Catherine Schuman, Robert Patton, Shruti Kulkarni, Maryam Parsa, Christopher Stahl, N. Quentin Haas, J. Parker Mitchell, Shay Snyder, Amelie Nagle, Alexandra Shanafield and Tom Potok

January, 2022

Neuromorphic Computing and Engineering

https://iopscience.iop.org/article/10.1088/2634-4386/ac45e7

PDF not available yet, or is only available from the conference/journal publisher.

Abstract

Neuromorphic computing offers the opportunity to implement extremely low power artificial intelligence at the edge. Control applications, such as autonomous vehicles and robotics, are also of great interest for neuromorphic systems at the edge. It is not clear, however, what the best neuromorphic training approaches are for control applications at the edge. In this work, we implement and compare the performance of evolutionary optimization and imitation learning approaches on an autonomous race car control task using an edge neuromorphic implementation. We show that the evolutionary approaches tend to achieve better performing smaller network sizes that are well-suited to edge deployment, but they also take significantly longer to train. We also describe a workflow to allow for future algorithmic comparisons for neuromorphic hardware on control applications at the edge.

Citation Information

Text

author      C. D. Schuman et al
title       Evolutionary vs imitation learning for neuromorphic control at the edge
journal     Neuromorphic Computing and Engineering
url         http://dx.doi.org/10.1088/2634-4386/ac45e7
doi         10.1088/2634-4386/ac45e7
year        2022
volume      2
publisher   IOP Publishing

Bibtex

@ARTICLE{sbk:22:evi,
    author = "C. D. {Schuman {\em et al}}",
    title = "Evolutionary vs imitation learning for neuromorphic control at the edge",
    journal = "Neuromorphic Computing and Engineering",
    url = "http://dx.doi.org/10.1088/2634-4386/ac45e7",
    doi = "10.1088/2634-4386/ac45e7",
    year = "2022",
    volume = "2",
    publisher = "IOP Publishing"
}