Verification and Design of Robust and Safe Neural Network-enabled Autonomous Systems
Verification and Design of Robust and Safe Neural Network-enabled Autonomous Systems
复制标题
DOI：
10.1109/allerton58177.2023.10313451
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Qi Zhu;Wenchao Li;Chao Huang;Xin Chen;Weichao Zhou;Yixuan Wang;Jiajun Li;Feisi Fu
中科院分区：
文献类型：
--
作者：
Qi Zhu;Wenchao Li;Chao Huang;Xin Chen;Weichao Zhou;Yixuan Wang;Jiajun Li;Feisi Fu
神经网络正被应用于自主系统中的广泛任务，例如感知、预测、规划、控制以及一般决策制定。虽然相较于传统的基于物理模型的方法，它们可能会提高系统性能，但人们对神经网络在不同输入下的不确定行为提出了紧迫的担忧，特别是对于自动驾驶车辆和机器人等安全关键系统。在本文中，我们将讨论在确保神经网络赋能的自主系统的安全性和鲁棒性方面所面临的挑战，并介绍我们近期在应对这些挑战方面所做的工作。这些工作包括验证神经网络鲁棒性的方法、验证神经网络控制系统安全性的方法、设计具有安全保障的此类系统以及进行有安全保障的运行时自适应。
Neural networks are being applied to a wide range of tasks in autonomous systems, such as perception, prediction, planning, control, and general decision making. While they may improve system performance over traditional physical model-based methods, pressing concerns have been raised on the uncertain behaviors of neural networks under varying inputs, especially for safety-critical systems such as autonomous vehicles and robots. In this paper, we will discuss the challenges in ensuring the safety and robustness of neural network-enabled autonomous systems, and present our recent work in addressing these challenges. These include methods for certifying the robustness of neural networks, verifying the safety of neural network-controlled systems, designing these systems with safety assurance, and conducting safety-assured runtime adaptation.