Layton Oliver W, Peng Siyuan, Steinmetz Scott T
Department of Computer Science, Colby College, Waterville, ME 04901, USA.
Microsoft Corporation, Redmond, WA 98052, USA.
Sensors (Basel). 2024 Nov 22;24(23):7453. doi: 10.3390/s24237453.
Accurate self-motion estimation is critical for various navigational tasks in mobile robotics. Optic flow provides a means to estimate self-motion using a camera sensor and is particularly valuable in GPS- and radio-denied environments. The present study investigates the influence of different activation functions-ReLU, leaky ReLU, GELU, and Mish-on the accuracy, robustness, and encoding properties of convolutional neural networks (CNNs) and multi-layer perceptrons (MLPs) trained to estimate self-motion from optic flow. Our results demonstrate that networks with ReLU and leaky ReLU activation functions not only achieved superior accuracy in self-motion estimation from novel optic flow patterns but also exhibited greater robustness under challenging conditions. The advantages offered by ReLU and leaky ReLU may stem from their ability to induce sparser representations than GELU and Mish do. Our work characterizes the encoding of optic flow in neural networks and highlights how the sparseness induced by ReLU may enhance robust and accurate self-motion estimation from optic flow.
精确的自我运动估计对于移动机器人的各种导航任务至关重要。光流提供了一种使用相机传感器估计自我运动的方法，在GPS和无线电信号受阻的环境中尤其有价值。本研究调查了不同激活函数（ReLU、泄漏ReLU、GELU和Mish）对经训练从光流估计自我运动的卷积神经网络（CNN）和多层感知器（MLP）的准确性、鲁棒性和编码特性的影响。我们的结果表明，具有ReLU和泄漏ReLU激活函数的网络不仅在从新颖光流模式进行自我运动估计时取得了更高的准确性，而且在具有挑战性的条件下表现出更大的鲁棒性。ReLU和泄漏ReLU所提供的优势可能源于它们比GELU和Mish能够诱导更稀疏表示的能力。我们的工作刻画了神经网络中光流的编码，并突出了ReLU所诱导的稀疏性如何增强从光流进行鲁棒且精确的自我运动估计。
