Fifth progress presentation

Vegard Bergsvik Øvstegård

Fri - 13 Nov 2020



Days until delivery: 109 days

GIL-UAV

GPS-Independent Localization for UAVs

System diagram
System diagram

Framework simulation

Status from previous progress presentation

Task Progress
In progress:
1. Tune the U-net
2. Acquire & improve Dataset*
3. Train the U-net*
To do:
4. Get drone footage
5. Implement framework(C++, SIMD, CUDA)
Completed
Code dataset-producing software

Updated tasks* New tasks**

Updated tasks

Task Progress
4. Get drone footage
5. Implement framework(C++, SIMD, CUDA)
5. Report writing

Get drone footage

  • A1/A2/A3 drone licence
    • A2 is not free of charge..
  • Footage of different environments:
    • Snow
    • No leafs
    • Rain

Implement framework

  • Acquired Nvidia Jetson Nano and Nvidia Jets Tegra TX1.
  • Started coding project in C++.

Current status and progress

Task Progress
In progress:
1. Tune the U-net
2. Acquire & improve Dataset
3. Train the U-net
4. Get drone footage*
5. Implement framework(C++, SIMD, CUDA)*
5. Report writing*
To do:
6. Create test-set from drone footage**
7. Test segmentation on Nvidia boards**

Updated tasks* New tasks**

Completed tasks

  • Code dataset-producing software
  • Create U-net (PyTorch, multi-GPU)
  • Implement naive MCL algorithm (Python)
  • Get hardware (nVIDIA Jetson TX1 & Jetson Nano)

Plan for the next fortnight:



Week 5 Week 6
Test segmentation on Nvidia Boards Get more drone footage
Develop further on MCL C++ implementation Write more on report.
Acquire & improve Dataset Write loads more on the report.

Print

Back