用扩散模型做动态系统状态估计，突破传统方法对噪声假设的限制。
DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Models
- 用扩散模型同时条件于预测状态和观测数据，实现非线性状态更新。
- 视觉里程计任务中比顶尖可微滤波器提升25%精度，超越使用未来信息的平滑器。
- 首次成功将扩散模型用于状态估计，适合复杂噪声下的非线性系统建模。
本文提出DnD Filter，一种利用扩散模型进行动态系统状态估计的可微滤波器。与传统可微滤波器常假设过程噪声为高斯分布不同，DnD Filter通过将扩散模型同时条件于预测状态和观测数据，无需强假设即可实现非线性状态更新，充分发挥其拟合复杂分布的能力。我们在模拟任务和真实世界视觉里程计任务上验证了其有效性，结果显示，在视觉里程计任务中，DnD Filter相比现有最优可微滤波器提升了25%的估计精度，甚至优于利用未来测量信息的可微平滑器。据我们所知，DnD Filter是首个成功将扩散模型应用于状态估计的工作，为在噪声测量下进行非线性估计提供了灵活且强大的框架。
原文摘要 · Abstract (English)
This paper proposes the DnD Filter, a differentiable filter that utilizes diffusion models for state estimation of dynamic systems. Unlike conventional differentiable filters, which often impose restrictive assumptions on process noise (e.g., Gaussianity), DnD Filter enables a nonlinear state update without such constraints by conditioning a diffusion model on both the predicted state and observational data, capitalizing on its ability to approximate complex distributions. We validate its effectiveness on both a simulated task and a real-world visual odometry task, where DnD Filter consistently outperforms existing baselines. Specifically, it achieves a 25\% improvement in estimation accuracy on the visual odometry task compared to state-of-the-art differentiable filters, and even surpasses differentiable smoothers that utilize future measurements. To the best of our knowledge, DnD Filter represents the first successful attempt to leverage diffusion models for state estimation, offering a flexible and powerful framework for nonlinear estimation under noisy measurements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。