NRDK: Neural Radar Development Kit¶
The Neural Radar Development Kit (NRDK) is an open-source and MIT-licensed Python library and framework for developing, training, and evaluating machine learning models on radar spectrum and multimodal sensor data.
Built around typed, high modular interfaces, the NRDK is designed to reduce the barrier of entry to learning on spectrum via out-of-the-box reference implementations for red-rover data and the I/Q-1M Dataset, while also providing an easy path towards customization and extensions for other radar and data collection systems.
-
neural radar development kit core framework
-
cli tools for working with NRDK output conventions
-
reference implementation for Towards Foundational Models for Single-Chip Radar
-
statistical testing for time series performance metrics
Setup¶
The NRDK is intended to be used as a library; we recommend installing it as a submodule:
Extras
The NRDK library also includes the following extras:
Development¶
After setting up nrdk for development (see above — don't forget to install the pre-commit hooks!), you can start contributing!
# Run all tests
uv run pytest --cov=src/nrdk --cov-report=html tests
# Build & serve documentation locally
uv run --extra docs mkdocs serve
Note that all code must pass our pre-commit hooks (ruff + pyright + pytest), which you can also run manually:
See Also¶
-
a multimodal mmWave Radar spectrum ecosystem
-
python interface for collecting raw time signal data from TI mmWave radars
-
abstract interface for composable dataloaders and preprocessing pipelines
-
our latest work, GRT: Towards Foundational Models for Single-Chip Radar
-
our prior work, DART: Implicit Doppler Tomography for Radar Novel View Synthesis
-
our previous data collection platform for radar time signal