VQ action tokenizer used by the public BARX XP-900 pick-and-place walkthrough
and source-pretraining checkpoints.
The tokenizer converts normalized 7-D policy-action chunks into discrete action
tokens. It is task/dataset specific and should be used with the normalization
statistics and policy configuration supplied by the BARX release.
The tokenizer was trained with the public BARX VQ-BeT-derived training path on
the CC BY 4.0 XP-900 PnP dataset linked above. That dataset contains IIWA,
Kinova3, and UR5e source demonstrations for both pick-and-place directions.
Configuration and training commands are recorded in the BARX release
repository.
This artifact is intended for BARX simulation-policy training and evaluation.
It is not a standalone robot controller, is not validated on real robots, and
should not be substituted across tasks or action-normalization regimes without
retraining and validation.
This BARX model artifact is released under
Apache 2.0. The training data is
CC BY 4.0. Preserve attribution for the BARX data, VQ-BeT lineage, RoboCasa-X,
MiniVLA/OpenVLA, and BARX.
1@inproceedings{sridhar2026barx,
2 title = {Cross-Embodiment Transfer via Behavior-Aligned Representations},
3 author = {Sridhar, Ajay and Gao, Jensen and Yang, Jonathan and Mercat, Jean and Belkhale, Suneel and Sadigh, Dorsa},
4 booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
5 year = {2026}
6}
