arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.03347cs.CV
收藏

通过学习端到端视觉注意力来解释自动驾驶

Explaining Autonomous Driving by Learning End-to-End Visual Attention

University of Florence(佛罗伦萨大学)

Luca Cultrera, Lorenzo Seidenari, Federico Becattini, Pietro Pala, Alberto Del Bimbo

摘要:

目前基于深度学习的自动驾驶方法产生了令人印象深刻的结果,也导致了某些受控场景中的生产部署。最流行和最吸引人的方法之一是直接从传感器感知的数据中学习车辆控制。这种端到端的学习范式既可以应用于经典的监督设置,也可以使用强化学习。尽管如此,这种方法的主要缺点,也在其他学习问题是缺乏可解释性。事实上,深度网络将作为一个黑盒子,根据先前看到的驾驶模式输出预测,而不提供任何关于为什么做出这样的决定的反馈。虽然为了获得最佳性能,从学习代理获得可解释的输出并不重要,特别是在这样一个安全关键领域,但了解网络的行为方式至关重要。这与解释此类系统的故障特别相关。在这项工作中,我们提出了训练一个模仿学习为基础的代理配备了注意力模型。注意力模型使我们能够理解图像的哪一部分被认为是最重要的。有趣的是,注意力的使用也导致了在使用CARLA驾驶模拟器的标准基准测试中的优异性能。

英文摘要:

Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios. One of the most popular and fascinating approaches relies on learning vehicle controls directly from data perceived by sensors. This end-to-end learning paradigm can be applied both in classical supervised settings and using reinforcement learning. Nonetheless the main drawback of this approach as also in other learning problems is the lack of explainability. Indeed, a deep network will act as a black-box outputting predictions depending on previously seen driving patterns without giving any feedback on why such decisions were taken. While to obtain optimal performance it is not critical to obtain explainable outputs from a learned agent, especially in such a safety critical field, it is of paramount importance to understand how the network behaves. This is particularly relevant to interpret failures of such systems. In this work we propose to train an imitation learning based agent equipped with an attention model. The attention model allows us to understand what part of the image has been deemed most important. Interestingly, the use of attention also leads to superior performance in a standard benchmark using the CARLA driving simulator.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑