# Transformer-Based Token Fusion and Dynamic Graph Planning for Audio-Visual Navigation

arXiv: https://arxiv.org/abs/2609.17421 · HTML: https://mlsanity.com/paper/2609.17421/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Look, Listen, and Act: Towards Audio-Visual Embodied Navigation](https://mlsanity.com/paper/1912.11684/) (2019)
- [Semantic Audio-Visual Navigation](https://mlsanity.com/paper/2012.11583/) (2020)
- [VisualEchoes: Spatial Image Representation Learning through Echolocation](https://mlsanity.com/paper/2005.01616/) (2020)
- [Sound Adversarial Audio-Visual Navigation](https://mlsanity.com/paper/2202.10910/) (2022)
- [Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds](https://mlsanity.com/paper/2111.14843/) (2021)
- [Measuring Acoustics with Collaborative Multiple Agents](https://mlsanity.com/paper/2310.05368/) (2023)
- [Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation](https://mlsanity.com/paper/2308.10306/) (2023)
- [Pay Self-Attention to Audio-Visual Navigation](https://mlsanity.com/paper/2210.01353/) (2022)
- [Audio-Guided Dynamic Modality Fusion with Stereo-Aware Attention for Audio-Visual Navigation](https://mlsanity.com/paper/2509.16924/) (2025)
- [DOPE: Dual Object Perception-Enhancement Network for Vision-and-Language Navigation](https://mlsanity.com/paper/2505.00743/) (2025)
- [Advancing Audio-Visual Navigation Through Multi-Agent Collaboration in 3D Environments](https://mlsanity.com/paper/2509.22698/) (2025)
- [Iterative Residual Cross-Attention Mechanism: An Integrated Approach for Audio-Visual Navigation Tasks](https://mlsanity.com/paper/2509.25652/) (2025)
- [DGFNet: End-to-End Audio-Visual Source Separation Based on Dynamic Gating Fusion](https://mlsanity.com/paper/2504.21366/) (2025)
- [Dynamic Multi-Target Fusion for Efficient Audio-Visual Navigation](https://mlsanity.com/paper/2509.21377/) (2025)
- [BSS-CFFMA: Cross-Domain Feature Fusion and Multi-Attention Speech Enhancement Network based on Self-Supervised Embedding](https://mlsanity.com/paper/2408.06851/) (2024)
- [VNet: A GAN-based Multi-Tier Discriminator Network for Speech Synthesis Vocoders](https://mlsanity.com/paper/2408.06906/) (2024)
- [Modality-Invariant Bidirectional Temporal Representation Distillation Network for Missing Multimodal Sentiment Analysis](https://mlsanity.com/paper/2501.05474/) (2025)
- [FSDENet: A Frequency and Spatial Domains based Detail Enhancement Network for Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2510.00059/) (2025)
- [Audio-Guided Visual Perception for Audio-Visual Navigation](https://mlsanity.com/paper/2510.11760/) (2025)

## Abstract (arXiv)

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.