SpikingNav: Robust Embodied Navigation with Spiking Neural Policies

2026-08-05

AI Summary

This work addresses the high computational cost and poor robustness of existing artificial neural network (ANN)-based embodied navigation models under visual perturbations. To overcome these limitations, we propose SpikingNav, a novel framework that, for the first time, integrates spiking neural networks (SNNs) into both perception and policy modules. Leveraging the event-driven nature and intrinsic temporal dynamics of SNNs, SpikingNav achieves efficient and robust indoor navigation. Evaluated on PointNav and ObjectNav tasks, our method surpasses ANN baselines with fewer parameters and lower per-step computation: it improves ObjectNav success rates from 31.05% to 34.12%, and under visual disturbances, average success increases from 8.45% to 13.71%. Hardware deployment on the Thruster-V2 neuromorphic chip further validates the practicality of our approach.

Abstract

Embodied navigation requires an agent to make sequential decisions from egocentric observations in a physical environment. Existing Artificial Neural Network (ANN)-based navigation models have achieved strong performance, yet they often rely on dense computation and may degrade under visual corruptions. Spiking neural networks (SNNs) provide event-driven computation and intrinsic temporal dynamics, which are promising for compact and robust navigation on resource-constrained platforms. However, whether spike-based sensing and policy dynamics can improve robustness in visually rich embodied navigation remains an open problem. This paper proposes SpikingNav, a spiking framework for robust indoor embodied navigation. It contains a Spiking Sensing Encoder (SSE) and a Spiking Policy Network (SPN). The SSE extracts task-conditioned visual features with a spike-based backbone. The SPN maintains a recurrent policy state through membrane integration, thresholding, and spike-triggered reset. In this way, SpikingNav exploits the dynamic properties and spike activations of SNNs to improve navigation performance and robustness. We evaluate SpikingNav on PointNav and ObjectNav under clean observations and visual corruptions. SpikingNav achieves competitive clean performance and stronger robustness with fewer parameters and lower per-step computation than a matched ANN baseline. For instance, SpikingNav improves ObjectNav success from 31.05% to 34.12%, and raises the average success under visual corruptions from 8.45% to 13.71%, demonstrating the benefits of spike-based sensing and policy dynamics. We further validate the deployability of our spike-based sensing method on the Thruster-V2 neuromorphic chip. This physical hardware validation shows that SpikingNav can be instantiated on a real neuromorphic substrate for cyber-physical systems.

Problem

• embodied navigation
• spiking neural networks
• visual corruptions
• robustness
• resource-constrained platforms

Innovation

• Spiking Neural Networks
• Embodied Navigation
• Robustness
• Neuromorphic Computing
• Event-driven Perception