Continuous then discrete: A recommendation for building robotic brains

Proceedings of the 5th Conference on Robot Learning, 2022

Chris Eliasmith, P. Michael Furlong

Abstract

Modern neural networks have allowed substantial advances in robotics, but these algorithms make implicit assumptions about the discretization of time. In this document we argue that there are benefits to be gained, especially in robotics, by designing learning algorithms that exist in continuous time, as well as state, and only later discretizing the algorithms for implementation on traditional computing models, or mapping them directly onto analog hardware. We survey four arguments to support this approach: That continuum representations provide a unified theory of functions for robotic systems; That many algorithms formulated as temporally continuous demonstrate anytime properties; That we can exploit temporal sparsity to effect energy efficiency in both traditional and analog hardware; and that these algorithms reflect the instantiations of intelligence that have evolved in organisms. Further, we present learning algorithms that are derived from continuous representations. Finally, we discuss robotic precedents for this approach, and conclude with the implications of using continuum representations in robotic systems.

Full text links

 PDF

 External link

Conference Proceedings

Booktitle
Proceedings of the 5th Conference on Robot Learning
Pages
1758–1763
Volume
164
Series
Proceedings of Machine Learning Research
Month
08–11 Nov
Publisher
PMLR
Editors
Aleksandra Faust, David Hsu, Gerhard Neumann

Cite

Plain text

BibTeX