In this paper, we investigate the two most popular families of deep neural architectures (i.e., ResNets and InceptionNets) for the autonomous driving task of steering angle prediction. This work provides preliminary evidence that Inception architectures can perform as well or sometimes better than ResNet architectures with less complexity for the autonomous driving task. Our focus is on the compact end of the complexity spectrum. Compact neural network architectures produce less carbon emissions and are thus more environmentally friendly. We look at various sizes of compact ResNet and InceptionNet models to compare results. Our derived models can achieve state-of-the-art results in terms of steering angle MSE. In addition, we also explore the attention mechanism and investigate its influence on steering angle prediction.

翻译：本文针对自动驾驶任务中的转向角预测，研究了两种最主流的深度神经网络架构（即ResNet和InceptionNet）的性能。本研究初步表明，在自动驾驶任务中，Inception架构能以更低的复杂度达到与ResNet架构相当甚至更优的表现。我们重点关注复杂度谱系的紧凑端——紧凑型神经网络架构可减少碳排放，因此更具环境友好性。通过对比不同规模的紧凑型ResNet和InceptionNet模型，我们推导出的模型在转向角均方误差指标上达到了当前最优水平。此外，我们还探讨了注意力机制及其对转向角预测的影响。