In this paper, our focus is on enhancing steering angle prediction for autonomous driving tasks. We initiate our exploration by investigating two veins of widely adopted deep neural architectures, namely ResNets and InceptionNets. Within both families, we systematically evaluate various model sizes to understand their impact on performance. Notably, our key contribution lies in the incorporation of an attention mechanism to augment steering angle prediction accuracy and robustness. By introducing attention, our models gain the ability to selectively focus on crucial regions within the input data, leading to improved predictive outcomes. Our findings showcase that our attention-enhanced models not only achieve state-of-the-art results in terms of steering angle Mean Squared Error (MSE) but also exhibit enhanced adversarial robustness, addressing critical concerns in real-world deployment. For example, in our experiments on the Kaggle SAP and our created publicly available datasets, attention can lead to over 6% error reduction in steering angle prediction and boost model robustness by up to 56.09%.

翻译：本文聚焦于提升自动驾驶任务中转向角预测的性能。我们首先系统探究两类广泛采用的深度神经网络架构——ResNets与InceptionNets，并在两类架构内对不同规模模型进行性能影响的系统评估。值得注意的是，核心贡献在于引入注意力机制以增强转向角预测的准确性与鲁棒性。通过引入注意力机制，模型能够选择性关注输入数据中的关键区域，从而显著提升预测效果。实验结果表明，引入注意力增强的模型不仅在转向角均方误差（MSE）指标上达到当前最优水平（state-of-the-art），还展现出更强的对抗鲁棒性，有效解决了实际部署中的关键挑战。例如，在Kaggle SAP数据集及我们自建的公开数据集上，注意力机制使转向角预测误差降低超过6%，模型鲁棒性最高提升56.09%。