Sirma Yavuz | Yildiz Technical University (original) (raw)

Papers by Sirma Yavuz

2022 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)

Journal of Medical Imaging and Health Informatics, 2021

Compared with traditional motion planners and deep reinforcement learning DRL has been applied mo... more Compared with traditional motion planners and deep reinforcement learning DRL has been applied more and more widely to achieving sequential behaviors control of movement robots in internal environment. There are two addressed issues of deep learning. The inability to generalize to achieve set of goals. The data inefficiency, that is, the model requires, many trial and error loops (often costly). Applied can impact a few key areas of medicine and explore how to build end-to-end systems. Our discussion of computer vision focuses largely on medical imaging. In this paper, we address these two issues and apply the proposed model to visual navigation in conformity with generalizing in conformity with obtaining new goals (target-driven). To tackle the first issue, we advise an actor-critic mannequin whose coverage is a feature of the intention as much properly namely the present day state, which approves higher generalization. To tackle the second issue, we advocate the 3D scenes in envir...

Signal Processing and Communications Applications Conference, Apr 9, 2009

El objetivo de este trabajo es disenar e implementar un sistema de informacion que permita el reg... more El objetivo de este trabajo es disenar e implementar un sistema de informacion que permita el registro de los diagnosticos e intervenciones, realizados por los estudiantes de enfermeria en el ejercicio de las practicas clinicas y comunitarias; y muestre las frecuencias estadisticas asociadas a ellos. El proyecto realizado aporta a la escuela de enfermeria las herramientas necesarias para dar respuesta a las necesidades academicas y asistenciales propias de la profesion y hacer visible su participacion en la deteccion e intervencion de los problemas de salud abordados en los diferentes campos de practica. El trabajo contempla los conceptos de Diagnostico e Intervencion enfermeros y las taxonomias de Clasificacion de Diagnosticos (NANDA) y de Intervenciones (CIE). Para desarrollar el proyecto se utilizaron la metodologia de proceso unificado de desarrollo software, el lenguaje unificado de modelado (UML) y las herramientas de desarrollo Delphi 5 e Interbase 6. La aplicacion fue construida bajo la arquitectura cliente/servidor. Algunas conclusiones del proyecto son: el uso de subsistemas y modulos permite agregar, eliminar, o modificar sin afectar los existentes. Se valido los aspectos funcionales de cada modulo y se efectuo pruebas generales a la aplicacion. Se recomendo la inclusion del modulo de resultados en las proximas iteraciones del proyecto para hacer visible integralmente el impacto de la profesion de enfermeria.

Journal of Intelligent Systems with Applications, 2018

Main study areas for robotics research can be given as: mapping, localization, navigation and exp... more Main study areas for robotics research can be given as: mapping, localization, navigation and exploration. Given a robot’s current position, partial map of the environment and a goal position; navigation problem can be defined as optimal path planning and path following. Path planning and path following problem should be handled according to environment being static or dynamic, robot's mobility capabilities, sensors used on the robot and the roughness of the environment. In the study a four wheeled, skid-steering robot with laser range finder and depth sensor is built for Gazebo simulation environment. Also a statically structured labyrinth that consists of 15 degree continuous ramps, 15 degree discontinuous ramps, amorphous holes that robot cannot autonomously escape from if fallen into, walls and discontinuous obstacles that are below the robot laser height. 2D simultaneous localization and mapping, 3D mapping, path planning and path following with respect to the 3D map are im...

2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)

Social robot navigation aims to generate human-friendly paths in human-robot interactive environm... more Social robot navigation aims to generate human-friendly paths in human-robot interactive environments. This paper focuses on maintaining humans' physical safety and mental comfort during robot navigation in an unknown dynamic environment. To achieve this goal, we use a variant of a pedestrian model that is particularly developed for low or average density environments. Design decisions on the representation of the obstacle and pedestrian are important for smooth motion planning. Limiting the local obstacles as a region centered at the robot would be taken into consideration has weaknesses in terms of time complexity because a much detailed map has a great number of cells to be evaluated. The study contributes to the theoretical field with extensions such as the development of the obstacle representation model which aims to overcome the computational cost of the current solutions for smooth motion planning which can be a bottleneck for the entire system. The proposed method is tested on a physical mobile robot in hallway scenario both in real-world environment and simulation, and its success is experimentally shown.

2017 25th Signal Processing and Communications Applications Conference (SIU)

RoboCup is the most prestigious robotics contest in the world, with increasing popularity among r... more RoboCup is the most prestigious robotics contest in the world, with increasing popularity among robot communities and new contests. In this study, design and implementation of a line follower robot for outdoor categories which have been recently added to RoboCup Search and Rescue League is emphasized. In this category, a 100m long colored rope is placed in a field whose floor is made of sand, concrete and laminate and the competing robots are ranked according to the maximum trajectory distance that they cover in 20 minutes. The track is made of right and acute angle parts for the robot which is expected to follow the line including also 15° ramps. The robot which is implemented on ROS (The Robot Operating System) follows the line with the camera sensor above it.

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017

Restricted 3D simultaneous localization and mapping (SLAM) can be achived in an environment that ... more Restricted 3D simultaneous localization and mapping (SLAM) can be achived in an environment that has negative and positive obstacles, using a 2D SLAM and a 3D mapping together. Exploration can utilize 2D navigation, which uses a 2D map constructed with respect to 3D map obstacles both negative and positive, and free areas. Robocup, Rescue League, Exploration 4 competition is designed to measure real platform autonomous mobile robot exploration capabilities in an negative obstacle scene. In this paper aforementioned exploration approach is implemented in a simulation environment created in Gazebo similar to Exploration 4 arena, using Robot Operating System (ROS).

2020 28th Signal Processing and Communications Applications Conference (SIU), 2020

One of the platforms that autonomous exploration applications can be used is micro aerial vehicle... more One of the platforms that autonomous exploration applications can be used is micro aerial vehicles, which are used by robotic scientists, because of their high dynamic capabilities. A robot needs to do navigation in its surrounding environment to be able to do exploration. In outdoor and indoor environments with obstacles around, sensing an environment and creating its map to do navigation is a common practice in robotic studies. An aerial vehicle is able to reach to a target position without crashing into static and dynamic obstacles, with the help of costmaps created in navigation applications. To prevent an aerial vehicle, which is trying to find a path to a target position, from getting crashed into other vehicles in applications with multiple aerial vehicles, that aerial vehicle needs to take into account the paths that found by other vehicles. In this way it's possible to prevent aerial vehicles getting crashed into each other. In this work, a simultaneous navigation appli...

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017

RoboCup competitions are among the most prestigious robotics organizations in the world. Contesta... more RoboCup competitions are among the most prestigious robotics organizations in the world. Contestants compete in different categories with the robots they develop step by step to achieve the objectives of the organization for 2050. One of these categories is designed for search and rescue robots. Robots get points from the following criteria: identifying the victims autonomously in disaster situations, detecting hazmat chars, reading QR code and recognizing the various objects which is identified during the competition and marking their the locations on a map. In this study, some performance tests of various feature extraction methods have been performed for the detection of hazmat signs in competition environments of RoboCup search and rescue league. The tests were conducted in a laboratory which designed as RoboCup search and rescue league competition environment. After some comparison tests, the most appropriate method for real-time operation has been decided considering acceptabl...

2019 Innovations in Intelligent Systems and Applications Conference (ASYU), 2019

Area scanning can be defined as complete coverage of an area delimited either by natural or virtu... more Area scanning can be defined as complete coverage of an area delimited either by natural or virtual borders, by a mobile robot. Area scanning has a wide spread usage from home cleaning vacuum clear for home users to minesweeping robot for military usage. Autonomous mobile robot design and software implementation for effective area scanning of an initially unknown area is realized with this work. Simultaneous localization and mapping (SLAM), area segmantation, complete coverage path planning (CCPP) algorithms are used for this purpose. Behavioural approach is implemented at the top level by means of SMACH based state machine for autonomous effective area scanning. Calculated orientation of the environment and previously visited areas are used for effective path planning. Software implementation is tested on a differantial drive, Robot Operating System (ROS) capable mobile platform.

2017 International Conference on Computer Science and Engineering (UBMK), 2017

The remote controls which are used to control the robots are very expensive. In addition, one rem... more The remote controls which are used to control the robots are very expensive. In addition, one remote control is required for each robot. The goal of this work is to control multi robots at the same time by publish a single ROS message using one Android device. The user can drive robots with help of a variety of sensors and camera data which are displayed on the Android device screen, even if the user is visually disconnected from all robots. The biggest difference of this application from similar applications is that two different robots can be driven at the same time. With this feature, many multi robot tasks can be performed. Also robots have different driving strategies. This feature allows drive robots on different surfaces. Another powerful aspect of the work is the usage of ROS. Thanks to ROS, it is ensured that processes such as data communication protocols, process scheduling, etc. are implemented easily and efficiently. Furthermore, this work developed for Android. This fea...

J. Intell. Fuzzy Syst., 2020

Robot can help human in their everyday life and routine. These are not an indoor robot which was ... more Robot can help human in their everyday life and routine. These are not an indoor robot which was designed to perform desired task, but they can adapt to our environment by themselves and to learn from their own experiences. In this research we focus on high degree of autonomy, which is a must for social robots. For training purpose autonomous exploration and unknown environments is used along with proper algorithm so that robot can adapt to unknown environments. For testing purpose, simulation is carried with sensor fusion method, so that real world noise can be reduced and accuracy can be increased. This dissertation focuses on the intelligent robot control in autonomous navigation tasks and investigates the robot learning in following aspects. This method is based on human instinct of imitation. In this standard real time data set is provided to the robot for training purpose, it gets train from these data and generalize over all unseen potential situations and environments. Convo...

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017

In the scope of the study, it was aimed to discover a closed multi-storey environment with autono... more In the scope of the study, it was aimed to discover a closed multi-storey environment with autonomous air robots and produce a three dimensional map. In order to reduce the complexity of the three-dimensional exploration algorithm, we have developed Target Elimination Method that can calculate the result by narrowing the problem space. The Target Elimination Method ensures that the exploration algorithm is faster to explore the environment as it reduces the calculation time.

Mobil robotlarda gezinge cikarimi, robotun harita uzerinde izledigi yolun belirlenmesi ve bu yol ... more Mobil robotlarda gezinge cikarimi, robotun harita uzerinde izledigi yolun belirlenmesi ve bu yol uzerinden robotun hedefine olan mesafesinin tespiti, robotun engellere takilmadan guvenli bir sekilde yoluna devam edebilmesi ve robotun egitilebilmesi acisindan oldukca onemlidir. Bu calismada, belirlenen bir alan icerisinde mobil bir robot ile tekerlek odometrisi kullanilmadan gezinge cikarimi amaclanmistir. Bunun icin temel olarak 2 farkli yontem kullanilmistir. Ilki, en cok kullanilan es zamanli konum belirleme ve haritalama (SLAM) algoritmalarindan olan sadece lazer mesafe duyargasi bilgisini kullanan gMapping ile gezinge cikarimi, ikincisi ise lazer mesafe duyargasi tabanli laser_scan_matcher (LSM) ile gezinge cikarimidir. LSM ile gezinge cikariminda hiz bilgisi ve atalet duyargasi da kullanilmistir. Tum yontemler, alt basliklar halinde incelenmistir. Anahtar Kelimeler — gezinge cikarimi, LSM, gMapping. Trajectory estimation is important for mobile robots as it can be used in path ...

2017 International Conference on Computer Science and Engineering (UBMK)

2022 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)

Journal of Medical Imaging and Health Informatics, 2021

Compared with traditional motion planners and deep reinforcement learning DRL has been applied mo... more Compared with traditional motion planners and deep reinforcement learning DRL has been applied more and more widely to achieving sequential behaviors control of movement robots in internal environment. There are two addressed issues of deep learning. The inability to generalize to achieve set of goals. The data inefficiency, that is, the model requires, many trial and error loops (often costly). Applied can impact a few key areas of medicine and explore how to build end-to-end systems. Our discussion of computer vision focuses largely on medical imaging. In this paper, we address these two issues and apply the proposed model to visual navigation in conformity with generalizing in conformity with obtaining new goals (target-driven). To tackle the first issue, we advise an actor-critic mannequin whose coverage is a feature of the intention as much properly namely the present day state, which approves higher generalization. To tackle the second issue, we advocate the 3D scenes in envir...

Signal Processing and Communications Applications Conference, Apr 9, 2009

El objetivo de este trabajo es disenar e implementar un sistema de informacion que permita el reg... more El objetivo de este trabajo es disenar e implementar un sistema de informacion que permita el registro de los diagnosticos e intervenciones, realizados por los estudiantes de enfermeria en el ejercicio de las practicas clinicas y comunitarias; y muestre las frecuencias estadisticas asociadas a ellos. El proyecto realizado aporta a la escuela de enfermeria las herramientas necesarias para dar respuesta a las necesidades academicas y asistenciales propias de la profesion y hacer visible su participacion en la deteccion e intervencion de los problemas de salud abordados en los diferentes campos de practica. El trabajo contempla los conceptos de Diagnostico e Intervencion enfermeros y las taxonomias de Clasificacion de Diagnosticos (NANDA) y de Intervenciones (CIE). Para desarrollar el proyecto se utilizaron la metodologia de proceso unificado de desarrollo software, el lenguaje unificado de modelado (UML) y las herramientas de desarrollo Delphi 5 e Interbase 6. La aplicacion fue construida bajo la arquitectura cliente/servidor. Algunas conclusiones del proyecto son: el uso de subsistemas y modulos permite agregar, eliminar, o modificar sin afectar los existentes. Se valido los aspectos funcionales de cada modulo y se efectuo pruebas generales a la aplicacion. Se recomendo la inclusion del modulo de resultados en las proximas iteraciones del proyecto para hacer visible integralmente el impacto de la profesion de enfermeria.

Journal of Intelligent Systems with Applications, 2018

Main study areas for robotics research can be given as: mapping, localization, navigation and exp... more Main study areas for robotics research can be given as: mapping, localization, navigation and exploration. Given a robot’s current position, partial map of the environment and a goal position; navigation problem can be defined as optimal path planning and path following. Path planning and path following problem should be handled according to environment being static or dynamic, robot's mobility capabilities, sensors used on the robot and the roughness of the environment. In the study a four wheeled, skid-steering robot with laser range finder and depth sensor is built for Gazebo simulation environment. Also a statically structured labyrinth that consists of 15 degree continuous ramps, 15 degree discontinuous ramps, amorphous holes that robot cannot autonomously escape from if fallen into, walls and discontinuous obstacles that are below the robot laser height. 2D simultaneous localization and mapping, 3D mapping, path planning and path following with respect to the 3D map are im...

2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)

Social robot navigation aims to generate human-friendly paths in human-robot interactive environm... more Social robot navigation aims to generate human-friendly paths in human-robot interactive environments. This paper focuses on maintaining humans' physical safety and mental comfort during robot navigation in an unknown dynamic environment. To achieve this goal, we use a variant of a pedestrian model that is particularly developed for low or average density environments. Design decisions on the representation of the obstacle and pedestrian are important for smooth motion planning. Limiting the local obstacles as a region centered at the robot would be taken into consideration has weaknesses in terms of time complexity because a much detailed map has a great number of cells to be evaluated. The study contributes to the theoretical field with extensions such as the development of the obstacle representation model which aims to overcome the computational cost of the current solutions for smooth motion planning which can be a bottleneck for the entire system. The proposed method is tested on a physical mobile robot in hallway scenario both in real-world environment and simulation, and its success is experimentally shown.

2017 25th Signal Processing and Communications Applications Conference (SIU)

RoboCup is the most prestigious robotics contest in the world, with increasing popularity among r... more RoboCup is the most prestigious robotics contest in the world, with increasing popularity among robot communities and new contests. In this study, design and implementation of a line follower robot for outdoor categories which have been recently added to RoboCup Search and Rescue League is emphasized. In this category, a 100m long colored rope is placed in a field whose floor is made of sand, concrete and laminate and the competing robots are ranked according to the maximum trajectory distance that they cover in 20 minutes. The track is made of right and acute angle parts for the robot which is expected to follow the line including also 15° ramps. The robot which is implemented on ROS (The Robot Operating System) follows the line with the camera sensor above it.

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017

Restricted 3D simultaneous localization and mapping (SLAM) can be achived in an environment that ... more Restricted 3D simultaneous localization and mapping (SLAM) can be achived in an environment that has negative and positive obstacles, using a 2D SLAM and a 3D mapping together. Exploration can utilize 2D navigation, which uses a 2D map constructed with respect to 3D map obstacles both negative and positive, and free areas. Robocup, Rescue League, Exploration 4 competition is designed to measure real platform autonomous mobile robot exploration capabilities in an negative obstacle scene. In this paper aforementioned exploration approach is implemented in a simulation environment created in Gazebo similar to Exploration 4 arena, using Robot Operating System (ROS).

2020 28th Signal Processing and Communications Applications Conference (SIU), 2020

One of the platforms that autonomous exploration applications can be used is micro aerial vehicle... more One of the platforms that autonomous exploration applications can be used is micro aerial vehicles, which are used by robotic scientists, because of their high dynamic capabilities. A robot needs to do navigation in its surrounding environment to be able to do exploration. In outdoor and indoor environments with obstacles around, sensing an environment and creating its map to do navigation is a common practice in robotic studies. An aerial vehicle is able to reach to a target position without crashing into static and dynamic obstacles, with the help of costmaps created in navigation applications. To prevent an aerial vehicle, which is trying to find a path to a target position, from getting crashed into other vehicles in applications with multiple aerial vehicles, that aerial vehicle needs to take into account the paths that found by other vehicles. In this way it's possible to prevent aerial vehicles getting crashed into each other. In this work, a simultaneous navigation appli...

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017

RoboCup competitions are among the most prestigious robotics organizations in the world. Contesta... more RoboCup competitions are among the most prestigious robotics organizations in the world. Contestants compete in different categories with the robots they develop step by step to achieve the objectives of the organization for 2050. One of these categories is designed for search and rescue robots. Robots get points from the following criteria: identifying the victims autonomously in disaster situations, detecting hazmat chars, reading QR code and recognizing the various objects which is identified during the competition and marking their the locations on a map. In this study, some performance tests of various feature extraction methods have been performed for the detection of hazmat signs in competition environments of RoboCup search and rescue league. The tests were conducted in a laboratory which designed as RoboCup search and rescue league competition environment. After some comparison tests, the most appropriate method for real-time operation has been decided considering acceptabl...

2019 Innovations in Intelligent Systems and Applications Conference (ASYU), 2019

Area scanning can be defined as complete coverage of an area delimited either by natural or virtu... more Area scanning can be defined as complete coverage of an area delimited either by natural or virtual borders, by a mobile robot. Area scanning has a wide spread usage from home cleaning vacuum clear for home users to minesweeping robot for military usage. Autonomous mobile robot design and software implementation for effective area scanning of an initially unknown area is realized with this work. Simultaneous localization and mapping (SLAM), area segmantation, complete coverage path planning (CCPP) algorithms are used for this purpose. Behavioural approach is implemented at the top level by means of SMACH based state machine for autonomous effective area scanning. Calculated orientation of the environment and previously visited areas are used for effective path planning. Software implementation is tested on a differantial drive, Robot Operating System (ROS) capable mobile platform.

2017 International Conference on Computer Science and Engineering (UBMK), 2017

The remote controls which are used to control the robots are very expensive. In addition, one rem... more The remote controls which are used to control the robots are very expensive. In addition, one remote control is required for each robot. The goal of this work is to control multi robots at the same time by publish a single ROS message using one Android device. The user can drive robots with help of a variety of sensors and camera data which are displayed on the Android device screen, even if the user is visually disconnected from all robots. The biggest difference of this application from similar applications is that two different robots can be driven at the same time. With this feature, many multi robot tasks can be performed. Also robots have different driving strategies. This feature allows drive robots on different surfaces. Another powerful aspect of the work is the usage of ROS. Thanks to ROS, it is ensured that processes such as data communication protocols, process scheduling, etc. are implemented easily and efficiently. Furthermore, this work developed for Android. This fea...

J. Intell. Fuzzy Syst., 2020

Robot can help human in their everyday life and routine. These are not an indoor robot which was ... more Robot can help human in their everyday life and routine. These are not an indoor robot which was designed to perform desired task, but they can adapt to our environment by themselves and to learn from their own experiences. In this research we focus on high degree of autonomy, which is a must for social robots. For training purpose autonomous exploration and unknown environments is used along with proper algorithm so that robot can adapt to unknown environments. For testing purpose, simulation is carried with sensor fusion method, so that real world noise can be reduced and accuracy can be increased. This dissertation focuses on the intelligent robot control in autonomous navigation tasks and investigates the robot learning in following aspects. This method is based on human instinct of imitation. In this standard real time data set is provided to the robot for training purpose, it gets train from these data and generalize over all unseen potential situations and environments. Convo...

2017 25th Signal Processing and Communications Applications Conference (SIU), 2017

In the scope of the study, it was aimed to discover a closed multi-storey environment with autono... more In the scope of the study, it was aimed to discover a closed multi-storey environment with autonomous air robots and produce a three dimensional map. In order to reduce the complexity of the three-dimensional exploration algorithm, we have developed Target Elimination Method that can calculate the result by narrowing the problem space. The Target Elimination Method ensures that the exploration algorithm is faster to explore the environment as it reduces the calculation time.

Mobil robotlarda gezinge cikarimi, robotun harita uzerinde izledigi yolun belirlenmesi ve bu yol ... more Mobil robotlarda gezinge cikarimi, robotun harita uzerinde izledigi yolun belirlenmesi ve bu yol uzerinden robotun hedefine olan mesafesinin tespiti, robotun engellere takilmadan guvenli bir sekilde yoluna devam edebilmesi ve robotun egitilebilmesi acisindan oldukca onemlidir. Bu calismada, belirlenen bir alan icerisinde mobil bir robot ile tekerlek odometrisi kullanilmadan gezinge cikarimi amaclanmistir. Bunun icin temel olarak 2 farkli yontem kullanilmistir. Ilki, en cok kullanilan es zamanli konum belirleme ve haritalama (SLAM) algoritmalarindan olan sadece lazer mesafe duyargasi bilgisini kullanan gMapping ile gezinge cikarimi, ikincisi ise lazer mesafe duyargasi tabanli laser_scan_matcher (LSM) ile gezinge cikarimidir. LSM ile gezinge cikariminda hiz bilgisi ve atalet duyargasi da kullanilmistir. Tum yontemler, alt basliklar halinde incelenmistir. Anahtar Kelimeler — gezinge cikarimi, LSM, gMapping. Trajectory estimation is important for mobile robots as it can be used in path ...

2017 International Conference on Computer Science and Engineering (UBMK)