Metraipolis › archive › dc_4237ddce0708
EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation — arXiv:2609.36575
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36575
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T19:15:16.563Z
- SHA-256 of the archived text
25b223d7525a485dfce5ebe6782185869a677d39723387e24a67ad6faf2654dc- Stable URL of this page
https://metraipolis.com/documento/dc_4237ddce0708
How to cite
EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation — arXiv:2609.36575 — arXiv (en), https://arxiv.org/abs/2609.36575 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4237ddce0708 (Metraipolis archive dc_4237ddce0708, sha256 25b223d7525a485dfce5ebe6782185869a677d39723387e24a67ad6faf2654dc)
BibTeX
@misc{dc4237ddce0708,
title = {EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation — arXiv:2609.36575},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36575},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4237ddce0708; sha256 25b223d7525a485dfce5ebe6782185869a677d39723387e24a67ad6faf2654dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36575. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visuomotor policies for humanoid loco-manipulation must generalize across object poses and lighting from only a handful of demonstrations. 3D Diffusion Policy (DP3) conditions a diffusion-based action generator on point-cloud features, but its PointNet-style encoder has no built-in equivariance to the rotations, translations, and scalings (SIM(3)) that manipulation tasks respect. EquiBot closed this gap for wheeled manipulators with a SIM(3)-equivariant Vector Neuron Network (VNN) encoder. We extend this to a substantially more complex embodiment, the 43-joint Unitree G1 humanoid, and propose EquivDP3: a two-stage policy where a high-level diffusion planner with a SIM(3)-equivariant VNN encoder emits 6 Hz whole-body command chunks, executed at 50 Hz by a frozen, pre-trained RL locomotion policy and a differential inverse-kinematics module for the arms, trained end-to-end by behavior cloning. Across two simulated IsaacLab benchmarks and four non-equivariant baselines (5-100 demonstrations, in- and out-of-distribution), EquivDP3's advantage concentrates in the low-data regime: at 5-10 demonstrations it reaches 67.1% success versus 38.2-52.4% for the baselines, while by 50-100 all encoders converge (74.3-85.2%) and the ordering is no longer meaningful. A proprioception-only control confirms this gap is genuinely perceptual: with the point cloud removed, success drops to 31% vs. 60% (EquivDP3) at 5 demonstrations and 78% vs. 99% at 10, but vanishes by 50-100, showing the high-data plateau reflects a benchmark ceiling, not five encoders learning the same invariance. The encoder costs only 0.8 ms of extra latency per action chunk over the PointNet encoder it replaces. Baking geometric symmetry into a hierarchical diffusion policy's perception backbone is a practical, nearly free way to improve data efficiency for humanoid loco-manipulation when demonstrations are scarce. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.36575 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T18:40:59.422Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).