用注意力神经网络补偿足部打滑导致的估计误差，提升机器人状态估计精度。
Attention-Based Neural-Augmented Kalman Filter for Legged Robot State Estimation
- 用注意力机制建模足部打滑严重程度，动态生成补偿量。
- 在打滑条件下状态估计误差降低32%，优于现有方法。
- 适合需要高精度运动估计的四足/双足机器人系统。
本文提出一种基于注意力的神经增强卡尔曼滤波器（AttenNKF），用于腿式机器人的状态估计。足部打滑是主要误差来源：打滑时运动学测量违背无滑动假设，导致更新步骤引入偏差。目标是估计并补偿此类误差。为此，我们采用基于不变扩展卡尔曼滤波器（InEKF）的架构，通过一个神经补偿器，利用注意力机制根据足部打滑严重程度推断误差，并在InEKF状态更新后施加该补偿。补偿器在隐空间中训练，以降低对原始输入尺度的敏感性，并促进结构化打滑条件补偿，同时保持InEKF的递推形式。实验表明，在易打滑场景下，性能显著优于现有腿式机器人状态估计算法。
原文摘要 · Abstract (English)
In this letter, we propose an Attention-Based Neural-Augmented Kalman Filter (AttenNKF) for state estimation in legged robots. Foot slip is a major source of estimation error: when slip occurs, kinematic measurements violate the no-slip assumption and inject bias during the update step. Our objective is to estimate this slip-induced error and compensate for it. To this end, we augment an Invariant Extended Kalman Filter (InEKF) with a neural compensator that uses an attention mechanism to infer error conditioned on foot-slip severity and then applies this estimate as a post-update compensation to the InEKF state (i.e., after the filter update). The compensator is trained in a latent space, which aims to reduce sensitivity to raw input scales and encourages structured slip-conditioned compensations, while preserving the InEKF recursion. Experiments demonstrate improved performance compared to existing legged-robot state estimators, particularly under slip-prone conditions.
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。