Cargando…

Tunable Neural Encoding of a Symbolic Robotic Manipulation Algorithm

We present a neurocomputational controller for robotic manipulation based on the recently developed “neural virtual machine” (NVM). The NVM is a purely neural recurrent architecture that emulates a Turing-complete, purely symbolic virtual machine. We program the NVM with a symbolic algorithm that so...

Descripción completa

Detalles Bibliográficos
Autores principales: Katz, Garrett E., Akshay, Davis, Gregory P., Gentili, Rodolphe J., Reggia, James A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8712426/
https://www.ncbi.nlm.nih.gov/pubmed/34970133
http://dx.doi.org/10.3389/fnbot.2021.744031
Descripción
Sumario:We present a neurocomputational controller for robotic manipulation based on the recently developed “neural virtual machine” (NVM). The NVM is a purely neural recurrent architecture that emulates a Turing-complete, purely symbolic virtual machine. We program the NVM with a symbolic algorithm that solves blocks-world restacking problems, and execute it in a robotic simulation environment. Our results show that the NVM-based controller can faithfully replicate the execution traces and performance levels of a traditional non-neural program executing the same restacking procedure. Moreover, after programming the NVM, the neurocomputational encodings of symbolic block stacking knowledge can be fine-tuned to further improve performance, by applying reinforcement learning to the underlying neural architecture.