High-level architecture for the control of humanoid robot

From AIRWiki
Revision as of 21:49, 8 October 2012 by AndreaBonarini (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
High-level architecture for the control of humanoid robot
Short Description: This project is aimed at designing and constructing a bio-inspired brain for the control of humanoid robots. The brain should be able to combine sensory information and human orders to produce a voluntary movement.

At present the project has developed a model of the V1 cortex; future steps will include V2 area and analysis of movements.

Coordinator:
Tutor: GiuseppinaGini (gini@elet.polimi.it)
Collaborator:
Students: FlavioMutti (mutti@elet.polimi.it)
Research Area: Robotics
Research Topic:
Start: 2010/10/1
End: 2011/9/30
Status: Closed
Type: Thesis

Part 1: project profile

Project name

High-level architecture for the control of humanoid robot

Project short description

This project is aimed at designing and constructing a bio-inspired brain for the control of humanoid robots. The brain should be able to combine sensory information and human orders to produce a voluntary movement. At present the project has developed a model of the V1 cortex; future steps will include V2 area and analysis of movements.

Dates

Start date: 2008/10/1

End date: 2011/9/30

Website(s)

(void)

People involved

Project head(s)

G. Gini - User:GiuseppinaGini

Other Politecnico di Milano people

(void)

Students currently working on the project

Flavio Mutti - User:FlavioMutti

Students who worked on the project in the past

(void)

External personnel

(void)

Laboratory work and risk analysis

Laboratory work for this project will be mainly performed at AIRLab/Lambrate. It will include significant amounts of mechanical work as well as of electrical and electronic activity. Potentially risky activities are the following:

  • Use of mechanical tools. Standard safety measures described in Safety norms will be followed.
  • Use of soldering iron. Standard safety measures described in Safety norms will be followed.
  • Use of high-voltage circuits. Special gloves and a current limiter will be used.
  • Transportation of heavy loads (e.g. robot parts). Standard safety measures described in Safety norms will be followed.
  • Robot testing. Standard safety measures described in Safety norms will be followed.
  • Death ray testing: on the robot will be mounted professor Azzoide's death ray projector. When testing it on live animals (e.g. pigeons, pigs, camels) we will make sure that people stay away from the test area.

Part 2: project description

The perception of the environment depth is closely related to the estimate of retinal disparity; retinal images are not strictly equal because of the physical distance between the two eyes. Computing the disparity between the two retinal images allows to estimate the environment depth, relative to the fixation plan determined by the eyes convergence.

So the problem of depth perception can be reduced to the computation of retinal disparity; then the main task of the model of the primary visual cortex will be to compute the binocular disparity, according to the disparity energy model.