system, configurations and functions are proposed for the agents and a framework for collaboration and arbitration between agents is presented. Furthermore, methods are introduced for preventing duplicate work and minimizing interference effects during the collaboration process. Methods are also presented for performing advance planning for the excavators and compactors that are involved in the construction. The current study suggests a theoretical framework and evaluates the results using virtual simulations. However, in the future, an empirical study will be conducted in order to apply these concepts to actual construction sites through the development of a physical system.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.125-132
• /
• 2021

In this paper, We propose a study on the construction of an environment for collaboration in mixed reality and a method for working with wearable IoT devices. Mixed reality is a mixed form of virtual reality and augmented reality. We can view objects in the real and virtual world at the same time. And unlike VR, MR HMD does not occur the motion sickness. It is using a wireless and attracting attention as a technology to be applied in industrial fields. Myo wearable device is a device that enables arm rotation tracking and hand gesture recognition by using a triaxial sensor, an EMG sensor, and an acceleration sensor. Although various studies related to MR are being progressed, discussions on developing an environment in which multiple people can participate in mixed reality and manipulating virtual objects with their own hands are insufficient. In this paper, We propose a method of constructing an environment where collaboration is possible and an interaction method for smooth interaction in order to apply mixed reality in real industrial fields. As a result, two people could participate in the mixed reality environment at the same time to share a unified object for the object, and created an environment where each person could interact with the Myo wearable interface equipment.

• Journal of Drive and Control
• /
• v.11 no.2
• /
• pp.22-29
• /
• 2014

This paper presents simulation-based analysis of energy flow of a wheel loader. The objective of this study is to analyze the energy flow of a wheel loader during driving and working. Because the wheel loader powertrain consists of a mechanical and hydraulic powertrain, the generated power from the engine is divided into 2 powertrains. Further, a virtual prediction of energy flow in the powertrains is a key factor in terms of optimal design. Accordingly, the simulation model that is able to predict the virtual energy flow is developed and analyzed in this study. The proposed wheel loader simulation model has been constructed in the Matlab/Simulink environment. It is expected that the developed simulation model will analyze the energy flow and efficiency in the design stage.

• Journal of Drive and Control
• /
• v.16 no.1
• /
• pp.36-44
• /
• 2019

Variable displacement swash plate piston pump analysis requires electric, hydraulics and dynamics which are similar to the one's incorporated in the complex fluid power and mechanical systems. The main variable capacity for the swash plate piston pumps, hydraulics or simple kinematic (swash plate degree, piston displacement) models are analyzed using AMESim, a multi-physics analysis program. AMESim is a multi-physics hydraulic analysis program that is considered good for the environment but not appropriate for environmental analysis for multibody dynamics. In this study, the analytical model of the swash plate type hydraulic piston pump variable capacity is modeled by combining the hydraulic part and the dynamic part through co-simulation of multibody dynamics program (Virtual.lab Motion) and multi-physics analysis (AMESim). This paper describes the whole modeling analysis method on the mechanical analysis of the multi-body dynamics program and how the hydraulic analysis in multi-physics analysis program works. This paper also presents a methodology for analyzing complex fluid power systems.

• Journal of Drive and Control
• /
• v.21 no.2
• /
• pp.15-22
• /
• 2024

The objective of this study was to examine whether a gerotor pump used in a transmission could be converted into an electric vehicle thermal management system pump using a virtual design environment. To achieve this objective, we first built an environment that could analyze the performance of a gerotor pump in heat transfer fluid. Flow rate, pressure, and volumetric efficiency were then analyzed when using heat transfer fluid in a gerotor pump. Finally, how large the displacement volume of the pump should be designed when using a heat transfer fluid other than oil was determined. Based on results of this study, it is expected that gerotor pumps will be applied to new business fields such as electric vehicle cooling systems.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2004.11a
• /
• pp.543-547
• /
• 2004

Visualization of construction process simulation and physical modeling were considered to overcome the limitations of current graphical simulation. The output of discrete-event simulation programs which are the most common mathematical statistical simulation tool for construction processes were analyzed for the visualization of earthmoving process that dealing with objects without fixed. Object-oriented models for equipment, material and work environments were devised to effectively visualize the numerical simulation results of the working time, the queuing time as well as the amount resources etc. The oscillation of the crane's cable and the lifted material that should be considered to rationally modeled and simulated by construction graphical simulation. The derived equation of motion was solved by numerical analysis procedure. Then obtained results was used for physical modeling.

• Journal of Drive and Control
• /
• v.17 no.1
• /
• pp.44-50
• /
• 2020

For the requirement of accurate tracking control and the safety of physical human-robot interaction, torque control is basically desirable for humanoid robots. Because of the complexity of humanoid robot dynamics, the TDC (time-delay control) is practical because it does not require a dynamic model. However, there occurs a considerable error due to discontinuous non-linearities. To solve this problem, the TDC-FLC (fuzzy logic compensator) is applied to humanoid robots. The applied controller contains three factors: a TDE (time-delay estimation) factor, a desired error dynamic factor, and FLC to suppress the TDE error. The TDC-FLC is easy to execute because it does not require complicated humanoid dynamic calculations and the heuristic fuzzy control rules are intuitive. TDC-FLC is implemented on the whole body of a humanoid, not on biped legs even though it is performed by a virtual humanoid robot. The simulation results show the validity of the TDC-FLC for humanoid robots.