JonasFrey96

I face the exact same problems. Did you find a solution to the problem ?

In my specific use case, it would be great to allow for parsing a list of data classes. This would help a lot. I tried to look into the code,...

Hello @grlee77, Thanks a lot for your kind response. I found an efficient workaround by using the FastGeodis library (BSD-3): https://github.com/masadcv/FastGeodis This avoids creating a graph. Creating python bindings for...

maybe we can improve this - visualizing this plot would be nice

I checked the confidence generation: In update_running_mean: ```python # The confidence used to be computed as the distance to the center of the Gaussian given factor*sigma # This is certainly...

Still the problem would remain when we start out training the confidence is very high everywhere and then only gets smaller for regions over time - therefore initially the traversability...

@Matthewjsiv we are currently having a big push to open-source a dataset with over 100 environments. The data should be officially ready by Feb. 2025. I hope this will be...

Did you manage to solve this issue ?

Hi Victor, I ran into some troubles using the raycasting: Here is a minimal script explaining what I tried to do: ```python import wavemap as wm import numpay as np...

Hi Victor, Big thanks this fixed everything:  Here is the correct code snippet that runs: ```cpp const auto colliding_index = raycast::first_collision_index( map, W_start_point, W_end_point, log_odds_occupancy_threshold_); if (colliding_index) { const...