Rapid Learning of Spatial Representations for Goal-Directed Navigation Based on a Novel Model of Hippocampal Place Fields

TL;DR

This paper introduces a self-organized hippocampal model that enables rapid one-shot learning for goal-directed navigation in complex environments, inspired by biological neural mechanisms.

Contribution

A novel self-organized model combining place cells and replay for fast learning in complex navigation tasks, advancing prior engineered neural network approaches.

Findings

Achieves rapid one-shot learning in obstacle-rich environments

Demonstrates biological plausibility with hippocampal-inspired mechanisms

Outperforms traditional models in complex navigation scenarios

Abstract

The discovery of place cells and other spatially modulated neurons in the hippocampal complex of rodents has been crucial to elucidating the neural basis of spatial cognition. More recently, the replay of neural sequences encoding previously experienced trajectories has been observed during consummatory behavior potentially with implications for quick memory consolidation and behavioral planning. Several promising models for robotic navigation and reinforcement learning have been proposed based on these and previous findings. Most of these models, however, use carefully engineered neural networks and are tested in simple environments. In this paper, we develop a self-organized model incorporating place cells and replay, and demonstrate its utility for rapid one-shot learning in non-trivial environments with obstacles.