• 제어로봇시스템학회논문지
• /
• 제16권5호
• /
• pp.420-427
• /
• 2010

This paper describes a localization method based on Monte Carlo Localization approach for a mobile robot. The method uses range data which are measured from ultrasound transmitting beacons whose locations are given a priori. The ultrasound receiver on-board a robot detects the range from the beacons. The method requires several beacons, theoretically over three. The method proposes a sensor model for the range sensing based on statistical analysis of the sensor output. The experiment uses commercialized beacons and detector which are used for trilateration localization. The performance of the proposed method is verified through real implementation. Especially, it is shown that the performance of the localization degrades as the sensor update rate decreases compared with the MCL algorithm update rate. Though the method requires exact location of the beacons, it doesn't require geometrical map information of the environment. Also, it is applicable to estimation of the location of both the beacons and robot simultaneously.

• 로봇학회논문지
• /
• 제3권3호
• /
• pp.194-202
• /
• 2008

This paper describes a new method for indoor environment mapping and localization with stereo camera. For environmental modeling, we directly use the depth and color information in image pixels as visual features. Furthermore, only the depth and color information at horizontal centerline in image is used, where optical axis passes through. The usefulness of this method is that we can easily build a measure between modeling and sensing data only on the horizontal centerline. That is because vertical working volume between model and sensing data can be changed according to robot motion. Therefore, we can build a map about indoor environment as compact and efficient representation. Also, based on such nodes and sensing data, we suggest a method for estimating mobile robot positioning with random sampling stochastic algorithm. With basic real experiments, we show that the proposed method can be an effective visual navigation algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권1호
• /
• pp.1-8
• /
• 2002

It has been integrated into several navigation systems. This paper shows that system recognizes difficult indoor roads without any specific marks such as painted guide line or tape. In this method the robot navigates with visual sensors, which uses visual information to navigate itself along the read. The Neural Network System was used to learn driving pattern and decide where to move. In this paper, I will present a vision-based process for AMR(Autonomous Mobile Robot) that is able to navigate on the indoor read with simple computation. We used a single USB-type web camera to construct smaller and cheaper navigation system instead of expensive CCD camera.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.92-100
• /
• 2023

Wireless communication technology is becoming increasingly prevalent in smart factories, but the rise in the number of wireless devices can lead to interference in the ISM band and obstacles like metal blocks within the factory can weaken communication signals, creating radio shadow areas that impede information exchange. Consequently, accurately determining the radio communication coverage range is crucial. To address this issue, a Radio Environment Map (REM) can be used to provide information about the radio environment in a specific area. In this paper, a technique for estimating an indoor REM usinga mobile robot and machine learning methods is introduced. The mobile robot first collects and processes data, including the Received Signal Strength Indicator (RSSI) and location estimation. This data is then used to implement the REM through machine learning regression algorithms such as Extra Tree Regressor, Random Forest Regressor, and Decision Tree Regressor. Furthermore, the numerical and visual performance of REM for each model can be assessed in terms of R2 and Root Mean Square Error (RMSE).

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2009년도 제40회 하계학술대회
• /
• pp.1812_1813
• /
• 2009

This paper presents an accurate indoor localization method of a mobile robot using ultrasonic sensors. The coordinates of mobile robot are calculated by using trilateration which is using the distance between the transmitter and receiver. At this time, the distances can't be accurately calculated by containing noise. We propose Extended Kalman Filter(EKF) to improve estimation accuracy. The performance of proposed EKF is evaluated by simulation program. As a result, we confirm that the errors in estimate of mobile robot's position are eliminated from measured distance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.261-265
• /
• 2005

In this paper, we constructed the infrastructure with wireless LAN and Access Point in the indoor environment and implemented the teleoperation. Wireless LAN based teleoperation system is irregular communication delay according to environment condition and occurrence possibility of blackout is very high. In this paper, In case these problem happened, we measured communication delay time by real time, and did mobile robot to control harmoniously through vision and force reflection information. Also, we present obstacle-avoidance mode that mobile robot can travel without collision using direction information in case communication delay time is large. We proved usefulness of presented algorithm through teleoperation experiment to apply presented algorithm.

• 대한전자공학회논문지TE
• /
• 제42권4호
• /
• pp.33-40
• /
• 2005

본 논문에서는 이동 로봇 주위의 환경 인식과 자기 위치 인식을 위하여 초음파 센서와 한 개의 카메라를 이용하여 안정적인 이동 경로를 확보할 수 있는 방식을 제시하였다. 개발된 초음파 센서(SRF04)시스템은 주행환경의 지도 작성을 위하여 목표물의 특징 데이터를 작성하고, SDC313(SAMSUNG) 카메라에서 수집된 영상자료와 결합하도록 하여 안정적인 경로탐색이 가능한 이동로봇 제어방식을 실험을 통하여 구현하였다.

• 제어로봇시스템학회논문지
• /
• 제6권7호
• /
• pp.586-593
• /
• 2000

In this paper we propose a new approach to the autonomous wall-following of wheeled mobile robots using hybrid system reference motion synthesis and generation. The hybrid system approach is in-troduced to the motion control of nonholonomic mobile robots for the indoor navigation problems. In the dis-crete event system the discrete states are defined by the user-defined constraints and the reference mo-tion commands are specified in the abstracted motions. The hybrid control system applied for the non-holonomic mobile robots can combine the motion planning and autonomous navigation with obstacle avoid-ance for the indoor navigation problem. Simulation results show that hybrid system approach is an effective method for the autonomous navigation in indoor environments.

• 한국전자통신학회논문지
• /
• 제7권2호
• /
• pp.391-399
• /
• 2012

본 논문에서는 파티클 필터 방법을 이용한 이동로봇의 SLAM(Simultaneous Localization and Mapping) 방법을 제안한다. 이동로봇의 SLAM은 지도가 주어지지 않는 환경에서 로봇 스스로 자신의 위치를 파악하는 것과 동시에 지도를 만드는 것이다. 제안된 방법은 로봇의 위치를 추정함과 동시에 특징점인 외부 비이컨들의 위치를 추정하는 방법을 다루고 있다. 특히 파티클 필터 방법을 적용하여 이동로봇과 특징점 위치를 파티클의 분포에 의해 확률적으로 표현한다. 제안된 SLAM방법은 이동로봇의 동작 뿐 아니라 특징점 위치의 불확실성을 고려한다. 따라서 매 샘플링 시각에 특징점의 위치 정보도 불확실성을 고려하여 예측되어진다. 제안된 방법의 성능을 시뮬레이션과 실험을 통하여 평가하였다. 제안된 방법은 비이컨으로 부터의 거리 정보에 불규칙한 잡음이 있는 환경에서도 실질적으로 사용가능한 지도 정보를 제공하였다. 또한 통상의 최소자승법이나 데드레크닝 방법에 비해서 보다 정확하고 강건하게 로봇의 위치를 추정하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.249-251
• /
• 2009

Mobile patrol robots are mainly used in aerospace and military engineering because they can work at dangerous environment replacing a man. This paper presents a study on the remote monitoring and control system of a mobile patrol robot platform using TCP/IP. The mobile robot consists of intel PXA270 and linux-based system. It can get environment information such as images, temperature, humidity and slope by using two cameras and various sensors. And it transmits information data to a monitoring system through the ad-hoc network which is one of wireless network solutions. At this time, a mobile robot is a server and a monitoring system is a client. Users can monitor environment information which is received from a mobile robot by an application based on PC. We have used TCP/IP protocol, socket programming, interface technique of process and devices and control algorithm to embody the mobile robot and its monitoring system. Experimental results shows that the system can be utilized as a remote patrol monitoring tool.