/pfrnns

Particle Filter Recurrent Neural Networks (AAAI 2020)

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

PF-RNNs

This is the PyTorch implementation of Particle Filter Recurrent Neural Networks (PF-RNNs).

Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee: Particle Filter Recurrent Neural Networks. AAAI Conference on Artificial Intelligence (AAAI), 2020.

Network structure

Above is the network structures for PF-LSTM and PF-GRU. In PF-RNNs, we maintain a set of latent particles and update them using particle filter algorithm. In our implementation, PF-LSTM and PF-GRU update particles in a parallel manner which benefit from the GPU acceleration.

Install requirements

pip install -r requirements.txt

Run the code

The training parameters are specified in configs/train.conf. To run the robot localization experiment, use

python main.py -c ./configs/train.conf

Cite PF-RNNs

If you find this work useful, please consider citing us

@article{ma2019particle,
  title={Particle Filter Recurrent Neural Networks},
  author={Ma, Xiao and Karkus, Peter and Hsu, David and Lee, Wee Sun},
  journal={arXiv preprint arXiv:1905.12885},
  year={2019}
}