Course Information

Course Name	Turkish	Robotikde Olasılıksal Metodlar
	English	Probabilistics Methods in Robo
Course Code	KOM 613E	Credit	Lecture (hour/week)	Recitation (hour/week)	Laboratory (hour/week)
Semester	-	3	3	-	-
Course Language		English
Course Coordinator		Hakan Temeltaş
Course Objectives		In recent years, studies and application on the field of robotics have made substantial progress. In the past, robot manipulators with fixed workspace were located mostly on production lines, assigned to perform pre-defined jobs in the known environment. More recently, the research on robotics has mostly concentrated on mobile platforms with various sensors and actuators and mobile manipulators Within this context, the mobile robots and the mobile manipulators have been appeared in several fields such as domestic and service robotics, space and security robots, human robot interaction, medical robots. Today research studies in those areas have been continued increasingly. However many of these application areas have dynamical nature and involves several level of uncertainties. Uncertainty arises for many reasons, including the natural limitations of a model of the world, the noise and perceptual limitations in sensor measurements of mobile robots and manipulators, and the approximate nature of algorithmic solutions. Methods targeting to solve the problems mentioned, primarily consider the probabilistic representation of information.
Course Description		Description of this course is to introduce uncertainty problems in robotics and the bring solution by employing probabilistic methods in order to increase autonomous abilities of robotic systems. Furthermore, the course classifies the future problems by giving recent trends in algorithmic solutions of robotics in order to address active research areas for postgraduate students.
Course Outcomes		1. Gain knowledge about the research topics in probabilistic methods in robotics modeling, analysis, planning and control. 2. Gain knowledge about optimal state estimation methods using Gaussian and non-Gaussian filters 3. Develop stochastic models for robotic plants with under model disturbances, 4. Develop stochastic models for robotic measurement devices under sensor noise, 5. Learn probabilistic localization methods to be used in autonomous robot navigation, 6. Learn probabilistic mapping methods to be used in autonomous robot navigation, 7. Understanding SLAM problems and develop SLAM methods for autonomous robot navigation, 8. Learn robot planning method under uncertainty, 9. Improve communication skill by writing and presentations of research reports.
Pre-requisite(s)		Non
Required Facilities		Knowledge on MATLAB/simulink
Other
Textbook		Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic robotics. Intelligent robotics and autonomous agents. Cambridge, Mass: MIT Press.
Other References		Montemerlo, M., & Thrun, S. (2007). FastSLAM: A scalable method for the simultaneous localization and mapping problem in robotics. Springer tracts in advanced robotics, 27. Berlin: Springer. Siegwart, R., & Nourbakhsh, I. R. (2004). Introduction to autonomous mobile robots. Intelligent robotics and autonomous agents. Cambridge, Mass: MIT Press.

Courses

Help

About