LATENT
Research whole-body tennis controller evaluated on Unitree G1.
Identity and state
- No openness, availability, deployment, or interoperability facet is published for this identity.
Reviewed relationships
| State | Related entity | Relation | Scope | Boundary |
|---|---|---|---|---|
| Verified | → Unitree G1 | evaluated on | humanoid tennis paper | The paper and code target Unitree G1; ET1 is not retroactively inserted. |
| Boundary | → Galbot ET1 | not proven on | public evidence boundary | The tennis paper evaluates Unitree G1; an ET1 tennis-training announcement is not that evaluation. |
| Verified | → MuJoCo | uses simulator | repository simulator path | The README names MuJoCo. |
Canonical evidence claims
Claims are projected from authored tables. A dash remains an explicit missing value; it is never filled from a neighboring product or name match.
| Metric | Value | Class |
|---|---|---|
| Control / tracking note | default preprocess frequency 50 Hz [software-m10] | unitree-g1-research-code |
| License | — | unitree-g1-research-code |
| Paper | arXiv:2603.12686 [software-r2] | unitree-g1-research-code |
| Simulator in README | MuJoCo [software-m10] | unitree-g1-research-code |
| Stated target | Unitree G1 (G1TrackingGeneral; motion path UnitreeG1) [software-m10] | unitree-g1-research-code |
| LATENT | arXiv:2603.12686 [research-systems-r1] | paper-body-unitree-g1 |
| LATENT | paper eval — tennis whole-body control; the announced Galbot biped’s tennis mention is not this paper’s eval [research-systems-r1] | paper-body-unitree-g1 |
| LATENT | — | paper-body-unitree-g1 |
| LATENT | 29-DoF Unitree G1 [research-systems-r1] | paper-body-unitree-g1 |
| LATENT | official code on Galbot GitHub [research-systems-r1] | paper-body-unitree-g1 |
Source ledger
- Research LATENT — “Learning Athletic Humanoid Tennis Skills…”. Type: research paper. ID: arXiv:2603.12686. Retrieved: 2026-08-25. reviewed 2026-08-25
- Manual GalaxyGeneralRobotics — LATENT README (default branch: master). Type: official research-code repository. Retrieved: 2026-08-27. reviewed 2026-08-27
- Research Zhang et al. — LATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data. Type: research. Venue: IROS 2026. Retrieved: 2026-08-27. reviewed 2026-08-27
What is not inferred
No fuzzy entity matching, adjacent-column borrowing, universal compatibility, commercial maturity, or checkpoint-to-product identity. Absence of a relation means unreviewed or unsupported here—not proven incompatibility.