Neural Networks (NNs) can provide major empirical performance improvements for closed-
loop systems, but they also introduce challenges in formally analyzing those systems' safety …

The academic community has extensively studied fault management in dynamical and cyber-
physical systems, leading to the development of various model-based and data …

Control engineering has made significant progress in addressing various challenges for real-
world applications. For the next stage of robotics automation, it is necessary to guarantee …

State density distribution, in contrast to worst-case reachability, can be leveraged for safety-
related problems to better quantify the likelihood of the risk for potentially hazardous …

Artificial neural networks (ANNs) have been used over the last few decades to perform tasks
by learning with comparisons. Fitting input-output models, system identification, control, and …

For several decades, small electronic devices like wireless sensor network nodes (WSNs)
tend to be powered by ambient energy, and the multi-input energy platform attracts much …

Artificial neural networks have recently been utilized in many feedback control systems and
introduced new challenges regarding the safety of such systems. This paper considers the …

We propose a novel Branch-and-Bound method for reachability analysis of neural networks
in both open-loop and closed-loop settings. Our idea is to first compute accurate bounds on …

Learning-based methods could provide solutions to many of the long-standing challenges in
control. However, the neural networks (NNs) commonly used in modern learning …

Three-dimensional image reconstruction plays a pivotal role in microstructure information
extraction and virtual mechanical experiments of asphalt mixture. However, the traditional …