Metraipolis › archive › dc_2533c004ff22
DroneWAM: Efficient World Action Model for Drone Visual Navigation — arXiv:2609.33148
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33148
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:51:22.811Z
- SHA-256 of the archived text
17d5a23593115fa41545b9244c429aa3137004b86628cfe7cced9d525f3503b4- Stable URL of this page
https://metraipolis.com/documento/dc_2533c004ff22
How to cite
DroneWAM: Efficient World Action Model for Drone Visual Navigation — arXiv:2609.33148 — arXiv (en), https://arxiv.org/abs/2609.33148 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2533c004ff22 (Metraipolis archive dc_2533c004ff22, sha256 17d5a23593115fa41545b9244c429aa3137004b86628cfe7cced9d525f3503b4)
BibTeX
@misc{dc2533c004ff22,
title = {DroneWAM: Efficient World Action Model for Drone Visual Navigation — arXiv:2609.33148},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33148},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2533c004ff22; sha256 17d5a23593115fa41545b9244c429aa3137004b86628cfe7cced9d525f3503b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33148. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World-action models give visual navigation agents a way to anticipate how candidate actions will change future observations and to act from the predicted consequences. For drones, this capability must operate under tight accuracy and efficiency constraints. We present DroneWAM, an efficient world-action model for drone visual navigation. DroneWAM adopts a JEPA-based architecture to model future states directly in representation space, avoiding the cost of explicit future image generation. A pretrained Resampler further compresses dense encoder features into fewer latent tokens, reducing the computation repeated at each imagined step. We also introduce adaptive rollout, where a preference-trained Gate adaptively allocates prediction depth according to the current scene. To support learning under richer aerial motion, we construct DroneNav-6D, a simulated visual navigation dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances. On DroneNav-6D, DroneWAM achieves the best trajectory accuracy among the compared methods. Adaptive rollout further reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy, demonstrating that predictive computation can be allocated more effectively across scenes. \href{ this https URL }{Codes and data} will be released.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.33148 — 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 2026-10-07T23:29:27.149Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).