Metraipolis › archive › dc_193b3d3dd449
Transformer-Based Token Fusion and Dynamic Graph Planning for Audio-Visual Navigation — arXiv:2609.17421
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17421
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:32:28.065Z
- SHA-256 of the archived text
42af4c71387cd15b9e3ac39d46bc1e1c9fe807201a61d26916e9394b3315f7b3- Stable URL of this page
https://metraipolis.com/documento/dc_193b3d3dd449
How to cite
Transformer-Based Token Fusion and Dynamic Graph Planning for Audio-Visual Navigation — arXiv:2609.17421 — arXiv (en), https://arxiv.org/abs/2609.17421 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_193b3d3dd449 (Metraipolis archive dc_193b3d3dd449, sha256 42af4c71387cd15b9e3ac39d46bc1e1c9fe807201a61d26916e9394b3315f7b3)
BibTeX
@misc{dc193b3d3dd449,
title = {Transformer-Based Token Fusion and Dynamic Graph Planning for Audio-Visual Navigation — arXiv:2609.17421},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17421},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_193b3d3dd449; sha256 42af4c71387cd15b9e3ac39d46bc1e1c9fe807201a61d26916e9394b3315f7b3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17421. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio-Visual Navigation (AVN) requires an agent to localize and navigate toward a continuously vocalizing target relying solely on visual observations and acoustic cues. Currently, systems lack the ability to adaptively correct and replan when faced with incomplete or misleading visual perception. Furthermore, relying on physical collisions to compensate for missing visual information results in inefficient and unsafe navigation, whereas existing methods are overly dependent on passive visual perception. To address these issues, we propose the Transformer-based Token Fusion and Dynamic Graph Planning (TDGP) model, which incorporates high-level perception layers and leverages the Transformer model to fuse multimodal cues for precise local planning. Next, a low-level planning layer is designed that uses physical collision penalties to remove edges that collide with the map in real time and apply corresponding penalties, forcing the agent to automatically re-plan to compensate for the lack of visual information. Experiments show that our TDGP model outperforms baseline models on the Replica and Matterport3D (MP3D) datasets, and that the model's sound enhancement strategy significantly improves generalization in unheard acoustic scenarios. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Signal Processing (eess.SP). Pagina del lavoro: https://arxiv.org/abs/2609.17421 — 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 2026-10-15T18:03:09.536Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).