Embodied AI in Machine Learning -- is it Really Embodied?

Embodied AI in Machine Learning - is it Really Embodied? Matej Hoffmann and Shubhan Parag Patni Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague Introduction 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 Artifi cial 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 t he 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. GOFAI - powered robots never really worked Artificial Intelligence (AI) in the 1950's and 1960's, later called "Good Old - Fashioned Artificial Intelligence" (GOFAI) by Haugeland(1989), held that the key to intelligence is computation with symbols that represent the world. The keywords were algorithm ic nature, symbolic computation and representation. GOFAI was very successful in formal domains (like chess), where the state of the world is discrete and directly accessible and standard AI techniques (like search) can be applied. While the focus has been on abstract "thinking", when entering the real world, a relationship had to be established between the dynamic, continuous, partially accessible reality out there and the internal world representation. That is, reality had to be sensed and mapped onto the internal world model, in which the "thinking" was performed. Finally, whatever action was selected, it had to be executed in the real world.