SINRL: Socially Integrated Navigation with Reinforcement Learning using Spiking Neural Networks

TL;DR

This paper introduces SINRL, a novel socially integrated navigation method using spiking neural networks and reinforcement learning, achieving improved social navigation and significant energy efficiency in human-robot environments.

Contribution

It presents a hybrid DRL approach combining SNNs and ANNs for social navigation, addressing training stability issues in neuromorphic methods.

Findings

Enhanced social navigation performance

Reduced energy consumption by approximately 1.69 orders of magnitude

Effective capture of crowd dynamics and human-robot interactions

Abstract

Integrating autonomous mobile robots into human environments requires human-like decision-making and energy-efficient, event-based computation. Despite progress, neuromorphic methods are rarely applied to Deep Reinforcement Learning (DRL) navigation approaches due to unstable training. We address this gap with a hybrid socially integrated DRL actor-critic approach that combines Spiking Neural Networks (SNNs) in the actor with Artificial Neural Networks (ANNs) in the critic and a neuromorphic feature extractor to capture temporal crowd dynamics and human-robot interactions. Our approach enhances social navigation performance and reduces estimated energy consumption by approximately 1.69 orders of magnitude.