Modeling of vision based robot formation control using fuzzy logic controller and extended Kalman filter

Rusdinar, Angga,Kim, Sung-Shin Korean Institute of Intelligent Systems 2012 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.12 No.3

A modeling of vision based robot formation control system using fuzzy logic controller and extended Kalman filter is presented in this paper. The main problems affecting formation controls using fuzzy logic controller and vision based robots are: a robot's position in a formation need to be maintained, how to develop the membership function in order to obtain the optimal fuzzy system control that has the ability to do the formation control and the noise coming from camera process changes the position of references view. In order to handle these problems, we propose a fuzzy logic controller system equipped with a dynamic output membership function that controls the speed of the robot wheels to handle the maintenance position in formation. The output membership function changes over time based on changes in input at time t-1 to t. The noises appearing in image processing change the virtual target point positions are handled by Extended Kalman filter. The virtual target positions are established in order to define the formations. The virtual target point positions can be changed at any time in accordance with the desired formation. These algorithms have been validated through simulation. The simulations confirm that the follower robots reach their target point in a short time and are able to maintain their position in the formation although the noises change the target point positions.

Vision-Based Indoor Localization Using Artificial Landmarks and Natural Features on the Ceiling with Optical Flow and a Kalman Filter

Rusdinar, Angga,Kim, Sungshin Korean Institute of Intelligent Systems 2013 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.13 No.2

This paper proposes a vision-based indoor localization method for autonomous vehicles. A single upward-facing digital camera was mounted on an autonomous vehicle and used as a vision sensor to identify artificial landmarks and any natural corner features. An interest point detector was used to find the natural features. Using an optical flow detection algorithm, information related to the direction and vehicle translation was defined. This information was used to track the vehicle movements. Random noise related to uneven light disrupted the calculation of the vehicle translation. Thus, to estimate the vehicle translation, a Kalman filter was used to calculate the vehicle position. These algorithms were tested on a vehicle in a real environment. The image processing method could recognize the landmarks precisely, while the Kalman filter algorithm could estimate the vehicle's position accurately. The experimental results confirmed that the proposed approaches can be implemented in practical situations.

Implementation of real-time positioning system using extended Kalman filter and artificial landmark on ceiling

Rusdinar, Angga,Kim, Jung-Min,Lee, Jun-Ha,Kim, Sung-Shin 대한기계학회 2012 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.26 No.3

Most localization algorithms use a range sensor or vision in a horizontal view, which usually imparts some disruption from a dynamic or static obstacle. By using landmarks on ceiling which the vehicle position were vertically measured, the disruption from horizontal view was reduced. We propose an indoor localization and navigation system based on an extended Kalman filter (EKF) and real-time vision system. A single upward facing digital camera was mounted on an autonomous vehicle as a vision sensor to recognize the landmarks. The landmarks consisted of multiple circles that were arranged in a defined pattern. Information on a landmark's direction and its identity as a reference for an autonomous vehicle was produced by the circular arrangements. The pattern of the circles was detected using a robust image processing algorithm. To reduce the noise that came from uneven light, the process of noise reduction was separated into several regions of interest. The accumulative error caused by odometry sensors (i.e., encoders and a gyro) and the vehicle's position were calculated and estimated, respectively, using the EKF algorithm. Both algorithms were tested on a vehicle in a real environment. The image processing method could precisely recognize the landmarks, and the EKF algorithm could accurately estimate the vehicle's position. The experimental results confirmed that the proposed approaches are implementable.

Error Pose Correction of Mobile Robot for SLAM Problem using Laser Range Finder Based on Particle Filter

Angga Rusdinar,Jungmin Kim,Sungshin Kim 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

This paper presents the implementation of the particle filter (PF) to solve the simultaneous localization and mapping (SLAM) problem in mobile robot, particle filter is used to localize the mobile robot with a laser range finder (LRF) sensor. On this experiment we used the real data that taken from our robot. We used the weighted mean in a small window around the best particle called robust mean as the method of selection and calculation weight in every particle. The experiment result shows that the proposed particle filter can improve the performance and give more robustness of mobile robot localization inside our building.

Vision-Based Indoor Localization Using Artificial Landmarks and Natural Features on the Ceiling with Optical Flow and a Kalman Filter

Angga Rusdinar,Sungshin Kim 한국지능시스템학회 2013 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.13 No.2

This paper proposes a vision-based indoor localization method for autonomous vehicles. A single upward-facing digital camera was mounted on an autonomous vehicle and used as a vision sensor to identify artificial landmarks and any natural corner features. An interest point detector was used to find the natural features. Using an optical flow detection algorithm, information related to the direction and vehicle translation was defined. This information was used to track the vehicle movements. Random noise related to uneven light disrupted the calculation of the vehicle translation. Thus, to estimate the vehicle translation, a Kalman filter was used to calculate the vehicle position. These algorithms were tested on a vehicle in a real environment. The image processing method could recognize the landmarks precisely, while the Kalman filter algorithm could estimate the vehicle’s position accurately. The experimental results confirmed that the proposed approaches can be implemented in practical situations.

Modeling of vision based robot formation control using fuzzy logic controller and extended Kalman filter

Angga Rusdinar,Sungshin Kim 한국지능시스템학회 2012 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.12 No.3

A modeling of vision based robot formation control system using fuzzy logic controller and extended Kalman filter is presented in this paper. The main problems affecting formation controls using fuzzy logic controller and vision based robots are: a robot’s position in a formation need to be maintained, how to develop the membership function in order to obtain the optimal fuzzy system control that has the ability to do the formation control and the noise coming from camera process changes the position of references view. In order to handle these problems, we propose a fuzzy logic controller system equipped with a dynamic output membership function that controls the speed of the robot wheels to handle the maintenance position in formation. The output membership function changes over time based on changes in input at time t-1 to t. The noises appearing in image processing change the virtual target point positions are handled by Extended Kalman filter. The virtual target positions are established in order to define the formations. The virtual target point positions can be changed at any time in accordance with the desired formation. These algorithms have been validated through simulation. The simulations confirm that the follower robots reach their target point in a short time and are able to maintain their position in the formation although the noises change the target point positions.

Characteristic of Friction on Texturing Bearing Steel with Ultrasonic Hole Machine

신미정,Angga Rusdinar,권순홍,정성원,권순구,박종민,김종순,최원식 한국트라이볼로지학회 2015 한국트라이볼로지학회지 (Tribol. Lubr.) Vol.31 No.1

We carry out experiments to characterize textured bearing steel with varying hole density and depth. Textured surface is believed to reduce the friction coefficient, and improve performance and wearing caused by third-body contact. We employ three lubrication regime conditions based on the Stribeck curve: boundary lubrication, mixed lubrication, and hydrodynamic lubrication. Ultrasonic machining is an untraditional machiningmethod wherein abrasive grit particles are used. The hammering process on the work piece surface by abrasive provides the desired form. In this study, we create multi-holes on the bearing steel surface for texturing purposes. Holes are formed by an ultrasonic machine with a diameter of 0.534 mm and a depth of about 2-4 mm, and they are distributed on the contact surface with a density between 1.37-2.23%. The hole density over the surface area is an important factor affecting the friction. We test nine types of textured specimens using four times replication and compare them with the untextured specimen using graphs, as well as photographs taken using a scanning electron microscope. We use Analyzes variant in this experiment to find the correlation between each pair of treatments. Finally, we report the effect of hole density and depth on the friction coefficient.