Enabling Learning-based Navigation in Obscurants with Lightweight, Low-cost Millimeter Wave Radar Using Cross-modal Contrastive Learning of Representations
This repo demonstrate using generative model to reconstruct mmWave radar range data to dense range data closer to LiDAR ground truth.
The reconstructed range data can be used as signals for control policys. Futher details please refer to our website.
To run the inference model on colab. Please create a short cut of the dataset to your own google drive
pretrained model on our google drive
To run the inference model on colab. Please also create a short cut of pretrained models to your own google drive
-
cGAN generate
-
VAE generate
