In mining, grade control generally focuses on blast hole sampling and the estimation of ore control block models with little or no attention given to how the materials are being excavated from the ground. In the process of loading trucks, the underlying variability of the individual bucket load will determine the variability of truck payload. Hence, accurate material movement demands a good knowledge of the excavation process and the buckets interaction with the environment. However, equipment frequently goes into off nominal states due to unexpected delays, disturbances or faults. The large amount of such disturbances causes information loss that reduces the statistical power and biases estimates, leading to increased uncertainty in the production. A reliable method that inferences the missing knowledge about the interaction between the machine and the environment from the available data sources, is vital to accurately model the material movement. In this study, a twostep method was implemented that performed unsupervised clustering and then predicted the missing information. The first method is DBSCAN based spatial clustering which divides the diggers and buckets positional data into connected loading segments. Clear patterns of segmented bucket dig positions were observed. The second model utilized Gaussian process regression which was trained with the clustered data and the model was then used to infer the mean locations of the test clusters. Bucket dig locations were then simulated at the inferred mean locations for different durations and compared against the known bucket dig locations. This method was tested at an open pit mine in the Pilbara of Western Australia. The results demonstrate the advantage of the proposed method in inferencing the missing information of bucket environment interactions and therefore enables miners to continuously track the material movement.

The U.K. Government is seemingly backtracking on plans that would have allowed text and data mining "for any purpose," plans designed to position the U.K. as a "global AI superpower." The news emerges following months of blowback from creative industries concerned about what impact the rules might have on protected works. Text and data mining, for the uninitiated, is an essential component of just about every AI application, allowing researchers and developers to leverage disparate datasets to train their algorithms. But gaining access to a sufficient amount of data is not a straight-forward endeavor, given that data is often owned by organizations or individuals that might not want third-parties to have access to their data. Or, they may only make said data available under a commercial license, making it prohibitively expensive to harness.

Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification. Recently, PDE-solving deep learning methods, such as neural operators, are starting to make an important impact on learning and predicting the response of a complex physical system directly from observational data. Since the data acquisition in this context is commonly challenging and costly, the call of utilization and transfer of existing knowledge to new and unseen physical systems is even more acute. Herein, we propose a novel meta-learning approach for neural operators, which can be seen as transferring the knowledge of solution operators between governing (unknown) PDEs with varying parameter fields. Our approach is a provably universal solution operator for multiple PDE solving tasks, with a key theoretical observation that underlying parameter fields can be captured in the first layer of neural operator models, in contrast to typical final-layer transfer in existing meta-learning methods. As applications, we demonstrate the efficacy of our proposed approach on PDE-based datasets and a real-world material modeling problem, illustrating that our method can handle complex and nonlinear physical response learning tasks while greatly improving the sampling efficiency in unseen tasks.

This paper presents a novel approach for autonomous cooperating UAVs in search and rescue operations in subterranean domains with complex topology. The proposed system was ranked second in the Virtual Track of the DARPA SubT Finals as part of the team CTU-CRAS-NORLAB. In contrast to the winning solution that was developed specifically for the Virtual Track, the proposed solution also proved to be a robust system for deployment onboard physical UAVs flying in the extremely harsh and confined environment of the real-world competition. The proposed approach enables fully autonomous and decentralized deployment of a UAV team with seamless simulation-to-world transfer, and proves its advantage over less mobile UGV teams in the flyable space of diverse environments. The main contributions of the paper are present in the mapping and navigation pipelines. The mapping approach employs novel map representations -- SphereMap for efficient risk-aware long-distance planning, FacetMap for surface coverage, and the compressed topological-volumetric LTVMap for allowing multi-robot cooperation under low-bandwidth communication. These representations are used in navigation together with novel methods for visibility-constrained informed search in a general 3D environment with no assumptions about the environment structure, while balancing deep exploration with sensor-coverage exploitation. The proposed solution also includes a visual-perception pipeline for on-board detection and localization of objects of interest in four RGB stream at 5 Hz each without a dedicated GPU. Apart from participation in the DARPA SubT, the performance of the UAV system is supported by extensive experimental verification in diverse environments with both qualitative and quantitative evaluation.

Slope failures possess destructive power that can cause significant damage to both life and infrastructure. Monitoring slopes prone to instabilities is therefore critical in mitigating the risk posed by their failure. The purpose of slope monitoring is to detect precursory signs of stability issues, such as changes in the rate of displacement with which a slope is deforming. This information can then be used to predict the timing or probability of an imminent failure in order to provide an early warning. In this study, a more objective, statistical-learning algorithm is proposed to detect and characterise the risk of a slope failure, based on spectral analysis of serially correlated displacement time series data. The algorithm is applied to satellite-based interferometric synthetic radar (InSAR) displacement time series data to retrospectively analyse the risk of the 2019 Brumadinho tailings dam collapse in Brazil. Two potential risk milestones are identified and signs of a definitive but emergent risk (27 February 2018 to 26 August 2018) and imminent risk of collapse of the tailings dam (27 June 2018 to 24 December 2018) are detected by the algorithm. Importantly, this precursory indication of risk of failure is detected as early as at least five months prior to the dam collapse on 25 January 2019. The results of this study demonstrate that the combination of spectral methods and second order statistical properties of InSAR displacement time series data can reveal signs of a transition into an unstable deformation regime, and that this algorithm can provide sufficient early warning that could help mitigate catastrophic slope failures.

According to the authors, such integration is like riding a bicycle made for two, also known as a tandem. This kind of vehicle requires a strong collaboration between the two riders to pedal synchronically and the one in front must be able and willing to drive the tandem towards a common destination, on which both riders agree. The structure of the bicycle should suit a diversity of users: tall and short; married couples and perfect strangers; sportspeople and lazy ones. The way it can be used must adapt to any kind of road, dirt trails and urban well-paved streets alike. Cycling metaphors aside, the convergence and integration of two different disciplines puts requirements to the method and the attitude of both and of all participants.

Many industrial applications rely on real-time optimization to improve key performance indicators. In the case of unknown process characteristics, real-time optimization becomes challenging, particularly for the satisfaction of safety constraints. In this paper, we demonstrate the application of an adaptive and explorative real-time optimization framework to an industrial refrigeration process, where we learn the process characteristics through changes in process control targets and through exploration to satisfy safety constraints. We quantify the uncertainty in unknown compressor characteristics of the refrigeration plant by using Gaussian processes and incorporate this uncertainty into the objective function of the real-time optimization problem as a weighted cost term. We adaptively control the weight of this term to drive exploration. The results of our simulation experiments indicate the proposed approach can help to increase the energy efficiency of the considered refrigeration process, closely approximating the performance of a solution that has complete information about the compressor performance characteristics.

Constructing first-principles models is usually a challenging and time-consuming task due to the complexity of the real-life processes. On the other hand, data-driven modeling, and in particular neural network models often suffer from issues such as overfitting and lack of useful and highquality data. At the same time, embedding trained machine learning models directly into the optimization problems has become an effective and state-of-the-art approach for surrogate optimization, whose performance can be improved by physics-informed training. In this study, it is proposed to upgrade piece-wise linear neural network models with physics informed knowledge for optimization problems with neural network models embedded. In addition to using widely accepted and naturally piece-wise linear rectified linear unit (ReLU) activation functions, this study also suggests piece-wise linear approximations for the hyperbolic tangent activation function to widen the domain. Optimization of three case studies, a blending process, an industrial distillation column and a crude oil column are investigated. For all cases, physics-informed trained neural network based optimal results are closer to global optimality. Finally, associated CPU times for the optimization problems are much shorter than the standard optimization results.

A compact large-range six-degrees-of-freedom (six-DOF) parallel positioning system with high resolution, high resonant frequency, and high repeatability was proposed. It mainly consists of three identical kinematic sections. Each kinematic section consists of two identical displacement amplification and guiding mechanisms, which are finally connected to a limb. Each limb was designed with a universal joint at each end and connected to a moving stage. A computational model of the positioner was built in the ANSYS software package, hence, the input stiffness, output compliance, range, and modal analysis of the system were found. Furthermore, a monolithic prototype made of Acrylonitrile Butadiene Styrene (ABS) was successfully manufactured by the 3D-printing process. It was actuated and sensed by piezoelectric actuators (PEAs) and capacitive displacement sensors, respectively. Finally, the performances of this proposed positioner were experimentally investigated. The positioning resolution was achieved as 10.5nm {\times} 10.5nm {\times} 15nm {\times} 1.8{\mu}rad {\times} 1.3{\mu}rad {\times} 0.5{\mu}rad. The experimental results validate the behavior and capabilities of the proposed positioning system, and also verify the nanometer-scale spatial positioning accuracy within the overall stroke range. Practical applications of the proposed system can be expanded to pick-and-place manipulation, vibration-canceling in microsurgery/micro-assembly, and collaborative manipulators systems.

OpenAI CEO Sam Altman believes AI can help usher in "unbelievable abundance," but he says he wants to ensure that such abundance is shared. Toward that end, Altman has embraced a theory of 19th century political economist Henry George, who in his own lifetime worried about wealth amassing in the hands of the few following the Industrial Revolution. George posited that greater equality could be enjoyed if the economic value of land belonged equally to all members of society. Altman similarly believes that in a world where jobs may create less economic value, a land tax could make up for income tax and guarantee that all individuals' assets rise as land -- a fixed asset -- grows in value. He's putting his money where his mouth is, too, leading a seed round in a six-month-old startup that represents a step in that same direction.