Metraipolis › archive › dc_2fca05da8a2a

UniPoint: Unified Point-Level Sensor Fusion for Humanoid Locomotion Across Challenging Terrains — arXiv:2609.23666

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.23666
License (as archived): CC0-1.0
Archived: 2026-10-09T22:24:03.847Z
SHA-256 of the archived text: 0b65cc4ab7be1de3408e7bf35a8bbd553d8601cc76cd04bc56ad3d76a3634bbe
Stable URL of this page: https://metraipolis.com/documento/dc_2fca05da8a2a

How to cite

UniPoint: Unified Point-Level Sensor Fusion for Humanoid Locomotion Across Challenging Terrains — arXiv:2609.23666 — arXiv (en), https://arxiv.org/abs/2609.23666 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fca05da8a2a (Metraipolis archive dc_2fca05da8a2a, sha256 0b65cc4ab7be1de3408e7bf35a8bbd553d8601cc76cd04bc56ad3d76a3634bbe)

BibTeX

@misc{dc2fca05da8a2a,
  title = {UniPoint: Unified Point-Level Sensor Fusion for Humanoid Locomotion Across Challenging Terrains — arXiv:2609.23666},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23666},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fca05da8a2a; sha256 0b65cc4ab7be1de3408e7bf35a8bbd553d8601cc76cd04bc56ad3d76a3634bbe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23666. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-world deployment requires humanoid robots to cross highly heterogeneous terrain safely, with perception that simultaneously provides wide coverage, local accuracy, and redundancy against sensor failure. Existing approaches struggle to satisfy all three: one forward depth camera or nearby height sampling covers too little; odometry-corrected elevation maps drift under aggressive motion and miss thin vertical structures; image-level encoding costs grow with camera count. We present UniPoint, a humanoid whole-body locomotion framework built on multi-source point-level sensor fusion. Measurements from a 360° light detection and ranging (LiDAR) sensor and two depth cameras are early-fused into one base-frame point set. Voxelization resamples it to a fixed number of tokens encoded by linear self-attention and proprioception-queried cross-attention, decoupling forward cost from sensor count. The point set retains standing thin barriers; a single-modality failure removes only part of the tokens, so the policy degrades gracefully. A single training run with terrain-aware rewards, perception-degradation injection, and domain randomization produces one policy for all eight terrain types, deployed on an onboard RK3588 without fine-tuning. On a DR02 humanoid, 20 trials at each of nine real-world settings over seven terrain types validate the policy on 70-cm-high platforms, 100-cm gaps, thin barriers, and sparse or narrow footholds; it also generalizes zero-shot outdoors.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.23666 — 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 2026-10-09T21:59:59.616Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).