Progress for week 48 (2018)

From Robin

(Difference between revisions)
Jump to: navigation, search
(David Kolden)
 
(3 intermediate revisions not shown)
Line 2: Line 2:
=== Budget ===
=== Budget ===
* Implement one or more algorithms. Refine D2CO. Research a way to find a gradient with chamfer distance.
* Implement one or more algorithms. Refine D2CO. Research a way to find a gradient with chamfer distance.
 +
=== Accounting ===
 +
* Found out that Chamfer Distance Transform can be used as a gradient directly in an IBVC.
 +
* Sketching new algorithms and evaluating them:
 +
** Reducing hypotheses in a IBVC/PBVC hybrid.
 +
** Parallel lines and vanishing points.
 +
** Hybrid configuration set up using model description of gripper together with model description of the object.
 +
* GPU to calculate FDCM?
== Jonas S. Waaler ==
== Jonas S. Waaler ==
Line 9: Line 16:
** First: Traditional methods (similar to experiment 1)
** First: Traditional methods (similar to experiment 1)
** I suspect I need more data - transfer learning, RNN etc.
** I suspect I need more data - transfer learning, RNN etc.
 +
 +
=== Accounting ===
 +
* Added more metrics
 +
** Pearson Correlation Coefficient
 +
*** Liner simularity
 +
** Normalized Cross Correlation
 +
*** Simularity with displacement
 +
** MSE of Fast Fourier Transform
 +
*** Distance between frequencies
 +
* Added baselines
 +
** Random
 +
*** Uniform
 +
*** Normal
 +
** Mean of all training data
 +
 +
== Malin Aandahl ==
 +
=== Budget ===
 +
* Implement new fitness function.
 +
* Find out where the position to the robot is calculated(and change to be the back instead of the front of the robot)
 +
* Finish tutorials about Docker.
 +
* If time set up Docker or implement function to find position.
 +
 +
 +
 +
== Anders Rønningstad ==
 +
=== Budget ===
 +
* Finish deep learning project
 +
 +
=== Accounting ===
 +
* Finished the project

Current revision as of 11:53, 30 November 2018

Contents

David Kolden

Budget

  • Implement one or more algorithms. Refine D2CO. Research a way to find a gradient with chamfer distance.

Accounting

  • Found out that Chamfer Distance Transform can be used as a gradient directly in an IBVC.
  • Sketching new algorithms and evaluating them:
    • Reducing hypotheses in a IBVC/PBVC hybrid.
    • Parallel lines and vanishing points.
    • Hybrid configuration set up using model description of gripper together with model description of the object.
  • GPU to calculate FDCM?

Jonas S. Waaler

Budget

  • Tune data to fit classification task (experiment 2)
  • Construct algorithms/architectures to solve the classification task
    • First: Traditional methods (similar to experiment 1)
    • I suspect I need more data - transfer learning, RNN etc.

Accounting

  • Added more metrics
    • Pearson Correlation Coefficient
      • Liner simularity
    • Normalized Cross Correlation
      • Simularity with displacement
    • MSE of Fast Fourier Transform
      • Distance between frequencies
  • Added baselines
    • Random
      • Uniform
      • Normal
    • Mean of all training data

Malin Aandahl

Budget

  • Implement new fitness function.
  • Find out where the position to the robot is calculated(and change to be the back instead of the front of the robot)
  • Finish tutorials about Docker.
  • If time set up Docker or implement function to find position.


Anders Rønningstad

Budget

  • Finish deep learning project

Accounting

  • Finished the project
Personal tools
Front page