dc.contributor |
Ros Puig, Domènec |
dc.contributor.author |
González Sánchez, Tomás |
dc.date |
2009-09 |
dc.identifier.uri |
http://hdl.handle.net/2099.1/7722 |
dc.language.iso |
eng |
dc.publisher |
Universitat Politècnica de Catalunya |
dc.rights |
Attribution-NonCommercial-NoDerivs 3.0 Spain |
dc.rights |
info:eu-repo/semantics/openAccess |
dc.rights |
http://creativecommons.org/licenses/by-nc-nd/3.0/es/ |
dc.subject |
Àrees temàtiques de la UPC::Informàtica::Robòtica |
dc.subject |
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial |
dc.subject |
Robotics |
dc.subject |
Expert systems (Computer science) |
dc.subject |
Robòtica |
dc.subject |
Sistemes experts (Informàtica) |
dc.title |
Artificial Vision in the Nao Humanoid Robot |
dc.type |
info:eu-repo/semantics/masterThesis |
dc.description.abstract |
Projecte Final de Màster UPC realitzat en col.laboració amb l'Universitat Rovira i Virgili. Departament d'Enginyeria Informàtica i Matemàtiques |
dc.description.abstract |
Robocup is an international robotic soccer competition held yearly to promote
innovative research and application in robotic intelligence. Nao humanoid robot
is the new RoboCup Standard Platform robot. This platform is the new Nao
robot designed and manufactured by the french company Aldebaran Robotics.
The new robot is an advanced platform for developing new computer vision and
robotics methods. This Master Thesis is oriented to the study of some fundamental
issues for the artificial vision in the Nao humanoid robots. In particular,
color representation models, real-time segmentation techniques, object detection
and visual sonar approaches are the computer vision techniques applied to Nao
robot in this Master Thesis. Also, Nao’s camera model, mathematical robot
kinematic and stereo-vision techniques are studied and developed. This thesis
also studies the integration between kinematic model and robot perception
model to perform RoboCup soccer games and RoboCup technical challenges.
This work is focused in the RoboCup environment but all computer vision and
robotics algorithms can be easily extended to another robotics fields. |