当前位置: X-MOL 学术Eur. Transp. Res. Rev. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Towards behaviour based testing to understand the black box of autonomous cars
European Transport Research Review ( IF 4.3 ) Pub Date : 2020-07-29 , DOI: 10.1186/s12544-020-00438-2
Fabian Utesch , Alexander Brandies , Paulin Pekezou Fouopi , Caroline Schießl

Autonomous cars could make traffic safer, more convenient, efficient and sustainable. They promise the convenience of a personal taxi, without the need for a human driver. Artificial intelligence would operate the vehicle instead. Especially deep neural networks (DNNs) offer a way towards this vision due to their exceptional performance particularly in perception. DNNs excel in identifying objects in sensor data which is essential for autonomous driving. These networks build their decision logic through training instead of explicit programming. A drawback of this technology is that the source code cannot be reviewed to assess the safety of a system. This leads to a situation where currently used methods for regulatory approval do not work to validate a promising new piece of technology. In this paper four approaches are highlighted that might help understanding black box technical systems for autonomous cars by focusing on its behaviour instead. The method of experimental psychology is proposed to model the inner workings of DNNs by observing its behaviour in specific situations. It is argued that penetration testing can be applied to identify weaknesses of the system. Both can be applied to improve autonomous driving systems. The shadowing method reveals behaviour in a naturalistic setting while ensuring safety. It can be seen as a theoretical driving exam. The supervised driving method can be utilised to decide if the technology is safe enough. It has potential to be developed into a practical driving exam.

中文翻译:

进行基于行为的测试以了解自动驾驶汽车的黑匣子

自动驾驶汽车可以使交通更加安全,便捷,高效和可持续。它们保证了出租车的便利,而无需驾驶员。人工智能将代替车辆。尤其是深度神经网络(DNN),由于其卓越的性能(尤其是在感知方面),提供了一种实现此愿景的方法。DNN擅长识别传感器数据中的对象,这对于自动驾驶至关重要。这些网络通过培训而不是显式编程来建立决策逻辑。该技术的缺点是无法检查源代码以评估系统的安全性。这导致了一种情况,即当前使用的监管批准方法无法验证有希望的新技术。在本文中,重点介绍了四种方法,这些方法可以通过侧重于自动驾驶行为来帮助了解自动驾驶汽车的黑匣子技术系统。提出了一种通过观察DNN在特定情况下的行为来模拟DNN内部工作的实验心理学方法。有人认为,渗透测试可用于识别系统的弱点。两者都可以用于改进自动驾驶系统。遮蔽方法可在确保安全的同时,在自然主义环境中揭示行为。可以将其视为理论驾驶考试。可以使用监督驾驶方法来确定技术是否足够安全。它有可能发展为实际的驾驶考试。提出了一种通过观察DNN在特定情况下的行为来模拟DNN内部工作的实验心理学方法。有人认为,渗透测试可用于识别系统的弱点。两者都可以用于改进自动驾驶系统。遮蔽方法可在确保安全的同时,在自然主义环境中揭示行为。可以将其视为理论驾驶考试。可以使用监督驾驶方法来确定技术是否足够安全。它有可能发展为实际的驾驶考试。提出了一种通过观察DNN在特定情况下的行为来模拟DNN内部工作的实验心理学方法。有人认为,渗透测试可用于识别系统的弱点。两者都可以用于改进自动驾驶系统。遮蔽方法可在确保安全的同时,在自然主义环境中揭示行为。可以将其视为理论驾驶考试。可以使用监督驾驶方法来确定技术是否足够安全。它有可能发展为实际的驾驶考试。遮蔽方法可在确保安全的同时,在自然主义环境中揭示行为。可以将其视为理论驾驶考试。有监督的驾驶方法可以用来确定技术是否足够安全。它有可能发展为实际的驾驶考试。遮蔽方法可在确保安全的同时,在自然主义环境中揭示行为。可以将其视为理论驾驶考试。有监督的驾驶方法可以用来确定技术是否足够安全。它有可能发展为实际的驾驶考试。
更新日期:2020-07-29
down
wechat
bug