concept
active
concept:embodied-ai

Embodied AI

Emerging approach to run deep learning algorithms on autonomous robots and evolve robot bodies directly.

Neighborhood — ranked by edge-count

Claims (1)

claim

Methods (1)

method
  • Robots capable of building internal models of their own body and unexpected changes, blurring the embodied/non-embodied AI distinction

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Embodied cognitionframework0.850
    Framework treating cognition as inseparable from bodily organization and environmental interaction; aligned with biogenic approach.
  • Embodied Mindconcept0.844
    Philosophical position that minds are dependent on plastic material substrates that change during lifetime and evolution.
  • Embodied Meaningconcept0.814
    Intentions and meanings are grounded in recurrent neural network dynamics; semantic space is embodied in brain topology.
  • Embodied Inferenceconcept0.795
    Process by which organism's material states and internal dynamics realize variational inference through action
  • The contrast class for LLMs: humans acquire language through embodied interaction in communities, unlike disembodied LLMs
  • Observable actions used to infer cognition, including verbal self-report.
  • Future AI that may be rational, autonomous, and possibly conscious but lack affective consciousness.
  • compositional AIconcept0.775
    Artificial intelligence built on compositional principles, including NLP and beyond