One numpy-in / numpy-out API for robotics sensor datasets.
apairo is a unified loader for robotics sensor datasets — lidar, cameras,
poses, IMU, labels — with one chainable API across synchronous (KITTI-style)
and asynchronous (multi-rate) layouts. No bespoke glob + np.load loaders,
no hand-written timestamp matching: everything is a dataset you filter,
select, cache, synchronize, concat and feed straight to a PyTorch
DataLoader.
- numpy in, numpy out —
ds[i].data["lidar"] -> np.ndarray; convert to torch/tf at the edge, never inside the dataset. - everything is a dataset —
filter / select / cache / join / concat / synchronize / split / transformall return chainable, lazy views. .apairois the source of truth on disk — channels (raw + derived) are declared in a sidecar; expensive preprocess output is persisted and reloaded transparently.
import apairo
ds = (apairo.RawDataset("/data/mission", keys=["lidar", "image", "gps"])
.synchronize(reference="lidar", method="nearest", tolerance=0.05)
.filter(lambda s: s.data["lidar"].shape[0] > 1000))
ds[0].data # {"lidar": (N, 4), "image": (H, W, 3), "gps": (3,)}
# an apairo dataset *is* a torch Dataset -> DataLoader(ds, collate_fn=...), no adapterPoint RawDataset at a directory and it loads — no code. When a channel's clock
lives in its filenames, declare it right there and apairo reads it in memory,
never writing into your data. See
Bring your own dataset.
Mechanisms live in the core; collections live in satellites. The core never gains a dependency beyond numpy + PyYAML.
| Repo | What it does |
|---|---|
| apairo | The core — load / synchronize / filter / cache / preprocess robotics datasets, one API for sync + async layouts. |
| apairo_transform | Access-time numpy transforms & augmentations (range/box filters, voxelization, rotations, interpolators). |
| apairo_preprocess | Heavy offline preprocessors, persisted as derived .apairo channels and reloaded transparently. |
| apairo_extractor | Turn ROS bags into the apairo / KITTI on-disk layout, with optional preprocessing. |
| apairo_rr | Rerun-based lidar / multi-sensor visualization of apairo datasets. |
| apairo_huggingface | Label apairo datasets and export them to the HuggingFace LeRobotDataset format. |
pip install apairo # Python >= 3.11
pip install apairo[vision] # optional: image loading (Pillow)- Documentation — quickstart, the
.apairoschema, synchronizing async sensors, preprocessing. - Bring your own dataset — YAML profiles, thin subclasses, filename-encoded keys.
- apairo-robotics/apairo — source, issues, contributing.