On end-to-end driving, a large amount of expert driving demonstrations is used to train an agent that mimics the expert by predicting its control actions. This process is self-supervised on vehicle signals (e.g., steering angle, acceleration) and does not require extra costly supervision (human labeling). Yet, the improvement of existing self-supervised end-to-end driving models has mostly given room to modular end-to-end models where labeling data intensive format such as semantic segmentation are required during training time. However, we argue that the latest self-supervised end-to-end models were developed in sub-optimal conditions with low-resolution images and no attention mechanisms. Further, those models are confined with limited field of view and far from the human visual cognition which can quickly attend far-apart scene features, a trait that provides an useful inductive bias. In this context, we present a new end-to-end model, trained by self-supervised imitation learning, leveraging a large field of view and a self-attention mechanism. These settings are more contributing to the agent's understanding of the driving scene, which brings a better imitation of human drivers. With only self-supervised training data, our model yields almost expert performance in CARLA's Nocrash metrics and could be rival to the SOTA models requiring large amounts of human labeled data. To facilitate further research, our code will be released.

翻译：在端到端驾驶任务中，通常使用大量专家驾驶演示数据训练一个通过预测控制动作来模仿专家的智能体。该过程依赖车辆信号（如转向角、加速度）实现自监督，无需额外昂贵的人工标注。然而，现有自监督端到端驾驶模型的改进空间大多被模块化端到端模型所占据——这类模型在训练时需要语义分割等高标注数据密集型格式。但我们认为，最新自监督端到端模型是在低分辨率图像且无注意力机制的非最优条件下开发的。此外，这些模型受限于有限的视野范围，远不及人类视觉认知系统——后者能快速关注场景中相距较远的特征，这一特性提供了有益的归纳偏置。在此背景下，我们提出一种通过自监督模仿学习训练的全新端到端模型，其利用大视野范围与自注意力机制。这些设置更有助于智能体对驾驶场景的理解，从而实现对人类驾驶员更优的模仿。仅使用自监督训练数据，我们的模型在CARLA的Nocrash指标上即可达到近乎专家级的性能，并能与依赖大量人工标注数据的最先进模型相抗衡。为促进后续研究，我们将开源代码。