ANAVI is a framework for "Audio Noise Awareness using Visuals of Indoor environments for NAVIgation". This is presented at 8th Annual Conference on Robot Learning, 2024.
Website: https://anavi-corl24.github.io
- Download or clone this repo
- Creat conda/mamba environment
- Install
anp
by:pip install -e .
- Install PyTorch
Follow instructions on DATAGEN.md. Alternately, you can also download the simulated data sample here.
- Train
python train.py --config=dirdis_huberloss.yaml
python train.py --config=ego_huberloss.yaml
python train.py --config=pano_huberloss.yaml
You can train your own model by modifying config_template.yaml
.
- Evaluate
python train.py --config=configs/visdirdis_ce.yaml
@article{jain2024anavi,
author = {Jain, Vidhi and Veerapaneni, Rishi and Bisk, Yonatan},
title = {ANAVI: Audio Noise Awareness using Visuals of Indoor environments for NAVIgation},
journal = {8th Annual Conference on Robot Learning},
year = {2024},
}
If you have questions or concerns, you can raise an issue or email [email protected].