Progress for week 46 (2014)
From Robin
(Difference between revisions)
(→Rune) |
(→Stian) |
||
Line 16: | Line 16: | ||
=== Accounting === | === Accounting === | ||
+ | * Made a new dataset based on the KITTY benchmark which contains real world data with LIDAR-based ground truth images. | ||
+ | * Changed fitness evaluation criteria to better account for algorithms with sparse results. | ||
+ | * Finished implementing the OpenCV SGM algorithm, but initial evaluation still ongoing so no results to compare. | ||
== Else-Line == | == Else-Line == |
Revision as of 09:15, 18 November 2014
Contents |
Student template (copy this for your entry)
Budget
- Todo 1
- Todo 2
Accounting
- Done 1
- Done 2
Stian
Budget
- Continue moving algorithms into the framework.
- Will need to update the testset first.
- Start comparing results
- Look into good methods of doing so.
Accounting
- Made a new dataset based on the KITTY benchmark which contains real world data with LIDAR-based ground truth images.
- Changed fitness evaluation criteria to better account for algorithms with sparse results.
- Finished implementing the OpenCV SGM algorithm, but initial evaluation still ongoing so no results to compare.
Else-Line
Budget
- Continue testing parameters
- Compare Baldwinian and Lamarckian learning
- Compare different local searches
Accounting
Snorre
Budget
- Continue to implement the algorithm into my own project
- Start to look into transferability measurements
- Do some small experiments with the NSGA-II (if time)
Accounting
Rune
Budget
- Finish setting up library for png-handling
- Create a simple map-generator
- Continue on PRM
Accounting
- Created a simple map-generator
Eivind
Budget
- Performance-tests to aquire useful data
- Continue working on integration of the different project parts.
- Spend at least two days writing.
- Build/paint game area (?)
Accounting
André
Accounting
- write the program for steppermotor, and to get the angle when IR is received
- 3D Print the boxes for the beacons
- 3D print the tower