Advances in robotic control and sensing have propelled the rise of automated scientific laboratories capable of high-throughput experiments. However, automated scientific laboratories are currently limited by human intuition in their ability to efficiently design and interpret experiments in high-dimensional spaces, throttling scientific discovery. We present AutoSciLab, a machine learning framework for driving autonomous scientific experiments, forming a surrogate researcher purposed for scientific discovery in high-dimensional spaces. AutoSciLab autonomously follows the scientific method in four steps: (i) generating high-dimensional experiments (x) using a variational autoencoder (ii) selecting optimal experiments by forming hypotheses using active learning (iii) distilling the experimental results to discover relevant low-dimensional latent variables (z) with a ‘directional autoencoder’ and (iv) learning a human interpretable equation connecting the discovered latent variables with a quantity of interest (y = f (z)), using a neural network equation learner. We validate the generalizability of AutoSciLab by rediscovering a) the principles of projectile motion and b) the phase-transitions within the spin-states of the Ising model (NP-hard problem). Applying our framework to an open-ended nanophotonics problem, AutoSciLab discovers a new way to steer incoherent light emission beyond current state-of-the-art, defining a new structure(material)-property(light-emission) relationship governing the physical process using closed-loop noisy experimental feedback.

For researchers studying cyber-physical system security, working with realistic datasets is essential. To produce the datasets, the existing methodology is to emulate the cyber network. A challenge is that the industrial control systems (ICS) network consists of not just computers and communication equipment, but also field devices that collect data and execute controls. These devices play a significant role in the operation and the security of the system. However, in comparison to the cyber network, the research reproducibility and realism of the cyber-physical system emulation and its data has received far less attention. This paper thus develops an approach to answer, ”How well can emulated devices replicate the behavior of physical intelligent electronics devices (IEDs) in a realistic cyber attack and defense environment?” To study this, we perform a comparison study based on an emulation experiment using theminimegatestbed environment that is entirely virtual and a hardware-in-the-loop experiment using the Resilient Energy Systems Lab (RESLab) cyber-physical testbed featuring real industrial controllers and communications devices. Results show that under different reconnaissance attack scenarios,RESLabgenerates realistic datasets that validate the emulation-based cybersecurity model inminimega. The approach is generalizable toward validating the realism of other types of ICS devices in security studies.

Blue noise sampling has proved useful for many graphics applications, but remains underexplored in high-dimensional spaces due to the difficulty of generating distributions and proving properties about them. We present a blue noise sampling method with good quality and performance across different dimensions. The method, spoke-dart sampling, shoots rays from prior samples and selects samples from these rays. It combines the advantages of two major high-dimensional sampling methods: the locality of advancing front with the dimensionality-reduction of hyperplanes, specifically line sampling. We prove that the output sampling is saturated with high probability, with bounds on distances between pairs of samples and between any domain point and its nearest sample. We demonstrate spoke-dart applications for approximate Delaunay graph construction, global optimization, and robotic motion planning. Both the blue-noise quality of the output distribution and the adaptability of the intermediate processes of our method are useful in these applications.