Awesome-Embodied-AI

Awesome-Embodied-AI

A curated list of awesome papers on Embodied AI and related research/industry-driven resources, inspired by awesome-computer-vision.

Embodied AI has led to a new breakthrough, and this repository will keep tracking and summarizing the research or industrial progress.

- Contribution is highly welcome and feel free to submit a pull request or contact me.

If you find this repository helpful, please consider Stars ⭐ or Sharing ⬆️.

Contents

• Awesome-Embodied-AI
  • Contents
  • Workshops, tutorials, talks, blogs, etc.
  • Papers
    • Survey
    • Emboddied AI and Robotics
    • Navigation
    • R&D
    • LLM-Driven
    • Trendings
      • 2023

Workshops, tutorials, talks, blogs, etc.

• CVPR-Workshop
• ICCV-Workshop
• CS539-OregonStateUniversity
• ChatGPT for Robotics: Design Principles and Model Abilities

Papers

Please do consider this fantastic paper ： Agent AI: Surveying the Horizons of Multimodal Interaction

Survey

• Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
• Vision-Language Navigation with Embodied Intelligence: A Survey
• The Rise and Potential of Large Language Model Based Agents: A Survey
• A Survey of Embodied AI: From Simulators to Research Tasks
• A Survey on LLM-based Autonomous Agents
• Mindstorms in Natural Language-Based Societies of Mind

Emboddied AI and Robotics

• Tianxing CHEN’s repository
• Wenxuan Song’s repository
• Qiang (Jony) ZHANG’s repository
• GT-RIPL’s repository
• Jacob Rintamaki’s repository
• Jiankai-Sun’s repository
• Yafei Hu’s repository

Navigation

• Thanks to Changan’s repository

R&D

• Thanks to Rui’s repository

• OpenAgent :octocat:

LLM-Driven

• DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects
• An Interactive Agent Foundation Model
• AutoGen, EcoOptiGen:octocat:
• AgentTuning: Enabling Generalized Agent Abilities For LLMs:octocat:
• AgentBench: Evaluating LLMs as Agents:octocat:
• The Rise and Potential of Large Language Model Based Agents: A Survey:octocat:
• An Open-source Framework for Autonomous Language Agents:octocat:
• MetaGPT: Meta Programming for Multi-Agent Collaborative Framework:octocat:
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents :octocat:
• ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models :octocat:
• Embodied Task Planning with Large Language Models :octocat:
• Building Cooperative Embodied Agents Modularly with Large Language Models :octocat:
• State-Maintaining Language Models for Embodied Reasoning :octocat:
• Embodied Executable Policy Learning with Language-based Scene Summarization
• Voyager: An Open-Ended Embodied Agent with Large Language Models :octocat:
• Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning :octocat:
• Vision-Language Tasks :octocat:
• Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf

Trendings

2023

• Language Guided Generation of 3D Embodied AI Environments:octocat:
• CogAgent: Visual Expert for Pretrained Language Models:octocat:
• ProAgent: from Robotic Process Automation to Agentic Process Automation:octocat:
• Waymax: An accelerated simulator for autonomous driving research:octocat:
• HOW FAR ARE LARGE LANGUAGE MODELS FROM AGENTS WITH THEORY-OF-MIND?
• AgentBench: Evaluating LLMs as Agents:octocat:
• MINDAGENT: EMERGENT GAMING INTERACTION
• Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
• Emergent Communication for Embodied Control
• Simple but Effective: CLIP Embeddings for Embodied AI :octocat:
• Embodied AI-Driven Operation of Smart Cities: A Concise Review
• Modeling Dynamic Environments with Scene Graph Memory :octocat:
• An Open-source Framework for Autonomous Language Agents:octocat:
• MetaGPT: Meta Programming for Multi-Agent Collaborative Framework:octocat: