This repository provides a comprehensive and continuously updated paper list and resource repository for Embodied AI research. It serves as a valuable reference for researchers and practitioners in the field, offering a structured overview of key advancements, simulators, datasets, and research directions, particularly in the context of Multi-modal Large Models (MLMs) and World Models.

How It Works

The project curates a vast collection of academic papers, simulators, and datasets related to Embodied AI. It categorizes research into key areas such as embodied perception, interaction, agents, and sim-to-real adaptation. The repository aims to provide a structured and navigable resource, highlighting the latest advancements and challenges in bridging the cyber and physical worlds through AI.

Quick Start & Requirements

This is a curated list of resources, not a runnable software package. Accessing the papers requires standard academic research tools. Links to official project pages and datasets are provided within the README.

Highlighted Details

• Comprehensive coverage of Embodied AI, including foundational concepts and recent trends like MLMs.
• Extensive lists of simulators (e.g., Isaac Sim, Webots, AirSim) and datasets (e.g., Matterport3D, ScanNet, ALFRED).
• Detailed categorization of research topics: embodied perception, interaction, agents, and sim-to-real adaptation.
• Regular updates to reflect the rapid progress in the field.

Maintenance & Community

The project is maintained by HCPLab-SYSU and Pengcheng Laboratory. Contributions and suggestions are welcomed via GitHub issues or email. The project is actively updated, with recent logs indicating weekly updates.

Licensing & Compatibility

The repository itself is a collection of links and information; licensing details would pertain to the individual papers and resources linked.

Limitations & Caveats

As a curated list, the repository's primary limitation is its reliance on external resources for actual functionality. The quality and accessibility of linked papers and datasets may vary.