HjemEmner

TEL310 Probabilistisk Robotikk

Studiepoeng:10

Ansvarlig fakultet:Fakultet for realfag og teknologi

Emneansvarlig:Antonio Candea Leite

Campus / nettbasert:Undervises campus Ås

Undervisningens språk:Engelsk

Frekvens:Annually

Forventet arbeidsmengde:Lectures, computer exercises, lab exercises and homework, approximately 250 hours.

Undervisnings- og vurderingsperiode:This course starts in the autumn parallel. This course has teaching and evaluation during the autumn parallel.

Om dette emnet

This course provides a comprehensive overview of probabilistic algorithms for robotics at the Master's level and focuses on a critical element of robotics: uncertainty in robot perception and action. The key idea of probabilistic robotics is to represent uncertainty explicitly, using the calculus of probability theory. It includes basic concepts of Probability, Bayes Filters, Gaussian and Non-parametric Filters, Robot Motion, Perception, Mobile Robot Localization, Grid and Monte Carlo Localization, Occupancy Grid Mapping, SLAM and Markov Decision Processes. The course also addresses the main sources of uncertainty in robotics: environments, sensors, actuators, robot models, and computational algorithms.

Dette lærer du

After completing the course, the students have acquired knowledge about and skills in designing, analyzing, and applying probabilistic approaches for robotic systems. This includes the combination of practical work and programming, with algorithms for filtering, planning, localization, and so on. The students should also have basic knowledge about, and skills in, applying the most used methods in probabilistic robotics for a wide variety of robotic applications.

  • The course consists of lectures and exercises, problem-based learning from industry partners, and computer exercises, with the use of programs in the analysis and design of probabilistic algorithms. The course is complemented with laboratory work (lab exercises), a set of practical implementation instructions in simulation using Matlab/Simulink software and Python language, and fieldwork (if any) on real mobile robots using the ROS framework.

    Lectures and Exercises: concepts are presented and problems analyzed.

    Computer Exercises: presented concepts are practiced through tutorials and exercises.

    Lab Exercises: presented concepts are tested on simulated and real robots.

    • The teacher is available for consultation in the lecturing period and otherwise available by e-mail or appointment.
    • Assistant teachers will guide and support students during exercises, practice classes and labs.
    • Course room on Canvas.
    • Licenses for the The Construct Platform will be provided at the start of the course.
    • Thrun, S., Burgard, W. & Fox, D., "Probabilistic Robotics," The MIT Press, 2005.
    • Corke, P., "Robotics, Vision and Control: Fundamental Algorithms in Matlab," Springer Int. Pub. AG, 2nd Ed., 2017.
    • Video Classes: Youtube, MATLAB Tech Talks.
    • INF120 Programming and Data Processing, ECTS 10.
    • TEL240 Control and Engineering and Automation, ECTS 10.
    • TEL200Introduction to Robotics, ECTS 10.
    • TEL211Robot Programming, ECTS 10.
    • TEL280Mobile Robots and Navigation, ECTS 10.
  • Continuous exam: All mandatory exercises, laboratory work and oral presentation must be approved. A Technical Report about the laboratory work and fieldwork (if any) will count 100% towards the final grade (A-E/F).

    Mappe/sammensatt vurdering Karakterregel: Bokstavkarakterer
  • The external examiner will control the quality of the syllabus, the questions for the final exam (if any), and the principles for evaluating the exam answers.
  • Mandatory work: laboratory work, fieldwork (if any), oral presentation and written technical report.
  • Science and Technology