Related papers: Developing Compelling Safety Cases
Diffusion model-based approaches have shown promise in data-driven planning, but there are no safety guarantees, thus making it hard to be applied for safety-critical applications. To address these challenges, we propose a new method,…
In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many…
An open problem for autonomous driving is how to validate the safety of an autonomous vehicle in simulation. Automated testing procedures can find failures of an autonomous system but these failures may be difficult to interpret due to…
When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided because the agent recognized the risk and chose the safe action, or because it…
With information systems becoming larger scale, recommendation systems are a topic of growing interest in machine learning research and industry. Even though progress on improving model design has been rapid in research, we argue that many…
Although simulation represents a major advance in the understanding of problems in complex systems, the field currently does not has standards in place that would guide the reporting of the data underlying each model, the process for model…
Modern cyber-physical systems are operated by complex software that increasingly takes over safety-critical functions. Software enables rapid iterations and continuous delivery of new functionality that meets the ever-changing expectations…
Difficulty of safety-related software standards to help producing software for safe systems is discussed. Some research activity and other actions are proposed to focus on and possibly resolve long-lasting related problems.
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…
Systems engineering approaches use high-level models to capture the architecture and behavior of the system. However, when safety engineers conduct safety and reliability analysis, they have to create formal models, such as fault-trees,…
Reinforcement learning algorithms typically necessitate extensive exploration of the state space to find optimal policies. However, in safety-critical applications, the risks associated with such exploration can lead to catastrophic…
Safety and assurance standards often rely on the principle that requirements errors can be minimised by expressing the requirements more formally. Although numerous case studies have shown that the act of formalising previously informal…
Safety of medical devices and of their interoperation is an unresolved issue causing severe and sometimes deadly accidents for patients with shocking frequency. Formal methods, particularly in support of highly reusable and provably safe…
In robust optimization, we would like to find a solution that is immunized against all scenarios that are modeled in an uncertainty set. Which scenarios to include in such a set is therefore of central importance for the tractability of the…
Safe reinforcement learning is a promising path toward applying reinforcement learning algorithms to real-world problems, where suboptimal behaviors may lead to actual negative consequences. In this work, we focus on the setting where…
Designing Reinforcement Learning (RL) solutions for real-life problems remains a significant challenge. A major area of concern is safety. "Shielding" is a popular technique to enforce safety in RL by turning user-defined safety…
Case study research has become an important research methodology for exploring phenomena in their natural contexts. Case studies have earned a distinct role in the empirical analysis of software engineering phenomena which are difficult to…
Reinforcement learning has been established over the past decade as an effective tool to find optimal control policies for dynamical systems, with recent focus on approaches that guarantee safety during the learning and/or execution phases.…
Software architecture education remains challenging for instructors, students, and software industry professionals. Several initiatives have been proposed to mitigate the inherent challenges, including games, supporting tools, collaborative…
The safety and clinical effectiveness of medical devices are closely associated with their specific use in clinical treatments. Assuring safety and the desired clinical effectiveness is challenging. Different people may react differently to…