This paper introduces a novel proprioceptive state estimator for legged robots that combines model-based filters and deep neural networks. Recent studies have shown that neural networks such as multi-layer perceptron or recurrent neural networks can estimate the robot states, including contact probability and linear velocity. Inspired by this, we develop a state estimation framework that integrates a neural measurement network (NMN) with an invariant extended Kalman filter. We show that our framework improves estimation performance in various terrains. Existing studies that combine model-based filters and learning-based approaches typically use real-world data. However, our approach relies solely on simulation data, as it allows us to easily obtain extensive data. This difference leads to a gap between the learning and the inference domain, commonly referred to as a sim-to-real gap. We address this challenge by adapting existing learning techniques and regularization. To validate our proposed method, we conduct experiments using a quadruped robot on four types of terrain: \textit{flat}, \textit{debris}, \textit{soft}, and \textit{slippery}. We observe that our approach significantly reduces position drift compared to the existing model-based state estimator.

翻译：本文提出一种新型的腿式机器人本体状态估计器，将基于模型的滤波器与深度神经网络相结合。近年研究表明，多层感知机或循环神经网络等神经网络可估计机器人状态，包括接触概率和线速度。受此启发，我们开发了一个将神经测量网络（NMN）与不变扩展卡尔曼滤波相融合的状态估计框架。实验证明，该框架在多种地形条件下均能提升估计性能。现有结合模型滤波器与学习方法的典型研究多采用真实世界数据，而本方法仅依赖仿真数据——这使得我们能便捷地获取海量数据。这种差异导致了学习域与推理域之间的鸿沟，即所谓的仿真到现实迁移差距。我们通过适配现有学习技术与正则化方法解决了这一挑战。为验证所提方法，采用四足机器人在四种地形（平坦、碎石、松软、湿滑）上开展实验。结果表明，相较于现有基于模型的状态估计器，本方法可显著降低位置漂移。