Commander Andrew Feustel (FOY-stull) used a robot arm to capture the White Stork. It holds more than 5 tons of supplies, including new batteries for the station's solar power grid. Spacewalking astronauts will help install the batteries in October, later than planned due to launch delays caused by bad weather and rocket issues.

Understanding how artificial intelligence (AI) and machine learning (ML) can benefit your business may seem like a daunting task. But there is a myriad of applications for these technologies that you can implement to make your life easier. Through AI and ML, your business will benefit as it becomes more efficient at its operations and eliminates those mundane tasks that seem to be slowing you down. Additionally, AI-powered tools and automated systems can help your company improve the use of its resources, with visible effects on your bottom line. Fifteen members of Forbes Technology Council discuss some of the latest applications they've found for AI/ML at their companies.

IBM and Galp, a Portuguese energy group with a global footprint, have developed an AI-based advisor to enhance seismic interpretation in the oil and gas exploration area. This tool can facilitate creation of enhanced geological models, risk assessment of new prospects, and optimization of the placement of new oil wells. As global energy consumption increases and much of the globe still relies on fossil fuels to supply its energy needs, the oil and gas industry is facing the challenge of finding new resources. More advanced analysis and computing are required to find and evaluate hidden sources of fuel. IBM and Galp are helping to solve that.

A lit cigarette burns at around 600-degrees Celsius (1,100 F). The auto-ignition point for gasoline is less than half that. Somehow, despite these facts, people smoke while pumping gas. In fact, it's such a prevalent problem that Microsoft developed an AI-powered alarm system to help gas station employees crack down on offenders. It's difficult to imagine the amount of idiotic hubris it takes to disregard basic thermodynamics, but some people simply won't be bothered by certain doom.

Climate change has a direct impact on the agrarian societies, the frequency of natural disasters and the overall ecology of the planet. Using artificial intelligence, countries like Norway and India have made significant development in increasing their crop yields (30% increase in groundnut yields) and production of flexible and autonomous renewable energy grids and circuits. AI has also helped scientists map cyclones, atmospheric rivers, and weather fronts with 89 to 99 percent accuracy. These things were often hard to identify and predict beforehand, until now. Today, issues like water conservation, agriculture, biodiversity, and climate change are increasingly getting addressed by AI-powered terrestrial machines and geospatial satellites.

For scale, consider the Statue of Liberty, standing 305 feet tall. At 466 feet, the average wind turbine in the U.S. dwarfs Lady Liberty by more than half. And when GE's next-generation monster wind turbine, the Haliade-X, hits the market in 2021, it will nearly double that size to 877 feet, just shy of the Eiffel Tower. A single Haliade-X rotor blade will stretch 315 feet, longer than a football field. As a general rule of thumb, when it comes to energy and energy exploration, bigger is better: the larger the machinery, the deeper the dig, the greater the production yield.

This paper proposes an exploration method for deep reinforcement learning based on parameter space noise. Recent studies have experimentally shown that parameter space noise results in better exploration than the commonly used action space noise. Previous methods devised a way to update the diagonal covariance matrix of a noise distribution and did not consider the direction of the noise vector and its correlation. In addition, fast updates of the noise distribution are required to facilitate policy learning. We propose a method that deforms the noise distribution according to the accumulated returns and the noises that have led to the returns. Moreover, this method switches isotropic exploration and directional exploration in parameter space with regard to obtained rewards. We validate our exploration strategy in the OpenAI Gym continuous environments and modified environments with sparse rewards. The proposed method achieves results that are competitive with a previous method at baseline tasks. Moreover, our approach exhibits better performance in sparse reward environments by exploration with the switching strategy.

We study the adaptive sensing problem for the multiple source seeking problem, where a mobile robot must identify the strongest emitters in an environment with background emissions. Background signals may be highly heterogeneous, and can mislead algorithms which are based on receding horizon control, greedy heuristics, or smooth background priors. We propose AdaSearch, a general algorithm for adaptive sensing. AdaSearch combines global trajectory planning with principled confidence intervals in order to concentrate measurements in promising regions while still guaranteeing sufficient coverage of the entire area. Theoretical analysis shows that AdaSearch significantly outperforms a uniform sampling strategy when the distribution of background signals is highly variable. Simulation studies demonstrate that when applied to the problem of radioactive source-seeking, AdaSearch outperforms both uniform sampling and a receding time horizon information-maximization approach based on the current literature. We corroborate these findings with a hardware demonstration, using a small quadrotor helicopter in a motion-capture arena.

We present an adaptive approach to the construction of Gaussian process surrogates for Bayesian inference with expensive-to-evaluate forward models. Our method relies on the fully Bayesian approach to training Gaussian process models and utilizes the expected improvement idea from Bayesian global optimization. We adaptively construct training designs by maximizing the expected improvement in fit of the Gaussian process model to the noisy observational data. Numerical experiments on model problems with synthetic data demonstrate the effectiveness of the obtained adaptive designs compared to the fixed non-adaptive designs in terms of accurate posterior estimation at a fraction of the cost of inference with forward models.

Learning influence pathways of a network of dynamically related processes from observations is of considerable importance in many disciplines. In this article, influence networks of agents which interact dynamically via linear dependencies are considered. An algorithm for the reconstruction of the topology of interaction based on multivariate Wiener filtering is analyzed. It is shown that for a vast and important class of interactions, that respect flow conservation, the topology of the interactions can be exactly recovered. The class of problems where reconstruction is guaranteed to be exact includes power distribution networks, dynamic thermal networks and consensus networks. The efficacy of the approach is illustrated through simulation and experiments on consensus networks, IEEE power distribution networks and thermal dynamics of buildings.