Dynamic Multi-Target Fusion for Efficient Audio-Visual Navigation
This addresses the challenge of guiding robots to locate audio sources using dynamic fusion of visual and auditory data, with incremental improvements in multimodal fusion strategies for robotic navigation.
The paper tackles the problem of effectively leveraging multimodal cues for audio-visual navigation by proposing DMTF-AVN, which achieves state-of-the-art performance in success rate, path efficiency, and scene adaptation on Replica and Matterport3D datasets.
Audiovisual embodied navigation enables robots to locate audio sources by dynamically integrating visual observations from onboard sensors with the auditory signals emitted by the target. The core challenge lies in effectively leveraging multimodal cues to guide navigation. While prior works have explored basic fusion of visual and audio data, they often overlook deeper perceptual context. To address this, we propose the Dynamic Multi-Target Fusion for Efficient Audio-Visual Navigation (DMTF-AVN). Our approach uses a multi-target architecture coupled with a refined Transformer mechanism to filter and selectively fuse cross-modal information. Extensive experiments on the Replica and Matterport3D datasets demonstrate that DMTF-AVN achieves state-of-the-art performance, outperforming existing methods in success rate (SR), path efficiency (SPL), and scene adaptation (SNA). Furthermore, the model exhibits strong scalability and generalizability, paving the way for advanced multimodal fusion strategies in robotic navigation. The code and videos are available at https://github.com/zzzmmm-svg/DMTF.