Marjaninejad A, Urbina-Meléndez D, Cohn BA, Valero-Cuevas FJ. Autonomous Functional Movements in a Tendon-Driven Limb via Limited Experience.
NAT MACH INTELL 2019;
1:144-154. [PMID:
31161156 PMCID:
PMC6544439 DOI:
10.1038/s42256-019-0029-0]
[Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2018] [Accepted: 02/05/2019] [Indexed: 11/09/2022]
Abstract
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, open-loop approach allows few-shot autonomous learning to produce effective movements in a 3-tendon 2-joint limb. We use a short period of motor babbling (to create an initial inverse map) followed by building functional habits by reinforcing high-reward behavior and refinements of the inverse map in a movement's neighborhood. This biologically-plausible algorithm, which we call G2P (General-to-Particular), can potentially enable quick, robust and versatile adaptation in robots as well as shed light on the foundations of the enviable functional versatility of organisms.
Collapse