New Trends in Robotics

You are here

Credits
3
Types
Elective
Requirements
This subject has not requirements
Department
URV;CS
The discipline of robotics is now extending its arms towards new applications in new environments, to meet new demands of a new society. Most of the success is motivated by the application of AI techniques.
In this course, some of such AI techniques will be analysed.

Teachers

Person in charge

  • Albert Oller ( )

Weekly hours

Theory
1.2
Problems
0
Laboratory
0.6
Guided learning
0
Autonomous learning
3.2

Objectives

  1. Probabilistic techniques applied in robotics
    Related competences:
    Subcompetences:
    • Bayesian filters, Extended Kalman filters, Ant colony optimization, Particle filtering
  2. Search techniques are applied in robotics
    Related competences:
    Subcompetences:
    • Voronoi teselation, A*, C-space
  3. Decision making techniques applied in robotics
    Related competences:
    Subcompetences:
    • Intelligent control, Action selection, Task assignment

Activities

Activity Evaluation act


Paper discussion: probabilistic methods


Objectives: 1
Theory
6h
Problems
0h
Laboratory
3h
Guided learning
0h
Autonomous learning
16h

Paper discussion: search methods


Objectives: 2
Theory
6h
Problems
0h
Laboratory
3h
Guided learning
0h
Autonomous learning
16h

Paper discussion: decision making methods


Objectives: 3
Theory
6h
Problems
0h
Laboratory
3h
Guided learning
0h
Autonomous learning
16h

Teaching methodology

For each AI methodology:
Week-1. Classroom slides and paper introduction (by teacher)
Week-2. Homework: paper reading
Week-3. Paper discussion in classroom
Week-4. Report writing
Week-5. Oral presentation. Next paper introduction (by teacher)

Evaluation methodology

Report of Probabilistic methods 33%
Report of Search methods 33%
Report of Decision Making methods 33%