RS Energy Group, Inc. (RSEG) is an advanced analytics and technology firm that delivers industry-leading, comprehensive insights to those operating, investing in or servicing the energy space. RSEG's work environment is positive, supportive, innovative, and dynamic, with interdisciplinary teams focused on leveraging the latest in technology, machine learning, data science and AI. Headquartered in Calgary, RSEG also has offices in Houston, New York and Conshohocken.

Fluid Dynamics is around us every day. Any flow moving fast enough or with a small kinematic viscosity generates turbulence. Turbulent flows, like atmospheric and oceanic circulations or flows around vehicles, develop extremely complex dynamics coupling structures over a large range of scales, and with chaotic behavior, which makes them unpredictable. For engineers this creates significant design challenges as they have to find aerodynamic data that best replicates the conditions in the outside world. Today, scientists rely on experiments such as wind tunnels or numerical simulations performed on the largest supercomputers in the world, an approach known as computational fluid dynamics (CFD).

Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive Navigation tasks are usually long-horizon and composed of heterogeneous phases of pure navigation, pure manipulation, and their combination. Using the wrong part of the embodiment is inefficient and hinders progress. We propose HRL4IN, a novel Hierarchical RL architecture for Interactive Navigation tasks. HRL4IN exploits the exploration benefits of HRL over flat RL for long-horizon tasks thanks to temporally extended commitments towards subgoals. Different from other HRL solutions, HRL4IN handles the heterogeneous nature of the Interactive Navigation task by creating subgoals in different spaces in different phases of the task. Moreover, HRL4IN selects different parts of the embodiment to use for each phase, improving energy efficiency. We evaluate HRL4IN against flat PPO and HAC, a state-of-the-art HRL algorithm, on Interactive Navigation in two environments - a 2D grid-world environment and a 3D environment with physics simulation. We show that HRL4IN significantly outperforms its baselines in terms of task performance and energy efficiency. More information is available at https://sites.google.com/view/hrl4in.

Underground penetration and exploration technologies have a long history and can be exploited in many sectors, such as agriculture, for example, to define soil water content1; geology, for example, for terrain seismic profiling2 and underground characterization3; and the oil and gas industry4 or construction, for example, for mapping and maintenance of underground utility service infrastructures5 and tunneling.6 Autonomous solutions, which can monitor the surrounding environment, make decisions, and adjust their behavior for improving penetration and exploration, could help make the process faster, more reliable, cheaper, and safer for humans and underground infrastructures.7 However, robotic solutions for such applications are still very limited,8–13 due to the strong constraints imposed on the movement of autonomous systems below ground by the physics of such a cluttered environment (i.e., high pressure and friction, stratifications with different soil impedance, and rocks). Ideally, a robotic system moving in soil should be able to adapt its actions to unpredictable constraints, avoiding or navigating around obstacles or sensitive objects, for example, to prevent damaging underground pipes or objects of the cultural heritage. However, they have a limited possibility of perception compared to aboveground robots, which for instance can take advantage of vision. Thus, within the soil, a possible strategy for movement and exploration is for the morphology of the body to adapt itself to the soil structure. Morphological adaptation in artificial solutions has been particularly exploited in the field of soft-bodied robotic systems,14,15 where soft materials are adopted for the deformation of soft artificial bodies, for moving through small gates16,17 or navigating cluttered environments, for example, by exploiting the passive buckling ability of soft inflatable structures in a robot, without the use of a sensory perception or bending control.18 Material properties or soft actuators are used for enhancing robot abilities.19 In fact, the adaptation provided by soft materials and actuators can effectively improve robot behaviors while decreasing the control complexity.20,21

As connected devices--anything from the computer built into a car or a fitness wearable to a smart gas meter or wind turbine--have become cheaper to manufacture, their use has grown rapidly. Some form of connected device or system is now in almost every industry and sector. This proliferation means that traditional maintenance models requiring engineers to have easy physical access to real-world devices and systems are often no longer viable. As such, the need for an alternative management model is growing, which is where "digital twin" AI technology has enormous potential for any enterprise doing business through connected devices. This report looks at the benefits companies can gain from digital twin technology, the options available on the market to take advantage of it, where digital twins are already in use, and what some industries stand to lose by ignoring this AI trend.

In a novel approach that could help reduce carbon emissions, a team of scientists led by Stony Brook's Anatoly Frenkel have described a way to use artificial intelligence (AI) to facilitate the conversion of carbon dioxide (CO2) into methane. By using this method to track the size, structure, and chemistry of catalytic particles under real reaction conditions, the scientists can identify which properties correspond to the best catalytic performance, and then use that information to guide the design of more efficient catalysts. "Improving our ability to convert CO2 to methane would'kill two birds with one stone' by making a sustainable non-fossil-fuel energy source that can be easily stored and transported while reducing carbon emissions," said Anatoly Frenkel, a chemist with a joint appointment at the U.S. Department of Energy's Brookhaven National Laboratory (BNL) and Stony Brook University. Frenkel is a professor of Materials Science in the College of Engineering and Applied Sciences. Frenkel's group has been developing a machine-learning approach to extract catalytic properties from x-ray signatures of catalysts collected as chemicals are transformed in reactions.

Database activity monitoring (DAM) systems are commonly used by organizations to protect the organizational data, knowledge and intellectual properties. In order to protect organizations database DAM systems have two main roles, monitoring (documenting activity) and alerting to anomalous activity. Due to high-velocity streams and operating costs, such systems are restricted to examining only a sample of the activity. Current solutions use policies, manually crafted by experts, to decide which transactions to monitor and log. This limits the diversity of the data collected. Bandit algorithms, which use reward functions as the basis for optimization while adding diversity to the recommended set, have gained increased attention in recommendation systems for improving diversity. In this work, we redefine the data sampling problem as a special case of the multi-armed bandit (MAB) problem and present a novel algorithm, which combines expert knowledge with random exploration. We analyze the effect of diversity on coverage and downstream event detection tasks using a simulated dataset. In doing so, we find that adding diversity to the sampling using the bandit-based approach works well for this task and maximizing population coverage without decreasing the quality in terms of issuing alerts about events.

This work presents an explicit-implicit procedure that combines an offline trained neural network with an online primal active set solver to compute a model predictive control (MPC) law with guarantees on recursive feasibility and asymptotic stability. The neural network improves the suboptimality of the controller performance and accelerates online inference speed for large systems, while the primal active set method provides corrective steps to ensure feasibility and stability. We highlight the connections between MPC and neural networks and introduce a primal-dual loss function to train a neural network to initialize the online controller. We then demonstrate online computation of the primal feasibility and suboptimality criteria to provide the desired guarantees. Next, we use these neural network and criteria measures to accelerate an online primal active set method through warm starts and early termination. Finally, we present a data set generation algorithm that is critical for successfully applying our approach to high dimensional systems. The primary motivation is developing an algorithm that scales to systems that are challenging for current approaches, involving state and input dimensions as well as planning horizons in the order of tens to hundreds.

Deep learning methods have received increasing interest by the remote sensing community for multi-temporal land cover classification in recent years. Convolutional Neural networks that elementwise compare a time series with learned kernels, and recurrent neural networks that sequentially process temporal data have dominated the state-of-the-art in the classification of vegetation from satellite time series. Self-attention allows a neural network to selectively extract features from specific times in the input sequence thus suppressing non-classification relevant information. Today, self-attention based neural networks dominate the state-of-the-art in natural language processing but are hardly explored and tested in the remote sensing context. In this work, we embed self-attention in the canon of deep learning mechanisms for satellite time series classification for vegetation modeling and crop type identification. We compare it quantitatively to convolution, and recurrence and test four models that each exclusively relies on one of these mechanisms. The models are trained to identify the type of vegetation on crop parcels using raw and preprocessed Sentinel 2 time series over one entire year. To obtain an objective measure we find the best possible performance for each of the models by a large-scale hyperparameter search with more than 2400 validation runs. Beyond the quantitative comparison, we qualitatively analyze the models by an easy-to-implement, but yet effective feature importance analysis based on gradient back-propagation that exploits the differentiable nature of deep learning models. Finally, we look into the self-attention transformer model and visualize attention scores as bipartite graphs in the context of the input time series and a low-dimensional representation of internal hidden states using t-distributed stochastic neighborhood embedding (t-SNE).

This release contains statements that constitute forward-looking statements. These statements appear in a number of places in this release and include all statements that are not statements of historical fact regarding the intent, belief or current expectations of the Company, its directors or its officers with respect to, among other things: (i) the Company's financing plans; (ii) trends affecting the Company's financial condition or results of operations; (iii) the Company's growth strategy and operating strategy; and (iv) the declaration and payment of dividends. The words "may," "would," "will," "expect," "estimate," "anticipate," "believe," "intend," and similar expressions and variations thereof are intended to identify forward-looking statements. Investors are cautioned that any such forward-looking statements are not guarantees of future performance and involve risks and uncertainties, many of which are beyond the Company's ability to control and that actual results may differ materially from those projected in the forward-looking statements as a result of various factors.