Self-evolving Embodied AI

TL;DR

This paper proposes a novel paradigm called self-evolving embodied AI, enabling agents to autonomously adapt and evolve in dynamic environments through self-updating memory, task switching, and model evolution, advancing towards general AI.

Contribution

It introduces the concept, framework, and mechanisms of self-evolving embodied AI, addressing limitations of static, human-crafted systems in dynamic real-world settings.

Findings

Systematic review of state-of-the-art components

Discussion of practical applications

Identification of future research directions

Abstract

Embodied Artificial Intelligence (AI) is an intelligent system formed by agents and their environment through active perception, embodied cognition, and action interaction. Existing embodied AI remains confined to human-crafted setting, in which agents are trained on given memory and construct models for given tasks, enabling fixed embodiments to interact with relatively static environments. Such methods fail in in-the-wild setting characterized by variable embodiments and dynamic open environments. This paper introduces self-evolving embodied AI, a new paradigm in which agents operate based on their changing state and environment with memory self-updating, task self-switching, environment self-prediction, embodiment self-adaptation, and model self-evolution, aiming to achieve continually adaptive intelligence with autonomous evolution. Specifically, we present the definition, framework, components, and mechanisms of self-evolving embodied AI, systematically review state-of-the-art works for realized components, discuss practical applications, and point out future research directions. We believe that self-evolving embodied AI enables agents to autonomously learn and interact with environments in a human-like manner and provide a new perspective toward general artificial intelligence.