• Title/Summary/Keyword: Collection robot

Search Result 63, Processing Time 0.029 seconds

Development of a Monitoring System for a Pipe Cleaning Robot with RS-485 (RS-485 통신을 이용한 배관청소 로봇의 모니터링 시스템 개발)

  • Kim, Min-wook;Lee, Hun-seok;Oh, Jin-seok
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.20 no.5
    • /
    • pp.923-930
    • /
    • 2016
  • Various pipes are used in the many industrial field such as water supply, drainage system and marine plants, so a maintenance of these pipes is essential. Especially, the maintenance of the piping in the industrial field, some professional staffs enter and clean the pipe. If the professional staffs can not enter and clean the pipe, the workers has to use the method of inserting a scraper connected to wire inside the pipe. However, this method demands huge budget and causes a number of problems such as traffic congestion. To solve these problems, pipe cleaning robot has been researching and developing. Many Pipe cleaning robots have a problem, that is impossible to confirm the operating condition of the robot in a real time. This paper suggest pipe cleaning robot with RS-485 which transmit operating and cleaning condition of robot and inner pipe filmed by camera, that user can check.

Protector Design and Shock Analysis for a Launch-Reconnaissance Robot (발사형 정찰로봇을 위한 보호체 설계 및 충격해석)

  • Kang, Bong-Soo;Park, Moon-Sik
    • Transactions of the Korean Society of Mechanical Engineers A
    • /
    • v.35 no.8
    • /
    • pp.971-976
    • /
    • 2011
  • This paper presents the design concepts of a protector for a launch-reconnaissance robot that is to be deployed for data-collection in hazardous regions. The protector protects the reconnaissance robot inside from shock induced during the process of launch, flight, and landing. Since the outer shells of the protector are automatically opened wide by the unlocking mechanism during the landing stage, the reconnaissance robot can easily exit the protector and move around to carry out its mission. We carefully simulated a finite-element model of the protector with the robot and compared the results with the actual dynamic behavior of the system. Shock- response tests using a droptable showed that the proposed protector filled with silicon material successfully attenuated external shock.

Robot Controller Design with Embedded RTOS (임베디드 RTOS 기반의 로봇 컨트롤러 설계)

  • Hong, Seon Hack;Youn, Jin Sub
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.6 no.4
    • /
    • pp.143-151
    • /
    • 2010
  • In this paper, We designed the robot controller with Linux OS, Cygwin under the Marvell Monahan PXA320 embedded platform. Cygwin is a collection of tools for using the Linux-like environment for commercially released x86 32 bit and 64 bit versions of Windows and is a DLL that acts as a Linux API emulation layer providing substantial Linux API functionality. TinyOS-2. x is a component based embedded OS by UC Berkeley and is an open-source OS designed for interfacing the sensor application with specific C-language. The results of experiment are described to show the improvement of sensor interfacing functionality under the PXA320 embedded RTOS platform.

Mapless Navigation with Distributional Reinforcement Learning (분포형 강화학습을 활용한 맵리스 네비게이션)

  • Van Manh Tran;Gon-Woo Kim
    • The Journal of Korea Robotics Society
    • /
    • v.19 no.1
    • /
    • pp.92-97
    • /
    • 2024
  • This paper provides a study of distributional perspective on reinforcement learning for application in mobile robot navigation. Mapless navigation algorithms based on deep reinforcement learning are proven to promising performance and high applicability. The trial-and-error simulations in virtual environments are encouraged to implement autonomous navigation due to expensive real-life interactions. Nevertheless, applying the deep reinforcement learning model in real tasks is challenging due to dissimilar data collection between virtual simulation and the physical world, leading to high-risk manners and high collision rate. In this paper, we present distributional reinforcement learning architecture for mapless navigation of mobile robot that adapt the uncertainty of environmental change. The experimental results indicate the superior performance of distributional soft actor critic compared to conventional methods.

Oil Spill Skimmer using Magnetic Oil Adsorbent (자성유류흡착제를 사용한 수면유출기름 처리 스키머)

  • Soh, Dae-Wha;Soh, Hyun-Jun
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2008.10a
    • /
    • pp.555-558
    • /
    • 2008
  • For trying to frontal attack of new solution by fusion of technical tasks and conditions with it's solving methods of the essential tasks of marine resource development and environmental conservation in addition with elements of electronic high-technologies, the skimmer robot was proposed by using of oil spill disaster prevention and its disposal system with sequentially circular collection type of magnetic oil spill adsorbent powder and fabrics on the electronic barge robot for the scheme of sustainable development of environment-friendly technology. It was verified from the experiment of electronic barge robot demonstrator that the skimmer system of magnetic oil spill adsorbent powder and fabrics was very effective and useful technique to collect oil spill samples. At this point, the barge-based electronic remote control was very useful system operating easily on the marine fields to skim oil spill with dangerous toxic substances of crude oil and very harmful to human. Therefore, fusion technology proposed in this study combined with electronic and marine technology is the novel contributable technology for developing marine environmental conservation and environment-friendly disaster prevention, and also its management techniques.

  • PDF

Engineering Students' Ethical Sensitivity on Artificial Intelligence Robots (공학전공 대학생의 AI 로봇에 대한 윤리적 민감성)

  • Lee, Hyunok;Ko, Yeonjoo
    • Journal of Engineering Education Research
    • /
    • v.25 no.6
    • /
    • pp.23-37
    • /
    • 2022
  • This study evaluated the engineering students' ethical sensitivity to an AI emotion recognition robot scenario and explored its characteristics. For data collection, 54 students (27 majoring in Convergence Electronic Engineering and 27 majoring in Computer Software) were asked to list five factors regarding the AI robot scenario. For the analysis of ethical sensitivity, it was checked whether the students acknowledged the AI ethical principles in the AI robot scenario, such as safety, controllability, fairness, accountability, and transparency. We also categorized students' levels as either informed or naive based on whether or not they infer specific situations and diverse outcomes and feel a responsibility to take action as engineers. As a result, 40.0% of students' responses contained the AI ethical principles. These include safety 57.1%, controllability 10.7%, fairness 20.5%, accountability 11.6%, and transparency 0.0%. More students demonstrated ethical sensitivity at a naive level (76.8%) rather than at the informed level (23.2%). This study has implications for presenting an ethical sensitivity evaluation tool that can be utilized professionally in educational fields and applying it to engineering students to illustrate specific cases with varying levels of ethical sensitivity.

Development of Web Crawler for Archiving Web Resources (웹 자원 아카이빙을 위한 웹 크롤러 연구 개발)

  • Kim, Kwang-Young;Lee, Won-Goo;Lee, Min-Ho;Yoon, Hwa-Mook;Shin, Sung-Ho
    • The Journal of the Korea Contents Association
    • /
    • v.11 no.9
    • /
    • pp.9-16
    • /
    • 2011
  • There are no way of collection, preservation and utilization for web resources after the service is terminated and is gone. However, these Web resources, regardless of the importance of periodically or aperiodically updated or have been destroyed. Therefore, to collect and preserve Web resources Web archive is being emphasized. Web resources collected periodically in order to develop Web archiving crawlers only was required. In this study, from the collection of Web resources to be used for archiving existing web crawlers to analyze the strengths and weaknesses. We have developed web archiving systems for the best collection of web resources.

$M^2$ MAC: MAC protocol for Real Time Robot Control System based on Underwater Acoustic Communication ($M^2$ MAC(Message Merging): 수중음파통신 기반의 실시간 로봇 제어 시스템을 위한 MAC 프로토콜)

  • Kim, Yung-Pyo;Park, Soo-Hyun
    • Journal of the Institute of Electronics Engineers of Korea CI
    • /
    • v.48 no.6
    • /
    • pp.88-96
    • /
    • 2011
  • Underwater acoustic communication is applicable in various areas, such as ocean data collection, undersea exploration and development, tactical surveillance, etc. Thus, robot control system construction used for underwater-robot like AUV or ROV is essential in these areas. In this paper, we propose the Message Merging MAC($M^2$-MAC) protocol, which is suitable for real time robot control system, considering energy efficiency in important parts of underwater acoustic sensor network constitution. In this proposed MAC protocol, gateway node receives the data from robot nodes according to the time slots that were allotted previously. And messages delivered from base-station are generated to one MAC frame by buffering process. Finally, generated MAC frames are broadcasted to all robot nodes in the cluster. Our suggested MAC protocol can also be hybrid MAC protocol, which is successful blend of contention based and contention-free based protocol through relevant procedure with Maintenance&Sleep (M&S) period, when new nodes join and leave as an orphan. We propose mathematical analysis model concerned about End-to-End delay and energy consumption, which is important factor in constructing real-time robot control system. We also verify the excellence of performance according to comparison of existing MAC protocols with our scheme.

Design and Realization of Retrieval Engine On Demand Using a Dynamic Robot Agent (동적 로봇에이전트를 이용한 주문형 검색엔진의 설계 및 구현)

  • Kim, Sung;Park, Chol-Woo;Lee, Chung-Seok;Park, Kyoo-Seok
    • The KIPS Transactions:PartD
    • /
    • v.8D no.5
    • /
    • pp.631-636
    • /
    • 2001
  • The technologies relevant to e-business have rapidly developed during very short period of time and recently it is expanding to the area of B2B. Keeping pace with this development in e-business, the information of comparison or analysis on commodities of a lot of sites is also required. Though the information on price comparison among internal shopping malls are now being offered, its not efficient for its renewing intervals are long and, due to some indiscreet collection of information for the purpose of fast renewal, much loads are being generated on the pertinent shopping malls. In this article, the retrieval engine on demand is designed and realized using a dynamci robot agent changing kinetically on the status of the pertinent shopping malls that can offer the customized service and presents the shopping malls with the lowest price for each commodity under e-business after the shortest time of collection and analysis while not giving loads to the pertinent shopping malls.

  • PDF

Therapeutic Robot Action Design for ASD Children Using Speech Data (음성 정보를 이용한 자폐아 치료용 로봇의 동작 설계)

  • Lee, Jin-Gyu;Lee, Bo-Hee
    • Journal of IKEEE
    • /
    • v.22 no.4
    • /
    • pp.1123-1130
    • /
    • 2018
  • A cat robot for the Autism Spectrum Disorders(ASD) treatment was designed and conducted field test. The designed robot had emotion expressing action through interaction by the touch, and performed a reasonable emotional expression based on Artificial Neural Network(ANN). However these operations were difficult to use in the various healing activities. In this paper, we describe a motion design that can be used in a variety of contexts and flexibly reaction with various kinds of situations. As a necessary element, the speech recognition system using the speech data collection method and ANN was suggested and the classification results were analyzed after experiment. This ANN will be improved through collecting various voice data to raise the accuracy in the future and checked the effectiveness through field test.