A Survey: Learning Embodied Intelligence from Physical Simulators and World Models

TL;DR

This survey reviews recent progress in embodied AI, emphasizing the integration of physical simulators and world models to improve robot autonomy, adaptability, and generalization in real-world tasks.

Contribution

It systematically analyzes how physical simulators and world models complement each other to advance embodied intelligence, highlighting current progress and open challenges.

Findings

Physical simulators enable safe, high-fidelity training environments.

World models provide internal representations for predictive planning.

Integration of both technologies enhances robot adaptability and generalization.

Abstract

The pursuit of artificial general intelligence (AGI) has placed embodied intelligence at the forefront of robotics research. Embodied intelligence focuses on agents capable of perceiving, reasoning, and acting within the physical world. Achieving robust embodied intelligence requires not only advanced perception and control, but also the ability to ground abstract cognition in real-world interactions. Two foundational technologies, physical simulators and world models, have emerged as critical enablers in this quest. Physical simulators provide controlled, high-fidelity environments for training and evaluating robotic agents, allowing safe and efficient development of complex behaviors. In contrast, world models empower robots with internal representations of their surroundings, enabling predictive planning and adaptive decision-making beyond direct sensory input. This survey systematically reviews recent advances in learning embodied AI through the integration of physical simulators and world models. We analyze their complementary roles in enhancing autonomy, adaptability, and generalization in intelligent robots, and discuss the interplay between external simulation and internal modeling in bridging the gap between simulated training and real-world deployment. By synthesizing current progress and identifying open challenges, this survey aims to provide a comprehensive perspective on the path toward more capable and generalizable embodied AI systems. We also maintain an active repository that contains up-to-date literature and open-source projects at https://github.com/NJU3DV-LoongGroup/Embodied-World-Models-Survey.