Trossen Robotics / AgileX
ALOHA 2 / Cobot Magic (dual-arm)
Facts
- Form
- Dual arm 2 Source
- DoF
- 12 0 Source
- End effector
- Dual parallel grippers 0 Source
- SDK / ROS
- github.com ↗ 0 Source
- Public price (CNY)
- unverified Unverified 0 Source
- Data formats
- ALOHA HDF5 · LeRobot 0 Source
Sources · 2 sources
form https://github.com/thu-ml/RoboticsDiffusionTransformer Official page · Fetched 2026-09-04 · No snapshot stored yet RDT-1B fine-tuned on ALOHA dual-arm with 6K+ episodes
form https://github.com/OpenHelix-Team/VLA-Adapter Official page · Fetched 2026-09-04 · No snapshot stored yet VLA-Adapter：ALOHA deployment support, verified on Cobot Magic
Models declaring this form as a target
Vendor claims, not verified compatibility. Verified states appear in the matrix below.
HPT（Heterogeneous Pre-trained Transformers） MIT (Lirui Wang, Kaiming He et al.) Vendor-declared target form
Compatibility on this embodiment
Legend Officially supportedCommunity reproducedFine-tunable in theoryUnsupportedUnknown Vendor-declared target form 13 / 40 cells with a definite status
Public datasets covering this body
Matched by the robot names or form the dataset states. Scale as stated; blanks are unknowns.
| Dataset | Hours | Episodes | Format | Licence |
|---|---|---|---|---|
| InternData-A1 InternRobotics | 7,433 | 630,000 | LeRobot v2.1 and LeRobot v3 (Parquet + MP4) | ✗ CC BY-NC-SA 4.0 (HF card); Mod |
| Fourier ActionNet Fourier Intelligence (FFTAI) | 140 | 30,000 | LeRobot v2 (LeRobotDatasetV2; raw MP4 RGB + MKV depth + HDF5 state/action + JSON timestamps with conversion script) | ✗ CC BY-NC-SA 4.0 |
| ARIO (All Robots In One) ARIO team (hosted on OpenI, Peng Cheng Laboratory) | — | 3,033,188 | custom (ARIO unified format) | ? CC-BY 4.0 or MIT for ARIO-coll |
| AgiBot World (Alpha / Beta) AgiBot (agibot-world) / OpenDriveLab | — | 1,003,672 | LeRobot (README); HF card format tag: webdataset | ✗ CC BY-NC-SA 4.0 |
| PhysicalAI-Robotics-GR00T-X-Embodiment-Sim NVIDIA | — | 345,102 | LeRobot v2 layout (GR00T LeRobot-compatible: data/chunk-*/episode_*.parquet + videos/*.mp4 + meta/info.json, modality.json, tasks.jsonl) | ✓ cc-by-4.0 |
| RoboMIND X-Humanoid (x-humanoid-robomind) | — | 107,000 | — | ✓ apache-2.0 |
| RoboTwin 2.0 RoboTwin-Platform (Tianxing Chen et al.) | — | 100,000 | HDF5 | ✓ MIT |
| DexMimicGen Datasets NVIDIA (NVlabs) | — | 21,000 | HDF5 | ? cc-by-nc-sa-4.0 (HF card YAML) |
| Galaxea Open-World Dataset (G0 data) Galaxea (OpenGalaxea) | — | — | LeRobot (HF tag 'lerobot') | ✗ cc-by-nc-sa-4.0 |
| Unitree Robotics open datasets (Hugging Face org) Unitree Robotics | — | — | LeRobot v3 (codebase_version 'v3.0' in sampled dataset G1_Dex1_Wipe_Board) | ✓ Apache-2.0 (94 of 160 datasets |
| AgiBot DigitalWorld (+ AgiBot World Challenge datasets) AgiBot (AgiBot World / OpenDriveLab) | — | — | custom (MP4 RGB + PNG depth + HDF5 proprioception + JSON task info); conversion scripts to LeRobot v2.0 provided | ✗ CC BY-NC-SA 4.0 |
| Open-TeleVision teleoperation datasets OpenTeleVision (Xuxin Cheng et al.) | — | — | custom (raw recordings placed in data/recordings/ and processed by repo scripts) | ? Apache-2.0 (code repository); |
Clear direction, grounded judgement.