| Autor: |
Garrett E. Katz, Akshay, Gregory P. Davis, Rodolphe J. Gentili, James A. Reggia |
| Jazyk: |
angličtina |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Frontiers in Neurorobotics, Vol 15 (2021) |
| Druh dokumentu: |
article |
| ISSN: |
1662-5218 |
| DOI: |
10.3389/fnbot.2021.744031 |
| Popis: |
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. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
