Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning

TL;DR

This survey reviews how large models are transforming embodied AI by improving decision-making and learning, highlighting recent advances, methodologies, and future challenges in creating more intelligent embodied agents.

Contribution

It provides the first comprehensive overview of large model integration in embodied AI, covering hierarchical and end-to-end decision-making, embodied learning, and world models.

Findings

Large models significantly enhance perception, planning, and learning in embodied AI.

Integration of world models improves decision-making and learning efficiency.

Challenges remain in achieving human-level intelligence in open environments.

Abstract

Embodied AI aims to develop intelligent systems with physical forms capable of perceiving, decision-making, acting, and learning in real-world environments, providing a promising way to Artificial General Intelligence (AGI). Despite decades of explorations, it remains challenging for embodied agents to achieve human-level intelligence for general-purpose tasks in open dynamic environments. Recent breakthroughs in large models have revolutionized embodied AI by enhancing perception, interaction, planning and learning. In this article, we provide a comprehensive survey on large model empowered embodied AI, focusing on autonomous decision-making and embodied learning. We investigate both hierarchical and end-to-end decision-making paradigms, detailing how large models enhance high-level planning, low-level execution, and feedback for hierarchical decision-making, and how large models enhance Vision-Language-Action (VLA) models for end-to-end decision making. For embodied learning, we introduce mainstream learning methodologies, elaborating on how large models enhance imitation learning and reinforcement learning in-depth. For the first time, we integrate world models into the survey of embodied AI, presenting their design methods and critical roles in enhancing decision-making and learning. Though solid advances have been achieved, challenges still exist, which are discussed at the end of this survey, potentially as the further research directions.