Metraipolis › archive › dc_ee1f93aa508d

Aero-VPA: Few-Step Flow-Matching Control over Non-Reconstructive JEPA Latents for Agile Flight on Edge Hardware — arXiv:2611.04392

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04392
License (as archived)
CC0-1.0
Archived
2026-11-04T12:42:43.867Z
SHA-256 of the archived text
1394a7cbb8399d45cd0c3e193a3f113525c77da31c9595eaf8775edcc587cf63
Stable URL of this page
https://metraipolis.com/documento/dc_ee1f93aa508d

How to cite

Aero-VPA: Few-Step Flow-Matching Control over Non-Reconstructive JEPA Latents for Agile Flight on Edge Hardware — arXiv:2611.04392 — arXiv (en), https://arxiv.org/abs/2611.04392 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee1f93aa508d (Metraipolis archive dc_ee1f93aa508d, sha256 1394a7cbb8399d45cd0c3e193a3f113525c77da31c9595eaf8775edcc587cf63)
BibTeX
@misc{dcee1f93aa508d,
  title = {Aero-VPA: Few-Step Flow-Matching Control over Non-Reconstructive JEPA Latents for Agile Flight on Edge Hardware — arXiv:2611.04392},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04392},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee1f93aa508d; sha256 1394a7cbb8399d45cd0c3e193a3f113525c77da31c9595eaf8775edcc587cf63},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04392. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models generalize across tasks, but their autoregressive decoders need sequential forward passes in proportion to the action horizon, each bounded below on embedded aerial platforms by streaming billions of parameters from memory. We present Aero-VPA, a lightweight Vision-Predictor-Action architecture for 3D navigation on edge hardware. A compact RGB-D Vision Transformer and a five-head ensemble predictor, trained without pixel reconstruction, forecast the next latent state; a Conditional Flow Matching solver generates a velocity and yaw-rate chunk in two Euler steps, so each decision takes five sequential network evaluations; and the ensemble dispersion drives an uncertainty fallback. Version 1 specified the architecture, deployment and protocol without results. This version reports the first closed-loop evaluation: PX4 software-in-the-loop simulation of quadrotor missions in procedurally generated forests. Behaviour cloning failed on all 60 missions despite open-loop errors of 0.02-0.04 m/s: the policy copies its last command, a copycat form of causal confusion. DAgger with a privileged, safety-gated supervisor gave the first successes but plateaued at 11.1-21.1% across six checkpoints. A map-free runtime shield with a 15 s depth memory, barrier constraints, a cap on motion outside the 73-degree field of view and backoff along the flown path raised the first DAgger policy's success on 180 paired missions from 21.1% to 52.2% (95% CI [45.0, 59.4]; exact McNemar p = 1.2 x 10^-10) and cut its crashes from 72.2% to 22.2%, while timeouts rose from 2.8% to 23.3%. All six checkpoints gained 30.0-34.4 percentage points, at mean speeds of 1.16-1.36 m/s. The code ( this https URL ), the trained policy (72.6 MB, this https URL ) and the full benchmark dataset are public.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Logic in Computer Science (cs.LO) ; Machine Learning (cs.LG); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.04392 — 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 2026-11-04T12:29:47.387Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).