# Generalizable Audio-Visual Navigation via Binaural Difference Attention and Action Transition Prediction

arXiv: https://arxiv.org/abs/2604.05007 · HTML: https://mlsanity.com/paper/2604.05007/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [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)
- [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)
- [Vision-Language Navigation: A Survey and Taxonomy](https://mlsanity.com/paper/2108.11544/) (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)
- [Zero-shot Object Navigation with Vision-Language Models Reasoning](https://mlsanity.com/paper/2410.18570/) (2024)
- [Pay Self-Attention to Audio-Visual Navigation](https://mlsanity.com/paper/2210.01353/) (2022)
- [Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges](https://mlsanity.com/paper/2311.18044/) (2023)
- [Audio-Guided Dynamic Modality Fusion with Stereo-Aware Attention for Audio-Visual Navigation](https://mlsanity.com/paper/2509.16924/) (2025)
- [CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments](https://mlsanity.com/paper/2306.04047/) (2023)
- [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)
- [Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation](https://mlsanity.com/paper/2304.10773/) (2023)
- [Generating Diverse Audio-Visual 360 Soundscapes for Sound Event Localization and Detection](https://mlsanity.com/paper/2504.02988/) (2025)

## Abstract (arXiv)

In Audio-Visual Navigation (AVN), agents must locate sound sources in unseen 3D environments using visual and auditory cues. However, existing methods often struggle with generalization in unseen scenarios, as they tend to overfit to semantic sound features and specific training environments. To address these challenges, we propose the Binaural Difference Attention with Action Transition Prediction (BDATP) framework, which jointly optimizes perception and policy. Specifically, the Binaural Difference Attention (BDA) module explicitly models interaural differences to enhance spatial orientation, reducing reliance on semantic categories. Simultaneously, the Action Transition Prediction (ATP) task introduces an auxiliary action prediction objective as a regularization term, mitigating environment-specific overfitting. Extensive experiments on the Replica and Matterport3D datasets demonstrate that BDATP can be seamlessly integrated into various mainstream baselines, yielding consistent and significant performance gains. Notably, our framework achieves state-of-the-art Success Rates across most settings, with a remarkable absolute improvement of up to 21.6 percentage points in Replica dataset for unheard sounds. These results underscore BDATP's superior generalization capability and its robustness across diverse navigation architectures.