Ontology highlight
ABSTRACT:
SUBMITTER: Marjaninejad A
PROVIDER: S-EPMC6544439 | biostudies-literature | 2019 Mar
REPOSITORIES: biostudies-literature
Marjaninejad Ali A Urbina-Meléndez Darío D Cohn Brian A BA Valero-Cuevas Francisco J FJ
Nature machine intelligence 20190311 3
Robots will become ubiquitously useful only when they can use few attempts to teach themselves to perform different tasks, even with complex bodies and in dynamical environments. Vertebrates, in fact, use sparse trial-and-error to learn multiple tasks despite their intricate tendon-driven anatomies-which are particularly hard to control because they are simultaneously nonlinear, under-determined, and over-determined. We demonstrate-for the first time in simulation and hardware-how a model-free, ...[more]