---
license: mit
tags:
- robotics
- autonomous-vehicles
- object-tracking
- kalman-filter
- fmcw-lidar
- doppler-lidar
- pytorch
datasets:
- AevaScenes
metrics:
- prediction-error
pipeline_tag: object-detection
---

# D-KalmanNet: Neural Kalman Filtering for Doppler LiDAR Tracking

This repository contains the pre-trained weights for **D-KalmanNet**, the tracking component of the DPNet framework. D-KalmanNet integrates a structured Gaussian State Space (GSS) model with a recurrent neural network to accurately predict and track the future states of dynamic obstacles using measurements from (FMCW) **Doppler LiDAR**.

The full framework can be found in the official GitHub repository.

## Model Details

- **Developed by:** [UUwei-zuo](https://github.com/UUwei-zuo)
- **Dataset Trained On:** [AevaScenes](https://github.com/aevainc/aevascenes) 
- **Framework:** PyTorch
- **Associated Code:** [GitHub: UUwei-zuo/DPNet](https://github.com/UUwei-zuo/DPNet)
- **Paper:** [RA-L '26][DPNet: Doppler LiDAR Motion Planning for Highly-Dynamic Environments](https://arxiv.org/abs/2512.00375)

## How to Use

Intructions for loading the pretraining `model.pt` or training your custom model can be found in [GitHub: UUwei-zuo/DPNet](https://github.com/UUwei-zuo/DPNet).

## Citation

```bibtex
@article{zuo2026dpnet,
  author={Zuo, Wei and Ren, Zeyi and Li, Chengyang and Wang, Yikun and Zhao, Mingle and Wang, Shuai and Sui, Wei and Gao, Fei and Wu, Yik-Chung and Xu, Chengzhong},
  journal={IEEE Robotics and Automation Letters}, 
  title={DPNet: Doppler LiDAR Motion Planning for Highly-Dynamic Environments}, 
  year={2026},
  volume={11},
  number={6},
  pages={7190-7197},
  doi={10.1109/LRA.2026.3685933}
}
```