• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 1999년도 추계학술대회논문집
• /
• pp.315-320
• /
• 1999

Obstacle Detection System(ODS) is a essential system for automated vehicle, such as AGV(Automatic Guided Vehicle), mobile robot. Automated vehicle must have a capability to detect and to avoid obstacles to guarantee a safe driving condition. To implement obstacle detection system, virtual bumper concept adapted. Like real bumper in a car, such as in the truck, it protects vehicle from collision using laser distance sensor. When an obstacle(such as other vehicle, building, etc) intrudes this virtual bumper area, a virtual force is calculated and produces necessary strategy to be able to avoid collision. In this paper, simplified virtual bumper concept is presented, and various problems when happens to implement are discussed.

• 한국전산구조공학회논문집
• /
• 제21권5호
• /
• pp.421-427
• /
• 2008

BIRDI(Bridge Inspection Robot Development Inter)ace)에서 현재 개발된 첨단굴절로봇차는 기존의 굴절차에 비해 소형이며, 12m에 이르는 작업붐으로 인해 교량의 진동, 풍하중 등에 의해 쉽게 진동이 발생할 것으로 예상된다. 본 연구에서는 첨단굴절로봇차의 머신비전 시스템을 통한 점검 성능 확보를 위해 작업붐에 엑츄에이터를 장착하여 유해 진동을 제어할 수 있는 시스템을 제안하였으며, 성능 평가를 위해 수치적, 실험적 연구를 수행하였다. 제안된 제어시스템의 수치적 연구를 위해 현재 제작된 작업붐의 제원을 이용하여 모델링하였고, 적당한 주파수 특성을 가진 하중을 가정하였으며, 최적 제어이론인 LQ 조정기를 설계하였다. 수치해석 결과, 제안된 제어시스템은 작업붐에 발생되는 유해 진동을 저감시킬 수 있었다. 실험적 연구를 위해 작업붐의 축소 모형을 제작하였고 제어시스템을 구축하였다. 또한 실험결과 작업붐의 진동을 짧은 시간에 제어하는 우수한 성능을 보였다. 본 연구를 통해 제안된 시스템의 진동제어 성능을 입증하였으며, 실제 첨단굴절로봇차에 적용될 경우 점검 시스템의 성능을 향상시킬 수 있을 것으로 사료된다.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.294-302
• /
• 2022

The article explores the prospects and trends for the transformation of some basic concepts of law associated with the development of artificial intelligence systems and the problems of liability for harm caused by a robot. The prospects, conditions and consequences of vesting robots with partial (quasi) or full legal personality are explored. This process should lead to a revision of the concepts of will, subjective side and legal responsibility in the direction of their greater universalization. The legally significant signs of will, legal personality, legal liability in relation to robots, artificial intelligence systems and other complex automated information systems are clarified. The author identifies the following essential factors of legal qualification of an act committed by a robot: goals, reasons for setting goals, connections between the planned result and the action taken, the actual result, the reasons for the difference between the actual result and the planned one. The article pays special attention to the preventive function of legal liability, which, when applied to robot subjects, can be expressed in the following basic procedures. 1. Accounting for legal requirements in the behavior of the robot. 2. Timely adaptation of the robot to changes in legislation and other regulatory legal acts that affect its behavior. 3. Accounting for incidents. 4. Destruction of a series of robots whose actions lead to unacceptable consequences.

• 한국전자통신학회논문지
• /
• 제18권2호
• /
• pp.231-240
• /
• 2023

심층 강화 학습(Deep Reinforcement Learning)을 사용한 경로 계획에서 장애물을 자동으로 회피하기 위해 로봇을 학습시키는 일은 쉬운 일이 아니다. 많은 연구자가 DRL을 사용하여 주어진 환경에서 로봇 학습을 통해 장애물 회피하여 경로 계획을 수립하려는 가능성을 시도하였다. 그러나 다양한 환경에서 로봇과 장착된 센서의 오는 다양한 요인 때문에 주어진 시나리오에서 로봇이 모든 장애물을 완전히 회피하여 이동하는 것을 실현하는 일은 흔치 않다. 이러한 문제 해결의 가능성과 장애물을 회피 경로 계획 실험을 위해 테스트베드를 만들었고 로봇에 카메라를 장착하였다. 이 로봇의 목표는 가능한 한 빨리 벽과 장애물을 피해 시작점에서 끝점까지 도달하는 것이다. 본 논문에서는 벽과 장애물을 회피하기 위한 DRL의 가능성을 검증하기 위해 이중 심층 Q 네트워크(DDQN)를 제안하였다. 실험에 사용된 로봇은 Jetbot이며 자동화된 경로 계획에서 장애물 회피가 필요한 일부 로봇 작업 시나리오에 적용할 수 있을 것이다.

• 한국안전학회지
• /
• 제32권1호
• /
• pp.1-8
• /
• 2017

In industry AGV's(automated guided vehicles) that can detect and follow guidelines drawn on the factory floor using magnetic or optical sensors are widely used. However, such AGV's without preview capability cannot effectively avoid collision with obstacles that may occasionally pass through the guideline. Furthermore, without preview information, they consume much energy at the right angle corners as they have to make sudden directional change. Also, the risk of dropping payloads increases in such situations. In this study, infrared preview sensors were adopted to a mobile robot for detecting not only the current position but also the forward position of the guideline and the preview control technique was applied to optimally control the mobile robot's motion using the information from the infrared preview sensors. Then the effectiveness of this approach was investigated through a series of experiments. The experimental result shows that the proposed approach is effective for safety enhancement as well as for better efficiency.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.929-934
• /
• 2004

As 3D scanner develops, it can be used in measurement. To accomplish complete 3D measurement, the scanner has to view different sides of the target. It can be done by moving the scanner and fix it at every measuring point. By human, it would take so much time. However, by using robot, measuring time can be reduced and the procedure can be automated. It is suitable for 6R serial manipulator to do this kind of work in which the scanner should go any position in arbitrary orientation. We did inverse kinematics analysis by analytical and graphical methods. Then, we compared two methods.

• 동력기계공학회지
• /
• 제2권3호
• /
• pp.83-88
• /
• 1998

This paper presents an efficient control algorithm that removes irregular burrs using vision and force sensors. In automated robotic deburring, the reference force should be accommodated to the profile of burrs in order to prevent the tool breakage. In this paper, (1) The profile of burrs is recognized by vision sensor and followed by the calculation of reference force, (2) Deburring expert's skill is transferred to robot. Finally, the performance of robot is evaluated through simulation and experiment.

• 품질경영학회지
• /
• 제31권3호
• /
• pp.114-125
• /
• 2003

In this paper, we deal with the problem of modeling of agent-based robot manufacturing cell. Its role is becoming increasingly important in automated manufacturing systems. For Object Oriented & Queueing Petri Nets (OO&QPNs), an extended formalism for the combined quantitative and qualitative analysis of different systems is used for structure and performance analysis of mobile robotic cell. In the case study, the OO&QPN model of a mobile robotic cell is represented and analyzed, considering multi-class parts, non-preemptive priority and alternative routing. Finally, the comparison of performance values between Shortest Process Time (SPT) rule and First Come First Serve (FCFS) rule is suggested. In general, SPT rule is most suitable for parts that have shorter processing time than others.

• 한국공작기계학회논문집
• /
• 제14권3호
• /
• pp.54-59
• /
• 2005

The cylindrical object are widely used as mechanical parts in the manufacturing process. In order to handling those objects using a robot or an automated machine automatically, the pose of the object must be known. The pose can be described by two rotation angles; one angle about the x axis and the other about the y axis. In the many previous researches these angles were obtained by the computationally intensive algorithm, that is, fitting the data as a polynomial and doing pseudo inverse. So that, this method required high performance microprocessor. In this paper in order to avoid complex computation, a new method based on a genetic algorithm is proposed and analyzed through a series of simulations. This algorithm utilized the geometry of the cylindrical shape. The simulation results show that this method find the pose angles very well In most cases, but the computation time is randomly changed because the genetic algorithm is basically one of the random search method.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2008년도 하계학술대회 논문집
• /
• pp.160-163
• /
• 2008

Currently workmen take charge of the maintenance work of bridges. But the process of sealing cracks in damage bridge is dangerous, costly, and labor-intensive operation Labor turnover and training are increasing problems related to crack sealing crews, and as traffic volumes increase, crack sealing operations become increasingly disruptive to the general public. Automation crack sealing can reduce labor and road user costs, improve work quality and decrease worker exposure to bridge hazards. This research aims to develop an automated damage bridge crack sealing system and developing of algorithms for hybrid controlling.