… , and fully autonomous vehicles. Along with this, so have grown concerns about the safety
of … This paper provides an overview of the state of the art in machine learning safety. System …

… This section introduces the subject of safety for the context of autonomous driving. Automation
systems are needed to deliver important functions that can be safety critical. Safety con…

… the machine learning methods is a key point to investigate one of the main origins of safety-…
issue in the domain of autonomous driving with an emphasis on four safety-related cases, …

… the safe operation of autonomous vehicles … learning of lane keeping for autonomous cars
[89]. Recently, researchers have now started working on utilizing deep reinforcement learning (…

… Abstract–Ensuring the safety of fully autonomous vehicles requires a multi-disciplinary …
fault tolerance, to resilient machine learning, to cooperating with humans driving conventional …

… practical machine learning safety … safety for machine learning based software in
autonomous vehicles. Our organization maps safety strategies to state-of-theart machine learning …

… deep-reinforcement-learning approaches. We demonstrate the effectiveness of our approach
by testing a highly automated vehicle … vehicles with physical road infrastructure and a real …

… on autonomous driving (AD), improving driving safety while … Recently, deep learning (DL)
approaches have solved … -of-theart strategies for safe AD, with their major achievements and …

… is how to operationalise the required high level of safety and reliability in driving [1]. With
maturity in sensor perception and vehicle control, safe decision-making and risk assessment …

… Moreover, existing works on ITS security often assume a constant attack model, … deep
reinforcement learning (RL) framework that aims at providing robust AV control. We consider a car …