发表机构
Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences; State Key Laboratory of Media Convergence and Communication, Communication University of China; Department of Computer Science and Technology, Tsinghua University; Beijing National Research Center for Information Science and Technology, Tsinghua University（中国科学院自动化研究所; 中国科学院大学人工智能学院; 中国传媒大学媒体融合与传播国家重点实验室; 清华大学计算机科学与技术系; 北京信息科学与技术国家研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出SpikingNav脉冲导航框架，含SSE与SPN，在PointNav、ObjectNav任务中，其参数更少、计算量更低，鲁棒性优于匹配的ANN基线，且可部署于Thruster-V2芯片。
AI 中文摘要
具身导航要求智能体在物理环境中基于自我中心观察做出序列决策。现有基于人工神经网络（ANN）的导航模型已取得优异性能，但通常依赖密集计算，且在视觉干扰下性能可能下降。脉冲神经网络（SNN）具备事件驱动计算与内在时间动态特性，有望在资源受限平台上实现紧凑且鲁棒的导航。然而，基于脉冲的感知与策略动态能否提升视觉丰富的具身导航中的鲁棒性仍是未解决的问题。本文提出SpikingNav，一种用于鲁棒室内具身导航的脉冲框架，包含脉冲感知编码器（SSE）与脉冲策略网络（SPN）。SSE以基于脉冲的骨干网络提取任务条件视觉特征；SPN通过膜整合、阈值处理与脉冲触发重置维持循环策略状态。SpikingNav利用SNN的动态特性与脉冲激活提升导航性能与鲁棒性。我们在PointNav与ObjectNav任务的干净观察及视觉干扰场景下评估SpikingNav，结果显示，与匹配的ANN基线相比，SpikingNav参数更少、每步计算量更低，且在干净观察下性能相当、鲁棒性更强。例如，SpikingNav将ObjectNav的成功率从31.05%提升至34.12%，并将视觉干扰下的平均成功率从8.45%提升至13.71%，证明了基于脉冲的感知与策略动态的优势。我们进一步在Thruster-V2神经形态芯片上验证了该脉冲感知方法的可部署性，该硬件验证表明SpikingNav可在真实神经形态载体上实现，适用于网络物理系统。
英文摘要
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.
