mlsanityData to 14 Oct 2026

Embodied Intelligence: The Key to Unblocking Generalized Artificial Intelligence

arXiv 2505.06897 ↗First posted 11 May 2025cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The ultimate goal of artificial intelligence (AI) is to achieve Artificial General Intelligence (AGI). Embodied Artificial Intelligence (EAI), which involves intelligent systems with physical presence and real-time interaction with the environment, has emerged as a key research direction in pursuit of AGI. While advancements in deep learning, reinforcement learning, large-scale language models, and multimodal technologies have significantly contributed to the progress of EAI, most existing reviews focus on specific technologies or applications. A systematic overview, particularly one that explores the direct connection between EAI and AGI, remains scarce. This paper examines EAI as a foundational approach to AGI, systematically analyzing its four core modules: perception, intelligent decision-making, action, and feedback. We provide a detailed discussion of how each module contributes to the six core principles of AGI. Additionally, we discuss future trends, challenges, and research directions in EAI, emphasizing its potential as a cornerstone for AGI development. Our findings suggest that EAI's integration of dynamic learning and real-world interaction is essential for bridging the gap between narrow AI and AGI.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 139 references that are in the map. First posted on arXiv 11 May 2025.

Builds on

30 of 139 references.

References · 30

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2019Large Scale Incremental Learningcited by 732
  3. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  4. 2015An Introduction to Convolutional Neural Networkscited by 514
  5. 2019A Theoretical Analysis of Deep Q-Learningcited by 215
  6. 2023OpenAGI: When LLM Meets Domain Expertscited by 197
  7. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 179
  8. 2021Embodied Intelligence via Learning and Evolutioncited by 163
  9. 2022Deep Hierarchical Semantic Segmentationcited by 84
  10. 2022Multi-modal Sensor Fusion for Auto Driving Perception: A Surveycited by 76
  11. 2024DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perceptioncited by 73
  12. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Executioncited by 70
18 more
  1. 2023MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perceptioncited by 67
  2. 2021Visual Semantic Role Labeling for Video Understandingcited by 60
  3. 2020The Unreasonable Effectiveness of Deep Learning in Artificial Intelligencecited by 57
  4. 2020Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusioncited by 53
  5. 2020Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Imagecited by 48
  6. 2020Multi-modal Sensor Fusion-Based Deep Neural Network for End-to-end Autonomous Driving with Scene Understandingcited by 42
  7. 2019Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Drivingcited by 36
  8. 2021From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligencecited by 35
  9. 2024Hybrid Inverse Reinforcement Learningcited by 32
  10. 2023Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learningcited by 31
  11. 2021Recent Advances and Trends in Multimodal Deep Learning: A Reviewcited by 26
  12. 2019Learning a Decision Module by Imitating Driver's Control Behaviorscited by 17
  13. 2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learningcited by 14
  14. 2018Visual Robot Task Planningcited by 11
  15. 2017ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learningcited by 8
  16. 2023Enhancing Social Decision-Making of Autonomous Vehicles: A Mixed-Strategy Game Approach With Interaction Orientation Identificationcited by 5
  17. 2023A Study of Forward-Forward Algorithm for Self-Supervised Learningcited by 4
  18. 2024Artificial Human Intelligence: The role of Humans in the Development of Next Generation AIcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025STORM: Search-Guided Generative World Models for Robotic Manipulationcited by 7

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Models
  2. 2025Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning
  3. 2025Embodied AI: From LLMs to World Models
  4. 2026Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents
  5. 2025EmbodiedBrain: Expanding Performance Boundaries of Task Planning for Embodied Intelligence
  6. 2026From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
  7. 2025NGENT: Next-Generation AI Agents Must Integrate Multi-Domain Abilities to Achieve Artificial General Intelligence
  8. 2026ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI