There is a growing interest in using electric vehicles (EVs) and drones for many applications. However, battery-oriented issues, including range anxiety and battery degradation, impede adoption. Battery swap stations are one alternative to reduce these concerns that allow the swap of depleted for full batteries in minutes. We consider the problem of deriving actions at a battery swap station when explicitly considering the uncertain arrival of swap demand, battery degradation, and replacement. We model the operations at a battery swap station using a finite horizon Markov Decision Process model for the stochastic scheduling, allocation, and inventory replenishment problem (SAIRP), which determines when and how many batteries are charged, discharged, and replaced over time. We present theoretical proofs for the monotonicity of the value function and monotone structure of an optimal policy for special SAIRP cases. Due to the curses of dimensionality, we develop a new monotone approximate dynamic programming (ADP) method, which intelligently initializes a value function approximation using regression. In computational tests, we demonstrate the superior performance of the new regression-based monotone ADP method as compared to exact methods and other monotone ADP methods. Further, with the tests, we deduce policy insights for drone swap stations.

Multi working-machines pathfinding solution enables more mobile machines simultaneously to work inside of a working site so that the productivity can be expected to increase evolutionary. To date, the potential cooperation conflicts among construction machinery limit the amount of construction machinery investment in a concrete working site. To solve the cooperation problem, civil engineers optimize the working site from a logistic perspective while computer scientists improve pathfinding algorithms' performance on the given benchmark maps. In the practical implementation of a construction site, it is sensible to solve the problem with a hybrid solution; therefore, in our study, we proposed an algorithm based on a cutting-edge multi-pathfinding algorithm to enable the massive number of machines cooperation and offer the advice to modify the unreasonable part of the working site in the meantime. Using the logistic information from BIM, such as unloading and loading point, we added a pathfinding solution for multi machines to improve the whole construction fleet's productivity. In the previous study, the experiments were limited to no more than ten participants, and the computational time to gather the solution was not given; thus, we publish our pseudo-code, our tested map, and benchmark our results. Our algorithm's most extensive feature is that it can quickly replan the path to overcome the emergency on a construction site.

Between 1977 and 2014, 80 percent of ExxonMobil's internal research supported the idea that human activity was a contributor to climate change. But during that same period, 80 percent of the oil and gas provider's public statements instead expressed doubt whether climate change was caused by humans--or even real in the first place. To draw this conclusion, Harvard researchers Geoffrey Supran and Naomi Oreskes used machine learning to review more than 200 internal documents, peer-reviewed research, and public statements from Exxon Mobil. The newly released paper, "Rhetoric and frame analysis of ExxonMobil's climate change communications," exposes a decades-long pattern of public statements that sanitize the company's role in contributing to CO2 emissions. Oreskes and Supran used machine learning analysis to support two claims.

Thirty-five years after the Chernobyl Nuclear Power Plant in Ukraine exploded in the world's worst nuclear accident, fission reactions are smoldering again in uranium fuel masses deep inside a mangled reactor hall. “It's like the embers in a barbecue pit,” says Neil Hyatt, a nuclear materials chemist at the University of Sheffield. Now, Ukrainian scientists are scrambling to learn whether the reactions will wink out—or require extraordinary steps to avert another accident. Sensors are tracking a rising number of neutrons, a signal of fission, streaming from one inaccessible room, Anatolii Doroshenko of the Institute for Safety Problems of Nuclear Power Plants (ISPNPP) in Kyiv, Ukraine, reported last month during discussions about dismantling the reactor. “There are many uncertainties,” says ISPNPP's Maxim Saveliev. “But we can't rule out the possibility of [an] accident.” The neutron counts are rising slowly, Saveliev says, suggesting managers still have a few years to figure out how to stifle the threat. Any remedy will be of keen interest to Japan, which is coping with the aftermath of its own nuclear disaster 10 years ago at Fukushima, Hyatt notes. “It's a similar magnitude of hazard.” The specter of self-sustaining fission, or criticality, in the nuclear ruins has long haunted Chernobyl. When part of the Unit Four reactor's core melted down on 26 April 1986, uranium fuel rods and their zirconium cladding, graphite blocks, and sand dumped on the core to try to extinguish the fire melted together into a lava. It flowed into basement rooms and hardened into formations called fuel-containing materials (FCMs), laden with about 170 tons of irradiated uranium—95% of the original fuel. The concrete-and-steel sarcophagus called the Shelter, erected 1 year after the accident to house Unit Four's remains, allowed rainwater to seep in. Because water slows, or moderates, neutrons and thus enhances their odds of striking and splitting uranium nuclei, heavy rains sometimes sent neutron counts soaring. After a downpour in June 1990, a “stalker”—a scientist at Chernobyl who risks radiation exposure to venture into the damaged reactor hall—dashed in and sprayed gadolinium nitrate solution, which absorbs neutrons, on an FCM that scientists feared might go critical. Several years later, the Shelter was equipped with gadolinium nitrate sprinklers. But the spray can't effectively penetrate some basement rooms. Chernobyl officials presumed any criticality risk would fade when the massive New Safe Confinement (NSC) was slid over the Shelter in November 2016. The €1.5 billion structure was meant to seal off the Shelter so it could be stabilized and eventually dismantled. It also keeps out the rain, and since its emplacement, neutron counts in much of the Shelter have been stable or are declining. But they began to edge up in a few spots, nearly doubling over 4 years in room 305/2, which contains tons of FCMs buried under debris. ISPNPP modeling suggests the drying of the fuel is somehow making neutrons ricocheting through it more, rather than less, effective at splitting uranium nuclei. “It's believable and plausible data,” Hyatt says. “It's just not clear what the mechanism might be.” The threat can't be ignored. As water continues to recede, the fear is that “the fission reaction accelerates exponentially,” Hyatt says, leading to “an uncontrolled release of nuclear energy.” There's no chance of a repeat of 1986, when the explosion and fire sent a radioactive cloud over Europe. A runaway fission reaction in an FCM could sputter out after heat from fission boils off the remaining water. Still, Saveliev notes, although any explosive reaction would be contained, it could threaten to bring down unstable parts of the rickety Shelter, filling the NSC with radioactive dust. Addressing the newly unmasked threat is a daunting challenge. Radiation levels in 305/2 preclude installing sensors. And spraying gadolinium nitrate on the nuclear debris there is not an option, as it's entombed under concrete. One idea is to develop a robot that can withstand the intense radiation for long enough to drill holes in the FCMs and insert boron cylinders, which would function like reactor control rods and sop up neutrons. In the meantime, ISPNPP intends to step up monitoring of two other areas where FCMs have the potential to go critical. The resurgent fission reactions are not the only challenge facing Chernobyl's keepers. Besieged by intense radiation and high humidity, the FCMs are disintegrating—spawning even more radioactive dust that complicates plans to dismantle the Shelter. Early on, an FCM formation called the Elephant's Foot was so hard scientists had to use a Kalashnikov rifle to shear off a chunk for analysis. “Now it more or less has the consistency of sand,” Saveliev says. Ukraine has long intended to remove the FCMs and store them in a geological repository. By September, with help from European Bank for Reconstruction and Development, it aims to have a comprehensive plan for doing so. But with life still flickering within the Shelter, it may be harder than ever to bury the reactor's restless remains.

Model based reinforcement learning (MBRL) uses an imperfect model of the world to imagine trajectories of future states and plan the best actions to maximize a reward function. These trajectories are imperfect and MBRL attempts to overcome this by relying on model predictive control (MPC) to continuously re-imagine trajectories from scratch. Such re-generation of imagined trajectories carries the major computational cost and increasing complexity in tasks with longer receding horizon. This paper aims to investigate how far in the future the imagined trajectories can be relied upon while still maintaining acceptable reward. Firstly, an error analysis is presented for systematic skipping recalculations for varying number of consecutive steps.% in several challenging benchmark control tasks. Secondly, we propose two methods offering when to trust and act upon imagined trajectories, looking at recent errors with respect to expectations, or comparing the confidence in an action imagined against its execution. Thirdly, we evaluate the effects of acting upon imagination while training the model of the world. Results show that acting upon imagination can reduce calculations by at least 20% and up to 80%, depending on the environment, while retaining acceptable reward.

Avoiding hybrid obstacles in unknown scenarios with an efficient flight strategy is a key challenge for unmanned aerial vehicle applications. In this paper, we introduce a technique to distinguish dynamic obstacles from static ones with only point cloud input. Then, a computationally efficient obstacle avoidance motion planning approach is proposed and it is in line with an improved relative velocity method. The approach is able to avoid both static obstacles and dynamic ones in the same framework. For static and dynamic obstacles, the collision check and motion constraints are different, and they are integrated into one framework efficiently. In addition, we present several techniques to improve the algorithm performance and deal with the time gap between different submodules. The proposed approach is implemented to run onboard in real-time and validated extensively in simulation and hardware tests. Our average single step calculating time is less than 20 ms.

Smart Cities and Communities (SCC) constitute a new paradigm in urban development. SCC ideates on a data-centered society aiming at improving efficiency by automating and optimizing activities and utilities. Information and communication technology along with internet of things enables data collection and with the help of artificial intelligence (AI) situation awareness can be obtained to feed the SCC actors with enriched knowledge. This paper describes AI perspectives in SCC and gives an overview of AI-based technologies used in traffic to enable road vehicle automation and smart traffic control. Perception, Smart Traffic Control and Driver Modelling are described along with open research challenges and standardization to help introduce advanced driver assistance systems and automated vehicle functionality in traffic. To fully realize the potential of SCC, to create a holistic view on a city level, the availability of data from different stakeholders is need. Further, though AI technologies provide accurate predictions and classifications there is an ambiguity regarding the correctness of their outputs. This can make it difficult for the human operator to trust the system. Today there are no methods that can be used to match function requirements with the level of detail in data annotation in order to train an accurate model. Another challenge related to trust is explainability, while the models have difficulties explaining how they come to a certain conclusion it is difficult for humans to trust it.

In this paper we show how using satellite images can improve the accuracy of housing price estimation models. Using Los Angeles County's property assessment dataset, by transferring learning from an Inception-v3 model pretrained on ImageNet, we could achieve an improvement of ~10% in R-squared score compared to two baseline models that only use non-image features of the house.

Climate change is a burning issue of our time, with the Sustainable Development Goal (SDG) 13 of the United Nations demanding global climate action. Realizing the urgency, in 2015 in Paris, world leaders signed an agreement committing to taking voluntary action to reduce carbon emissions. However, the scale, magnitude, and climate action processes vary globally, especially between developed and developing countries. Therefore, from parliament to social media, the debates and discussions on climate change gather data from wide-ranging sources essential to the policy design and implementation. The downside is that we do not currently have the mechanisms to pool the worldwide dispersed knowledge emerging from the structured and unstructured data sources. The paper thematically discusses how NLP techniques could be employed in climate policy research and contribute to society's good at large. In particular, we exemplify symbiosis of NLP and Climate Policy Research via four methodologies. The first one deals with the major topics related to climate policy using automated content analysis. We investigate the opinions (sentiments) of major actors' narratives towards climate policy in the second methodology. The third technique explores the climate actors' beliefs towards pro or anti-climate orientation. Finally, we discuss developing a Climate Knowledge Graph. The present theme paper further argues that creating a knowledge platform would help in the formulation of a holistic climate policy and effective climate action. Such a knowledge platform would integrate the policy actors' varied opinions from different social sectors like government, business, civil society, and the scientific community. The research outcome will add value to effective climate action because policymakers can make informed decisions by looking at the diverse public opinion on a comprehensive platform.

Scientists monitoring the ruins of the Chernobyl nuclear power plant in Ukraine have seen a surge in fission reactions in an inaccessible chamber within the complex. They are now investigating whether the problem will stabilise or require a dangerous and difficult intervention to prevent a runaway nuclear reaction. The explosion at Chernobyl in 1986 brought down walls and sealed off many rooms and corridors. Tonnes of fissile material from the interior of a reactor were strewn throughout the facility and the heat it generated melted sand from the reactor walls with concrete and steel to form lava-like and intensely radioactive substances that oozed into lower floors. One chamber, known as subreactor room 305/2, is thought to contain large amounts of this material, but it is inaccessible and hasn't been seen by human or robotic eyes since the disaster.