Evolutionary vs imitation learning for neuromorphic control at the edge*

Journal Article · 24 January 2022 · Neuromorphic Computing and Engineering

DOI: https://doi.org/10.1088/2634-4386/ac45e7 · OSTI ID:1841439

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

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.

• Sponsoring Organization: USDOE
• Grant/Contract Number: AC05-00OR22725
• OSTI ID: 1841439
• Journal Information: Neuromorphic Computing and Engineering, Journal Name: Neuromorphic Computing and Engineering Journal Issue: 1 Vol. 2; ISSN 2634-4386
• Publisher: IOP PublishingCopyright Statement
• Country of Publication: United Kingdom
• Language: English