English

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

Robotics 2025-12-09 v1 Artificial Intelligence Systems and Control Systems and Control

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.

Keywords

Cite

@article{arxiv.2512.07266,
  title  = {SINRL: Socially Integrated Navigation with Reinforcement Learning using Spiking Neural Networks},
  author = {Florian Tretter and Daniel Flögel and Alexandru Vasilache and Max Grobbel and Jürgen Becker and Sören Hohmann},
  journal= {arXiv preprint arXiv:2512.07266},
  year   = {2025}
}

Comments

8 pages, 6 figures

R2 v1 2026-07-01T08:14:23.317Z