Biologically-Inspired Representations for Adaptive Control with Spatial Semantic Pointers

2025 Neuro Inspired Computational Elements Conference (NICE), 2025

Graeme Damberger, Kathryn Simone, Chandan Datta, Ram Eshwar Kaundinya, Juan Escareno, Chris Eliasmith

Abstract

We explore and evaluate biologically-inspired representations for an adaptive controller using Spatial Semantic Pointers (SSPs). Specifically, we show our method for place-cell-like SSP representations outperforms past methods. Using this representation, we efficiently learn the dynamics of a given plant over its state space. We implement this adaptive controller in a spiking neural network along with a classical sliding mode controller and prove the stability of the overall system despite non-linear plant dynamics. We then simulate the controller on a 3-link arm and demonstrate that the proposed representational method gives a simpler and more systematic way of designing the neural representation of the state space. Compared to previous methods, we show an increase of 1.23-1.25x in tracking accuracy.

Full text links

 PDF

Conference Proceedings

Booktitle
2025 Neuro Inspired Computational Elements Conference (NICE)
Pages
1-10

Cite

Plain text

BibTeX