Biologically-Inspired Representations for Adaptive Control with Spatial Semantic Pointers

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.