Unit INTELLIGENT MOBILE ROBOTS
- Course
- Computer engineering and robotics
- Study-unit Code
- 70A00052
- Curriculum
- Robotics
- Teacher
- Paolo Valigi
- Teachers
-
- Paolo Valigi
- Hours
- 72 ore - Paolo Valigi
- CFU
- 9
- Course Regulation
- Coorte 2021
- Offered
- 2022/23
- Learning activities
- Caratterizzante
- Area
- Ingegneria informatica
- Academic discipline
- ING-INF/04
- Type of study-unit
- Obbligatorio (Required)
- Type of learning activities
- Attività formativa monodisciplinare
- Language of instruction
- Italian
- Contents
- Introduction.
Locomotion. Planning and Navigation.
Perception.
Localization and SLAM. - Reference texts
- Roland Siegwart, Illah, R. Nourbakhsh, and Davide Scaramuzza. Introduction to autonomous mobile robots. - 2nd ed./ MIT Press, 2014
Sebastian Thrun, Wolfram Burgard and Dieter Fox, Probabilistic Robotics, MIT Press, 2005 - Educational objectives
The key tools for the design and realization of autonomous mobile robots, with specific attention to localization, mostly vision based, motion planning, and control. Both well established and state-of-the-art approaches will be presented.- Prerequisites
- Robot Perception and Computer Vision.
Basic concepts on Embedded Electronic Systems; Automatic Control, Programming Languages. - Teaching methods
- Frontal lectures, laboratory activities. Project based learning (PBL).
Optional project-work with mobile robots available with the ISARLab. - Other information
- Project works will be made available, to allow for a more detailed study of the course subjects.
- Learning verification modality
- Oral tests and project discussion.
The oral test covers all course content, is based on three different questions, and will last about 30 minutes.
The overall grad is based on both oral and project, as well as on the participation to the coding sessions during the lectures. - Extended program
- Overview of mobile robotics (hardware, software architectures, sensors) and applications (industry 4.0, home, drones).
Robot guidance and trajectory planning.
Probabilistic models of sensing and acting.
State estimation and filtering for localization. Bayes filter, histogram filters, Kalman filters (extended, unscented), particle filters.
Robot localization, Map building.
The SLAM problem and solution: Kalman filtering, Rao-Blackwell particle filters, graph-SLAM.
Vision based localization, visual odometry and visual SLAM.