ENHANCING MACHINE LEARNING SAFETY IN AUTONOMOUS VEHICLES: PRACTICAL STRATEGIES AND SOLUTIONS FOR IMPROVED RELIABILITY
Keywords:
Machine Learning Safety, Autonomous Vehicles, Error Detection, Algorithm Robustness, Interdisciplinary CollaborationAbstract
This article explores the challenges and solutions for enhancing machine learning (ML) safety in autonomous vehicles. It examines the gaps in current automotive safety standards when applied to ML systems and proposes practical solutions to improve reliability and safety. The discussion is organized around two key strategies: implementing robust error detection mechanisms for safe failure modes, and improving algorithm robustness to enhance safety margins across various operational conditions. The article presents concrete implementations of these strategies, including a student model for predicting failures in steering control, an out-of-distribution sample detector, and a cross-domain object detection model for UAVs. Additionally, it outlines future research directions in security against adversarial attacks, procedural safeguards for user experience, and the need for interdisciplinary collaboration to address the complex challenges of ML safety in autonomous vehicle
References
M. Bojarski et al., "End to End Learning for Self-Driving Cars," arXiv:1604.07316 [cs], Apr. 2016. [Online]. Available: https://arxiv.org/abs/1604.07316
Y. Zhou and O. Tuzel, "VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 4490–4499. [Online]. Available: https://ieeexplore.ieee.org/document/8578570
S. A. Seshia, D. Sadigh, and S. S. Sastry, "Towards Verified Artificial Intelligence," arXiv:1606.08514 [cs], Jul. 2016. [Online]. Available: https://arxiv.org/abs/1606.08514
M. Bojarski et al., "VisualBackProp: Efficient visualization of CNNs for autonomous driving," in Arxiv, 2017. [Online]. Available: https://arxiv.org/abs/1611.05418
B. Lakshminarayanan, A. Pritzel, and C. Blundell, "Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles," in Advances in Neural Information Processing Systems 30, 2017, pp. 6402–6413. [Online]. Available: https://proceedings.neurips.cc/paper/2017/hash/9ef2ed4b7fd2c810847ffa5fa85bce38-Abstract.html
S. Mohseni, M. Pitale, J. Yadawa, and Z. Wang, "Self-Supervised Learning for Generalizable Out-of-Distribution Detection," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 5216-5223, Apr. 2020. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/5966
S. Mohseni, A. Jagadeesh, and Z. Wang, "Predicting Model Failure using Saliency Maps in Autonomous Driving Systems," in ICML 2019 Workshop on Uncertainty and Robustness in Deep Learning, 2019. [Online]. Available: https://arxiv.org/abs/1905.07679
S. Mohseni, M. Pitale, J. Yadawa, and Z. Wang, "Self-Supervised Learning for Generalizable Out-of-Distribution Detection," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 5216-5223, Apr. 2020. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/5966
N. Carlini and D. Wagner, "Towards Evaluating the Robustness of Neural Networks," in 2017 IEEE Symposium on Security and Privacy (SP), 2017, pp. 39-57. [Online]. Available: https://ieeexplore.ieee.org/document/7958570
P. Koopman and M. Wagner, "Autonomous Vehicle Safety: An Interdisciplinary Challenge," IEEE Intelligent Transportation Systems Magazine, vol. 9, no. 1, pp. 90-96, Spring 2017. [Online]. Available: https://ieeexplore.ieee.org/document/7823109
