Submitted:
10 November 2026
Posted:
11 November 2026
You are already at the latest version
Abstract
Embodied intelligence requires perception, reasoning, action, and interaction, yet existing systems predominantly rely on vision, text, and proprioception. Audio offers complementary evidence about environments and human intentions, but research remains fragmented. From a novel perspective linking auditory roles to behavioral functions, this survey establishes the first unified framework for embodied audio intelligence. It brings physical, semantic, and socio-affective capabilities into a common account of perception, reasoning, and interaction through continuous auditory feedback loops. By synthesizing foundations, methods, applications, and evaluation resources, the survey identifies challenges and establishes a systematic research agenda for advancing robust, adaptive, and interactive embodied audio intelligence.
Keywords:
embodied audio intelligence
; embodied AI
; audio perception
; multimodal reasoning
; audio-action grounding
; physical scene understanding
; human-robot interaction
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.