Progress for week 46 (2014)
From Robin
(Difference between revisions)
(→Rune) |
|||
(6 intermediate revisions not shown) | |||
Line 16: | Line 16: | ||
=== Accounting === | === Accounting === | ||
+ | * Made a new dataset based on the KITTY benchmark which contains real world vehicle-based data with LIDAR ground truth images. | ||
+ | * Changed fitness evaluation criteria to better account for algorithms with sparse results. | ||
+ | * Finished implementing the OpenCV SGBM algorithm, but initial evaluation still ongoing so no results to compare. | ||
== Else-Line == | == Else-Line == | ||
Line 24: | Line 27: | ||
=== Accounting === | === Accounting === | ||
+ | * Done some more testing | ||
+ | ** One-plus-lambda | ||
+ | ** Simulated annealing | ||
== Snorre == | == Snorre == | ||
Line 32: | Line 38: | ||
=== Accounting === | === Accounting === | ||
- | * | + | * Finished implementing the algorithm into my own project |
+ | * Started to do some experiments | ||
== Rune == | == Rune == | ||
Line 53: | Line 60: | ||
== André == | == André == | ||
- | === | + | ===Budget=== |
* write the program for steppermotor, and to get the angle when IR is received | * write the program for steppermotor, and to get the angle when IR is received | ||
* 3D Print the boxes for the beacons | * 3D Print the boxes for the beacons | ||
* 3D print the tower | * 3D print the tower | ||
+ | |||
+ | ===Accounting=== | ||
+ | * written program for stepper, and ir receiver. | ||
+ | * Started designing the box for the beacon. | ||
+ | |||
+ | == Bendik == | ||
+ | === Budget === | ||
+ | * Finish com. protocol between AI - motor controller | ||
+ | * Test performance of the robot | ||
+ | * Research GA path planning algorithms. | ||
+ | |||
+ | |||
+ | === Accounting === | ||
+ | * Finished com protocol | ||
+ | * Tested performance of robot | ||
+ | * Read articles about performance of A*(++) vs GA |
Current revision as of 10:08, 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 vehicle-based data with LIDAR ground truth images.
- Changed fitness evaluation criteria to better account for algorithms with sparse results.
- Finished implementing the OpenCV SGBM 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
- Done some more testing
- One-plus-lambda
- Simulated annealing
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
- Finished implementing the algorithm into my own project
- Started to do some experiments
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
Budget
- 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
Accounting
- written program for stepper, and ir receiver.
- Started designing the box for the beacon.
Bendik
Budget
- Finish com. protocol between AI - motor controller
- Test performance of the robot
- Research GA path planning algorithms.
Accounting
- Finished com protocol
- Tested performance of robot
- Read articles about performance of A*(++) vs GA