Toward Embodied AGI: A Review of Embodied AI and the Road Ahead
Yequan Wang, Aixin Sun

TL;DR
This paper reviews the current state and future directions of Embodied AGI, proposing a taxonomy, analyzing foundational challenges, and outlining a framework for advanced embodied AI systems.
Contribution
It introduces a systematic taxonomy of Embodied AGI levels and proposes a conceptual framework for developing higher-level embodied AI systems.
Findings
Taxonomy of five Embodied AGI levels (L1-L5)
Analysis of foundational research and challenges at L1-L2
Proposal of a conceptual L3+ robotic brain framework
Abstract
Artificial General Intelligence (AGI) is often envisioned as inherently embodied. With recent advances in robotics and foundational AI models, we stand at the threshold of a new era-one marked by increasingly generalized embodied AI systems. This paper contributes to the discourse by introducing a systematic taxonomy of Embodied AGI spanning five levels (L1-L5). We review existing research and challenges at the foundational stages (L1-L2) and outline the key components required to achieve higher-level capabilities (L3-L5). Building on these insights and existing technologies, we propose a conceptual framework for an L3+ robotic brain, offering both a technical outlook and a foundation for future exploration.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAction Observation and Synchronization · Embodied and Extended Cognition · Social Robot Interaction and HRI
