ExylosAi/table_spill_cleanup_bimanual_rgbd_segmentation_poses
Viewer • Updated • 6.77k • 2.49k • 5
AI & ML interests
Robotics, autonomous robot manipulation, high-fidelity simulation,
Recent Activity
Organization Card
EXYLOS
Robot-ready skill datasets for manipulation policy learning and evaluation.
What we do
EXYLOS builds structured robot manipulation datasets for imitation learning, VLA models, policy training, and evaluation.
Raw videos show what happened, but policy learning also needs synchronized actions, states, task metadata, outcomes, failure context, and task-specific quality signals. EXYLOS turns human-seeded manipulation workflows performed in simulation into train-ready episodes with multi-view observations, trajectories, annotations, success/failure labels, and quality diagnostics.
Public sample datasets
This organization hosts compact inspection samples for checking schema, loading data, inspecting trajectories, and evaluating whether the EXYLOS format fits a robotics ML stack.
| Dataset | Status | Contents |
|---|---|---|
ExylosAi/pick_and_place_sample |
Available | 50 pick-and-place episodes, 21,412 frames, 5 RGB views, 9D Panda state/action, phase annotations, and success/failure labels. |
ExylosAi/table_spill_cleanup_bimanual |
Available | 50 bimanual spill-cleanup episodes, 67,461 frames, 7 RGB views, 4 segmentation-mask streams, object pose labels, 18D dual-Panda state/action, and 27 success / 23 failure episodes. No depth modality in this 50-episode sample. |
ExylosAi/table_spill_cleanup_bimanual_rgbd_segmentation_poses |
Available | 5 full-modality bimanual spill-cleanup episodes, 6,736 frames, 7 RGB views, 4 depth-map streams, 4 segmentation-mask streams, object pose labels, and cleanup success metrics. |
The two spill-cleanup samples share the same task family but serve different inspection needs: the 50-episode release provides broader trajectory coverage without depth, while the 5-episode release exposes the full RGB-D, segmentation, and pose modality stack.
Dataset format
EXYLOS samples are packaged to be compatible with the LeRobot ecosystem whenever possible. A typical dataset contains:
README.md
annotations.json
meta/
info.json
tasks.jsonl
episodes.jsonl
episodes_stats.jsonl
data/
chunk-000/
episode_000000.parquet
episode_000001.parquet
videos/
chunk-000/
observation.images.<camera_name>/
episode_000000.mp4
episode_000001.mp4
Depending on the dataset, additional external assets may be referenced from parquet rows:
videos/
chunk-000/
observation.masks.<camera_name>/
episode_000000/
*.png
observation.depths.<camera_name>/
episode_000000/
*.npy
Depth .npy assets are included only in datasets that explicitly advertise depth or RGB-D modalities.
Core signals:
| Category | Examples |
|---|---|
| Visual observations | Synchronized RGB wrist and scene views; depth and masks where included |
| Action and state | Robot state, action vectors, timestamps, frame indices |
| Object signals | Object IDs, 3D positions, orientations, velocities, task-state metrics such as dirty_fraction |
| Labels | Success, failure reason, terminal flags, collisions, aborts, retries |
| Annotations | Phase boundaries, hand labels, object notes, scores, derived metrics |
| Metadata | Task description, duration, splits, feature schema, validation stats |
Exact fields vary by dataset, so each repository includes a dataset-specific card.
Why EXYLOS datasets are different
- Structured, not raw: episodes include synchronized video, actions, state, metadata, annotations, and quality checks.
- Skill-oriented: each dataset is organized around a manipulation workflow rather than unrelated clips.
- Failure-aware: samples include failed attempts, aborts, collisions, incomplete task executions, and recovery-relevant labels when available.
- Modality-aware: samples range from compact RGB trajectory datasets to richer variants with segmentation masks, depth maps, and object-state streams.
- LeRobot-oriented: data is stored in open formats such as MP4, Parquet, JSON, JSONL, PNG, and NPY.
- Transfer-minded: workflows are captured from human intent in consumer VR and procedurally expanded, with added visual domain randomization for broader policy-learning experiments.
Intended use
Public samples are suitable for:
- inspecting EXYLOS schema and annotation conventions
- testing LeRobot-compatible loaders and training pipelines
- running small imitation-learning experiments
- reviewing multi-view video, trajectories, masks, object states, and phase annotations
- evaluating success/failure semantics and cleanup-quality metrics
- assessing whether a custom EXYLOS skill pack would fit your workflow
They are compact inspection datasets, not complete production-scale benchmarks.
Commercial datasets and custom skill packs
EXYLOS can generate custom robot-ready skill datasets for pick-and-place, bimanual manipulation, spill cleanup, sorting, binning, object rearrangement, failure recovery, and evaluation/regression sets.
Commercial deliveries can add depth, segmentation masks, object states, event labels, custom cameras, larger episode volumes, stricter QA, and internal-pipeline packaging.
License
Current public samples are released under Apache 2.0. Please check each dataset card and license file before using a sample in research, demos, training, or commercial workflows.
Contact
- Website: exylos.ai
- Email: contact@exylos.ai
- LinkedIn: Exylos on LinkedIn
If you need structured skill data, send us the target task, robot, modalities, format, evaluation criteria, and timeline.
models 0
None public yet