# Body Discovery of Embodied AI

arXiv: https://arxiv.org/abs/2503.19941 · HTML: https://mlsanity.com/paper/2503.19941/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments](https://mlsanity.com/paper/1910.14442/) (2019)
- [GRUtopia: Dream General Robots in a City at Scale](https://mlsanity.com/paper/2407.10943/) (2024)
- [The State of Applied Econometrics - Causality and Policy Evaluation](https://mlsanity.com/paper/1607.00699/) (2016)
- [A First Course in Causal Inference](https://mlsanity.com/paper/2305.18793/) (2023)
- [VRGym: A Virtual Testbed for Physical and Interactive AI](https://mlsanity.com/paper/1904.01698/) (2019)
- [On the Emergence of Symmetrical Reality](https://mlsanity.com/paper/2401.15132/) (2024)
- [A soft robot that adapts to environments through shape change](https://mlsanity.com/paper/2008.06397/) (2020)
- [Symmetrical Reality: Toward a Unified Framework for Physical and Virtual Reality](https://mlsanity.com/paper/1903.02723/) (2019)
- [Rerandomization and Regression Adjustment](https://mlsanity.com/paper/1906.11291/) (2019)
- [Neighbor-Environment Observer: An Intelligent Agent for Immersive Working Companionship](https://mlsanity.com/paper/2403.18331/) (2024)

## Abstract (arXiv)

In the pursuit of realizing artificial general intelligence (AGI), the importance of embodied artificial intelligence (AI) becomes increasingly apparent. Following this trend, research integrating robots with AGI has become prominent. As various kinds of embodiments have been designed, adaptability to diverse embodiments will become important to AGI. We introduce a new challenge, termed "Body Discovery of Embodied AI", focusing on tasks of recognizing embodiments and summarizing neural signal functionality. The challenge encompasses the precise definition of an AI body and the intricate task of identifying embodiments in dynamic environments, where conventional approaches often prove inadequate. To address these challenges, we apply causal inference method and evaluate it by developing a simulator tailored for testing algorithms with virtual environments. Finally, we validate the efficacy of our algorithms through empirical testing, demonstrating their robust performance in various scenarios based on virtual environments.