Skip to content

Instantly share code, notes, and snippets.

@UditSinghParihar

UditSinghParihar/README.md

Created August 26, 2019 00:03
Show Gist options
  • Save UditSinghParihar/aec4837b09616513bddc4dfd91127627 to your computer and use it in GitHub Desktop.
Save UditSinghParihar/aec4837b09616513bddc4dfd91127627 to your computer and use it in GitHub Desktop.
Download ZIP
Dataset 2 results of manhattan
Raw
README.md
  1. Manhattan constraints results on dataset 2.
  2. Due to smooth robot trajectories, the final manhattan map generated on the whole dataset seems pretty close to ground truth.
  3. This could be good input for MLP and graph optimization can be done using both Manhattan world constraints and loop closing constraints on dense graph in one shot.
@UditSinghParihar
Copy link
Author

UditSinghParihar commented Aug 26, 2019 •
edited
Loading

  1. Dense ground truth trajectory:
    ground_truth
  2. Dense noisy trajectory:
    dense_noisy
  3. Sparse manhattan map generated on noisy trajectory:
    a. For generating manhattan map, boundaries are taken to be angle bisector of each quadrant(45, 135, 225) and no other hardcoding is done.
    manh

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment