Progress for week 45 (2014)

From Robin

Revision as of 12:00, 13 November 2014 by Eivinwi (Talk | contribs)
Jump to: navigation, search

Contents

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

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.
Personal tools
Front page