SpikeAEC: a neuromodulation-based spiking controller for explore-exploit balancing in mobile robots

TL;DR

This paper introduces SpikeAEC, a brain-inspired robot controller that improves exploration and exploitation balance using spiking neural networks.

Contribution

SpikeAEC introduces a neuromodulated spiking architecture that outperforms existing methods in robot control tasks.

Findings

SpikeAEC converges 24% faster than leading brain-inspired methods.

It reduces trajectory length by 18% and increases cumulative reward by over 5%.

The design maintains consistency with neurophysiological principles.

Abstract

Balancing exploration and exploitation remains a fundamental challenge in reliable mobile robot control, as conventional policies often converge on suboptimal behaviors. Inspired by the brain's division of labor for adaptive control, we propose SpikeAEC, a fully spiking, neuromodulated Actor-Explorer-Critic architecture designed to address this dilemma online within a closed-loop system. SpikeAEC comprises three specialized subnetworks operating in parallel: the Actor, inspired by the basal ganglia, proposes exploitative actions; the Explorer, modeled after the ACC-GPe-STN pathway, generates adaptive exploratory actions gated by a vigilance signal modulated by the accumulated global temporal-difference (TD) error; and the Critic, based on the ventral striatum, computes the TD error. The final action is selected by a separate, TAN-based Arbitrator, which probabilistically chooses between the Actor's and Explorer's action proposals according to recent performance and the TD error. These subnetworks are coupled through a unified three-factor learning framework that uses the TD signal and phasic neuromodulators (acetylcholine and dopamine) from the Arbitrator to drive pathway-specific synaptic plasticity. This online plasticity enhances the quality of action proposals and accelerates policy refinement. In simulation, SpikeAEC outperforms leading brain-inspired methods by converging 24% faster, reducing trajectory length by 18%, and increasing cumulative reward by over 5% against the top-performing baseline, all while maintaining consistency with established neurophysiological principles.

Figures