chqzhu/pi05-g1-ikea-joint
robotics model by chqzhu
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Five π0.5 policies, one per subtask of an IKEA table assembly, fine-tuned from pi05base for the Unitree G1 (29-DoF, Dex1-1 grippers). Each subfolder is a complete openpi checkpoint: an Orbax params/ store plus the assets/ holding its normalization statistics. The saved params/ are the EMA weights (decay 0.99, ≈100-step averaging window), not the final raw optimizer iterate — openpi writes emaparams in place of params when EMA is enabled. State and action are 16-dimensional: State comes from rt/lowstate; actions are rt/lowcmd (armsdk) targets, so the policy commands what a teleoperator's controller commanded — no IK anywhere. The source datasets store 19 dims (these 16 plus waist yaw/roll/pitch); the policies consume the leading 16 and leave the waist to the robot's own balance controller. Internally the 14 arm dims are trained as deltas against the observation's state while both grippers stay absolute (makeboolmask(14, -2)). openpi's AbsoluteActions inverts this at inference, so…
Read the full model card ↗ · Preview checked 2026-09-20T07:22:43.166Z
Inside the original model card — Document outline
- pi0.5 joint-space policies — Unitree G1 dual arm, IKEA table assembly
- Action space
- Usage
- Evaluation
- Provenance and limitations
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
chqzhu/pi05-g1-ikea-joint is a robotics model repository published by chqzhu on Hugging Face. The source reports the openpi library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- robotics
- Library
- openpi
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-20T06:13:32.000Z
- Last modified
- 2026-09-20T06:22:07.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-20T06:35:52.874Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
1977kantomoyuki/act_so101_test_20260920_143445
abdulrahimmirani/pi05-piperx-pick-cube-ft01-simdata
abdulrahimmirani/pi05-piperx-pick-cube-ft02-simdata
ases200q2/UR10_RTDE_SpaceMouse_EE_pick_and_place_object_tabletop_v2_act_20260916_095806
Dongkkka/Task_000004_Peanut_Pick_Place_lerobot_Intern_Diffusion_bs32_step5000