Practical Solutions for Machine Learning Safety in Autonomous Vehicles
This addresses safety challenges for autonomous vehicle systems, but it is incremental as it reviews and organizes existing techniques.
The paper tackles the problem of machine learning safety in autonomous vehicles by reviewing and organizing practical techniques to complement engineering safety, mapping safety strategies to state-of-the-art methods to enhance dependability.
Autonomous vehicles rely on machine learning to solve challenging tasks in perception and motion planning. However, automotive software safety standards have not fully evolved to address the challenges of machine learning safety such as interpretability, verification, and performance limitations. In this paper, we review and organize practical machine learning safety techniques that can complement engineering safety for machine learning based software in autonomous vehicles. Our organization maps safety strategies to state-of-the-art machine learning techniques in order to enhance dependability and safety of machine learning algorithms. We also discuss security limitations and user experience aspects of machine learning components in autonomous vehicles.