Embodied AI in Machine Learning -- is it Really Embodied?
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909612093997056 |
|---|---|
| author | Hoffmann, Matej Patni, Shubhan Parag |
| author_facet | Hoffmann, Matej Patni, Shubhan Parag |
| contents | Embodied Artificial Intelligence (Embodied AI) is gaining momentum in the machine learning communities with the goal of leveraging current progress in AI (deep learning, transformers, large language and visual-language models) to empower robots. In this chapter we put this work in the context of "Good Old-Fashioned Artificial Intelligence" (GOFAI) (Haugeland, 1989) and the behavior-based or embodied alternatives (R. A. Brooks 1991; Pfeifer and Scheier 2001). We claim that the AI-powered robots are only weakly embodied and inherit some of the problems of GOFAI. Moreover, we review and critically discuss the possibility of cross-embodiment learning (Padalkar et al. 2024). We identify fundamental roadblocks and propose directions on how to make progress. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10705 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embodied AI in Machine Learning -- is it Really Embodied? Hoffmann, Matej Patni, Shubhan Parag Artificial Intelligence Neural and Evolutionary Computing Robotics 68T40 I.2.9 Embodied Artificial Intelligence (Embodied AI) is gaining momentum in the machine learning communities with the goal of leveraging current progress in AI (deep learning, transformers, large language and visual-language models) to empower robots. In this chapter we put this work in the context of "Good Old-Fashioned Artificial Intelligence" (GOFAI) (Haugeland, 1989) and the behavior-based or embodied alternatives (R. A. Brooks 1991; Pfeifer and Scheier 2001). We claim that the AI-powered robots are only weakly embodied and inherit some of the problems of GOFAI. Moreover, we review and critically discuss the possibility of cross-embodiment learning (Padalkar et al. 2024). We identify fundamental roadblocks and propose directions on how to make progress. |
| title | Embodied AI in Machine Learning -- is it Really Embodied? |
| topic | Artificial Intelligence Neural and Evolutionary Computing Robotics 68T40 I.2.9 |
| url | https://arxiv.org/abs/2505.10705 |