SpikingNav: Robust Embodied Navigation with Spiking Neural Policies

📄 arXiv: 2608.05078v1 📥 PDF

作者: Jiahong Zhang, Sijun Shen, Dehua Wu, Yifan Lin, Xuechen Xia, Xu Chu, Youhui Zhang, GuoqiLi

分类: cs.RO

发布日期: 2026-08-05

💡 一句话要点

提出SpikingNav以解决视觉干扰下的导航鲁棒性问题

🎯 匹配领域: 支柱六：视频提取与匹配 (Video Extraction)

关键词: 脉冲神经网络 导航鲁棒性 室内导航 视觉干扰 动态决策 资源受限平台 智能机器人 神经形态计算

📋 核心要点

  1. 现有的基于人工神经网络的导航模型在视觉干扰下性能下降，缺乏鲁棒性。
  2. 论文提出SpikingNav框架，利用脉冲神经网络的动态特性和脉冲激活来增强导航性能。
  3. SpikingNav在ObjectNav任务中的成功率从31.05%提升至34.12%，在视觉干扰下的平均成功率从8.45%提升至13.71%。

📝 摘要（中文）

本论文提出了一种名为SpikingNav的脉冲神经网络框架，用于增强室内环境中的导航鲁棒性。现有的人工神经网络（ANN）导航模型在视觉干扰下表现不佳，而脉冲神经网络（SNN）通过事件驱动计算和内在时间动态特性，能够在资源受限的平台上实现更紧凑和鲁棒的导航。SpikingNav包含脉冲感知编码器（SSE）和脉冲策略网络（SPN），前者提取任务条件下的视觉特征，后者通过膜积分、阈值和脉冲触发重置来维持策略状态。实验结果表明，SpikingNav在干净观察和视觉干扰下均表现出竞争力的性能和更强的鲁棒性。

🔬 方法详解

问题定义：本论文旨在解决现有基于人工神经网络的导航模型在视觉干扰下的鲁棒性不足问题。现有方法依赖于密集计算，容易受到视觉干扰的影响，导致导航性能下降。

核心思路：论文提出的SpikingNav框架利用脉冲神经网络的事件驱动计算和内在时间动态特性，设计了脉冲感知编码器和脉冲策略网络，以增强导航的鲁棒性和性能。

技术框架：SpikingNav的整体架构包括两个主要模块：脉冲感知编码器（SSE）用于提取任务条件下的视觉特征，脉冲策略网络（SPN）则通过膜积分、阈值和脉冲触发重置来维护策略状态。

关键创新：SpikingNav的核心创新在于结合了脉冲神经网络的动态特性与策略决策过程，显著提高了在视觉干扰下的导航鲁棒性，与传统的人工神经网络方法相比，具有更低的计算需求和更少的参数。

关键设计：在设计中，SSE采用脉冲神经网络作为骨干网络，SPN则通过膜积分和脉冲触发重置机制来维持策略状态，确保了在动态环境中的决策能力。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，SpikingNav在ObjectNav任务中的成功率从31.05%提升至34.12%，在视觉干扰下的平均成功率从8.45%提升至13.71%。这些结果表明，脉冲神经网络在增强导航鲁棒性方面的有效性，且在参数和计算效率上优于匹配的人工神经网络基线。

🎯 应用场景

SpikingNav的研究成果具有广泛的应用潜力，尤其是在机器人导航、智能家居和无人驾驶等领域。其在资源受限平台上的有效性和鲁棒性使其适合于实际部署，能够提升这些系统在复杂环境中的适应能力和可靠性。

📄 摘要（原文）

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.