Robòtica Cognitiva

Esteu aquí

Crèdits
4.5
Tipus
Optativa
Requisits
Aquesta assignatura no té requisits, però té capacitats prèvies
Departament
URV;CS
Mail
1.To understand the main types of cognitive robots and their driving requirements (engineering operations, navigation, cooperation).
2.To understand advanced methods for creating highly capable cognitive robots.
3.To dive into the recent literature, and collectively synthesize, clearly explain and evaluate the state of the art in cognitive robotics.
4.To apply one or more core reasoning methods to create a simple agent that is driven by goals or rewards.

Professors

Responsable

  • Albert Oller ( )

Hores setmanals

Teoria
1.8
Problemes
0
Laboratori
0.9
Aprenentatge dirigit
0
Aprenentatge autònom
4.8

Continguts

  1. Planning and Acting in the World.
    Monitoring and Diagnosis
    Planning Missions
  2. Interacting with the world: state-awareness
    SLAM
    Cognitive Vision
    Navigation and Manipulation
    Human-Robot Interaction
  3. Fast, large-scale reasoning: planning for future
    Optimality and soft Constraints
    Incremental methods

Activitats

Activitat Acte avaluatiu


Desenvolupament dels continguts teòrics en un entorn de simulació



Teoria
27h
Problemes
0h
Laboratori
6h
Aprenentatge dirigit
0h
Aprenentatge autònom
36h

Treball en grup amb robots simulats



Teoria
0h
Problemes
0h
Laboratori
7.5h
Aprenentatge dirigit
0h
Aprenentatge autònom
36h

Metodologia docent

1. To understand the main types of cognitive robots and their driving requirements (engineering operations, navigation, cooperation)
Methodology: case studies

2. To understand advanced methods for creating highly capable cognitive robots
Methodology: lectures and classroom slides, implement and compare 2 core methods with computer simulation

3. To dive into the recent literature, and collectively synthesize, clearly explain and evaluate the state of the art in cognitive robotics
Methodology: oral presentation

4.To apply one or more core reasoning methods to create a simple agent that is driven by goals or rewards
Methodology: code programming

Mètode d'avaluació

1. Oral presentation 20%
2. Reports of lab sessions 30%
3. Final project 50%

(*) There are no exams.

Capacitats prèvies

Good programming skills (C, C++, Matlab)