finding
active
finding:a-soft-robot-recovers-from-unexpected-physical-injury-faster-by-contorting-its-body-into-a-new-shape-hardware-change-rather-than-learning-a-compensating-gait-software-changeA soft robot recovers from unexpected physical injury faster by contorting its body into a new shape (hardware change) rather than learning a compensating gait (software change).
Empirical inversion of the assumption that hardware changes are harder than software changes
Source paper
extracted_from(2021) · Joshua Bongard · Michael Levin
Neighborhood — ranked by edge-count
Claims (1)
claim
- The paper's proposed dissolution of binary software/hardware distinction into a continuum
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Cited as evidence that hardware change can be faster than software change for injury recovery
- Evidence for blurring of embodied robot / non-embodied AI distinction through self-modeling
- Bongard robot self-modeling: robot discovers its shape, then reuses information after damage.finding0.741Key Artificial Life experiment illustrating remapping of self-model (Bongard et al. 2006).
- Reframes fear of replacement as a failure of identity maturity
- Neural plausibility argument for softmax policy selection.
- Grounds the claim that digital minds could be engineered to experience pleasures as intensely rewarding as the worst pains are disrewarding
- Claim about the primacy of bioelectric morphogenesis.
- The paper's proposed new definition of 'robot' as a continuum rather than binary category