One of the main challenges in autonomous robotic exploration and navigation in unknown and unstructured environments is determining where the robot can or cannot safely move. A significant source of difficulty in this determination arises from stochasticity and uncertainty, coming from localization error, sensor sparsity and noise, difficult-to-model robot-ground interactions, and disturbances to the motion of the vehicle. Classical approaches to this problem rely on geometric analysis of the surrounding terrain, which can be prone to modeling errors and can be computationally expensive. Moreover, modeling the distribution of uncertain traversability costs is a difficult task, compounded by the various error sources mentioned above. In this work, we take a principled learning approach to this problem. We introduce a neural network architecture for robustly learning the distribution of traversability costs. Because we are motivated by preserving the life of the robot, we tackle this learning problem from the perspective of learning tail-risks, i.e. the Conditional Value-at-Risk (CVaR). We show that this approach reliably learns the expected tail risk given a desired probability risk threshold between 0 and 1, producing a traversability costmap which is more robust to outliers, more accurately captures tail risks, and is more computationally efficient, when compared against baselines. We validate our method on data collected a legged robot navigating challenging, unstructured environments including an abandoned subway, limestone caves, and lava tube caves.

In the binary search space, GSA framework encounters the shortcomings of stagnation, diversity loss, premature convergence and high time complexity. To address these issues, a novel binary variant of GSA called `A novel neighbourhood archives embedded gravitational constant in GSA for binary search space (BNAGGSA)' is proposed in this paper. In BNAGGSA, the novel fitness-distance based social interaction strategy produces a self-adaptive step size mechanism through which the agent moves towards the optimal direction with the optimal step size, as per its current search requirement. The performance of the proposed algorithm is compared with the two binary variants of GSA over 23 well-known benchmark test problems. The experimental results and statistical analyses prove the supremacy of BNAGGSA over the compared algorithms. Furthermore, to check the applicability of the proposed algorithm in solving real-world applications, a windfarm layout optimization problem is considered. Two case studies with two different wind data sets of two different wind sites is considered for experiments.

Statistical signal processing applications usually require the estimation of some parameters of interest given a set of observed data. These estimates are typically obtained either by solving a multi-variate optimization problem, as in the maximum likelihood (ML) or maximum a posteriori (MAP) estimators, or by performing a multi-dimensional integration, as in the minimum mean squared error (MMSE) estimators. Unfortunately, analytical expressions for these estimators cannot be found in most real-world applications, and the Monte Carlo (MC) methodology is one feasible approach. MC methods proceed by drawing random samples, either from the desired distribution or from a simpler one, and using them to compute consistent estimators. The most important families of MC algorithms are Markov chain MC (MCMC) and importance sampling (IS). On the one hand, MCMC methods draw samples from a proposal density, building then an ergodic Markov chain whose stationary distribution is the desired distribution by accepting or rejecting those candidate samples as the new state of the chain. On the other hand, IS techniques draw samples from a simple proposal density, and then assign them suitable weights that measure their quality in some appropriate way. In this paper, we perform a thorough review of MC methods for the estimation of static parameters in signal processing applications. A historical note on the development of MC schemes is also provided, followed by the basic MC method and a brief description of the rejection sampling (RS) algorithm, as well as three sections describing many of the most relevant MCMC and IS algorithms, and their combined use.

The combination of data-rich remote sensing and new machine learning approaches is creating a revolution in yield forecasting, with accurate and …

For oil and gas companies looking at drilling wells in a new field, the issue becomes one of return vs. cost. The goal is simple enough: install the fewest number of wells that will draw them the most oil or gas from the underground reservoirs for the longest amount of time. The more wells installed, the higher the cost and the larger the impact on the environment. However, finding the right well placements quickly becomes a highly complex math problem. Too few wells sited in the wrong places leaves a lot of resources in the ground.

In a highly competitive market, all energy generators rely on highly accurate predictions of how much electricity they'll be able to make. Australian researchers have figured out a way to improve these predictions for wind and solar farms, using artificial intelligence. The National Energy Market – "the grid" – requires automatic forecasts every five minutes from electricity generators. This ensures that electricity generation meets demand. It can be very costly if those five-minute forecasts prove to be incorrect.

Argonne National Lab is teasing an upcoming webinar that promises to unveil a new neuromorphic computing chip design that can drop power by 10 times or more without sacrificing accuracy. Insect brains are the inspiration for the work. The webinar, being held August 12 for only 15 minutes, will feature Angel Yanguas-Gil, principal materials scientist, discussing his team's discoveries to allow AI to perform on a chip design using less than 1 watt. The lab promoted the event with a vague reference that the new design relies on "new materials, designs and hardware," with few details. "Can we help AI adapt to new and extreme environments--in space, inside nuclear power plants, or anywhere temperatures exceed 500 degrees Fahrenheit?" the lab said in its promotion.

Artificial Intelligence (AI) and remote sensing can help us in this area.

The global pandemic has resulted in the rapid acceleration of the digital transformation of many aspects of our lives--how we work, where we buy, and what new services and products are offered to us. But it and also exposed the inadequacy, inefficiency, and the sheer primitive aspects of the many processes, practices and policies governing the way we live now. Which technologies promise at least some progress in the near future? In an online broadcast to a global audience, leading VC firm OurCrowd released today a list of what it considers the top tech trends in mid-2021, when global venture capital funding reached an all-time high with more than $288 billion invested worldwide in the first half of this year. "There is no better time to analyze what the tech trends are for the smart investor, and where the technology market is moving," said Jon Medved, OurCrowd's founder and CEO, opening the broadcast.

Content delivery networks (CDNs) provide efficient content distribution over the Internet. CDNs improve the connectivity and efficiency of global communications, but their caching mechanisms may be breached by cyber-attackers. Among the security mechanisms, effective anomaly detection forms an important part of CDN security enhancement. In this work, we propose a multi-perspective unsupervised learning framework for anomaly detection in CDNs. In the proposed framework, a multi-perspective feature engineering approach, an optimized unsupervised anomaly detection model that utilizes an isolation forest and a Gaussian mixture model, and a multi-perspective validation method, are developed to detect abnormal behaviors in CDNs mainly from the client Internet Protocol (IP) and node perspectives, therefore to identify the denial of service (DoS) and cache pollution attack (CPA) patterns. Experimental results are presented based on the analytics of eight days of real-world CDN log data provided by a major CDN operator. Through experiments, the abnormal contents, compromised nodes, malicious IPs, as well as their corresponding attack types, are identified effectively by the proposed framework and validated by multiple cybersecurity experts. This shows the effectiveness of the proposed method when applied to real-world CDN data.