Progress for week 45 (2014)

Fra Robin

(Forskjeller mellom versjoner)
Gå til: navigasjon, søk
(Stian)
 
(6 mellomrevisjoner ikke vist.)
Linje 13: Linje 13:
=== Accounting ===
=== Accounting ===
-
*
+
* Tried to use the paradisEO framework for the NSGA-II without success
 +
* Tried out another implementation of the NSGA-II with success
 +
* Started modifying and implementing it into my own project for use with the simulator and the robot
== Rune ==
== Rune ==
Linje 21: Linje 23:
=== Accounting ===
=== Accounting ===
-
*
+
* Continued on PRM
-
*
+
* Looked into map-generation
== Stian ==
== Stian ==
Linje 45: Linje 47:
=== Accounting ===
=== Accounting ===
 +
* Read a paper on possible statistical methods for comparing EAs
 +
** Mann-Whitney U test
 +
** Wilcoxon signed-rank test
 +
* Done some testing
 +
* Made testing more efficient
== André ==
== André ==
Linje 56: Linje 63:
=== Accounting ===
=== Accounting ===
 +
* Started to test the use of IR for the triangulation part
 +
* Started looking at Kinect
 +
* Started setting up headlines for the thesis
== Eivind ==
== Eivind ==
Linje 65: Linje 75:
=== Accounting ===
=== Accounting ===
 +
* All basic functionality is implemented
 +
* Communication protocol is mostly complete
 +
* Spent some time setting up a latex structure, and wrote a couple of pages.

Nåværende revisjon fra 13. nov 2014 kl. 12:07

Innhold

Student template (copy this for your entry)

Budget

  • Todo 1
  • Todo 2

Accounting

  • Done 1
  • Done 2

Snorre

Budget

  • Start to implement the NSGA-II algorithm

Accounting

  • Tried to use the paradisEO framework for the NSGA-II without success
  • Tried out another implementation of the NSGA-II with success
  • Started modifying and implementing it into my own project for use with the simulator and the robot

Rune

Budget

  • Finish PRM
  • Begin looking at learning

Accounting

  • Continued on PRM
  • Looked into map-generation

Stian

Budget

  • Move the previous OpenCV stereo implementation into the framework.
    • Extend it for some parameter experimentation.
  • Gather a new training set (current one can't be run on algorithms requiring image width divisible by 16)

Accounting

  • Switched to exploration using the NSGA-II algorithm.
    • This has made it easier to visualize pros and cons of different algorithms and their parameters for a given test setting.
  • Ran several tests to get a better understanding of both NSGA-II and some stereo algorithms explored with it.
    • Tested both with (NSGA) crowding distance on objectives and on parameters.
  • Moved the openCV implementation into the framework, but a couple problems has so far prevented proper testing.

Else-Line

Budget

  • Look into good statistical methods for data comparison
  • Continue testing parameters
  • Compare Baldwinian and Lamarckian learning
  • Compare different local searches

Accounting

  • Read a paper on possible statistical methods for comparing EAs
    • Mann-Whitney U test
    • Wilcoxon signed-rank test
  • Done some testing
  • Made testing more efficient

André

Budget

  • Try to find more information of where to by the omnidirectional camera
  • Try to implement a Feature detection algorithm with openCV
  • Borrow a Kinect an set the kinect up ready for testing
    • Use the kinect first as distance measure
    • Look into more usages of the kinect
  • Start writing on the Thesis

Accounting

  • Started to test the use of IR for the triangulation part
  • Started looking at Kinect
  • Started setting up headlines for the thesis

Eivind

Budget

  • Finish implementing navigation functionality
  • Tweak communication protocol
  • Paint and build game area (?)
  • Write something

Accounting

  • All basic functionality is implemented
  • Communication protocol is mostly complete
  • Spent some time setting up a latex structure, and wrote a couple of pages.
Personlige verktøy