Mobile Robot Localization Via Sensor Fusion Algorithms

Date

2017-09-08

Author

Uyulan, Caglar
ERGÜZEL, TÜRKER TEKİN
Arslan, Ersen

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

53
views

0
downloads

In order to make effective works with the mobile robot and maximize its working performance, it is necessary to estimate and track the current pose of the mobile robot. In this paper, under the assumption that the initial pose, kinematics and environmental model of a mobile robot are known, the localization and tracking of the mobile robot's position and orientation have been carried out. The odometry model with the problem of accumulation of unlimited errors is used for tracking the pose, and sensor fusion algorithms are applied to solve this problem. By using the odometry and laser range finder model, the Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), Unscented Information Filter (UIF), Extended Information Filter (EIF) algorithms were tested on a graphical user interface (GUI) based on occupancy grid maps as an environment model, respectively. In this context, the pose tracking and estimation performances of the non-linear model based estimators are compared to each other. Since occupancy grid maps are utilized, only the laser range finder measurement uncertainty should be considered unlike feature based maps. In this way, the computational complexity can be reduced. When the simulation results are evaluated, it is determined that the Extended Information Filter algorithm has expressed more stable performance in terms of the mobile robot pose estimation.

Subject Keywords

Extended kalman filter, Unscented information filter, Information filter, Localization, Occupancy grid map

URI

https://hdl.handle.net/11511/66637

Collections

Department of Mechanical Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Slippage estimation of a two wheeled mobile robot using deep neural network Özçil, İsmail; Konukseven, Erhan İlhan; Koku, Ahmet Buğra; Department of Mechanical Engineering (2018) Mobile robot navigaiton is an important task for the operations of the mobile robots. Due to the wheel slippages, performance of the dead reckoning in estimating speed of the robot and the position of the robot is not sufficient. To overcome the errors in navigation estimates, usage of the recurrent deep neural networks is porposed. Neural networks are used to understand the behaviour of the linear and nonlinear systems. Since wheel-ground interaction will be modeled with non-linear models and the estimatin...
Vision-based robot localization using artificial and natural landmarks Arıcan, Zafer; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2004) In mobile robot applications, it is an important issue for a robot to know where it is. Accurate localization becomes crucial for navigation and map building applications because both route to follow and positions of the objects to be inserted into the map highly depend on the position of the robot in the environment. For localization, the robot uses the measurements that it takes by various devices such as laser rangefinders, sonars, odometry devices and vision. Generally these devices give the distances o...
DEVELOPMENT OF A SOCIAL REINFORCEMENT LEARNING BASED AGGREGATION METHOD WITH A MOBILE ROBOT SWARM Gür, Emre; Turgut, Ali Emre; Şahin, Erol; Department of Mechanical Engineering (2022-9-09) In this thesis, the development of a social, reinforcement learning-based aggregation method is covered together with the development of a mobile robot swarm of Kobot- Tracked (Kobot-T) robots. The proposed method is developed to improve efficiency in low robot density swarm environments especially when the aggregated area is difficult to find. The method is called Social Reinforcement Learning, and Landmark-Based Aggregation (SRLA) and it is based on Q learning. In this method, robots share their Q tables ...
Control and motion planning for mobile robots via a secure wireless communication protocol Kaya, Muhammed Çağrı; Eroğlu, Alperen; Temizer, Selim (null; 2013-05-21) Mobile robot control is receiving considerably more attention in current robotics research. Especially unmanned vehicles are used in important missions such as bomb disposal, patrolling borders of a country by unmanned aerial vehicles (UAVs), etc. This usage increases the importance of unmanned vehicles and they become a target of malevolent people. In this study, a controllable robot system is designed with a secure communication protocol. A Pioneer P3-DX robot is used as a ground vehicle. The robot operat...
Aktif sönümleme denetimi ile bacaklı robotlarda model tabanlı enerji ve koşma kontrolü Özen, Merve; Orhon, Eftun Hasan; Saranlı, Uluç; Seçer, Görkem(2016) Mobil robotların arazi şartlarında ihtiyaç duyulan hareketlilik ve performansı gösterebilmeleri için, bacaklı tasarımların yüksek potansiyele sahip oldukları bilinmektedir. Buna rağmen, gerek bacaklı hareketin matematiksel modellenmesi ve denetimindeki, gerekse bu yapıya sahip robotların güvenilir, dayanıklı ve yüksek performanslı olarak tasarlanmalarındaki zorluklar bu alandaki gelişmelerin yavaş ilerlemesine sebep olmuştur. Bu kapsamda yaygın olarak kabul görmüş olan Yaylı Ters Sarkaç (YTS)...

Citation Formats

C. Uyulan, T. T. ERGÜZEL, and E. Arslan, “Mobile Robot Localization Via Sensor Fusion Algorithms,” 2017, p. 955, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/66637.