Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.3389/fnbot.2021.744031 | FRONTIERS IN NEUROROBOTICS |
Keywords | DocType | Volume |
neurosymbolic architectures, robotic manipulation, reinforcement learning, policy optimization, explainable AI | Journal | 15 |
ISSN | Citations | PageRank |
1662-5218 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Garrett E Katz | 1 | 0 | 0.34 |
Akshay | 2 | 0 | 0.34 |
Gregory P Davis | 3 | 0 | 0.34 |
Rodolphe J. Gentili | 4 | 24 | 7.92 |
James A. Reggia | 5 | 1000 | 276.13 |