Every year, around 1.3 million people all over the world are killed by road mishaps with approximately 20 to 50 million life-threatening injuries(International Transport Forum, 2018; World Health Organisation, 2018). Notwithstanding, there is a disparity in road traffic death from 9.3 to 26.6 per 100,000 population among countries based on their income level, while the global rate is still 18.2 per 100,000 population (World Health Organisation, 2018). Moreover, traffic collision at intersections is a significant threat to upholding road safety. As a whole, 45% of severe injuries occur at intersections, including 22% of fatal crashes (Li, Jia, et al., 2016). Drivers often inadvertently fail to break immediately at the onset of red light or deliberately run through the red light signal and also miscalculate the motif of the right angle vehicle [in a right-hand driving condition] while crossing the intersection (Zhang et al., 2018). Especially at the onset of yellow signal, drivers get confused with decision measurement either to stop or to run and to get involved in rear-end collision or right-angle collision or uncomfortable hard brake, often resulting in injuries or death (Gazis et al., 1960; Majhi & Senathipathi, 2019).

Adjoint-based optimization methods are attractive for aerodynamic shape design primarily due to their computational costs being independent of the dimensionality of the input space and their ability to generate high-fidelity gradients that can then be used in a gradient-based optimizer. This makes them very well suited for high-fidelity simulation based aerodynamic shape optimization of highly parametrized geometries such as aircraft wings. However, the development of adjoint-based solvers involve careful mathematical treatment and their implementation require detailed software development. Furthermore, they can become prohibitively expensive when multiple optimization problems are being solved, each requiring multiple restarts to circumvent local optima. In this work, we propose a machine learning enabled, surrogate-based framework that replaces the expensive adjoint solver, without compromising on predicting predictive accuracy. Specifically, we first train a deep neural network (DNN) from training data generated from evaluating the high-fidelity simulation model on a model-agnostic, design of experiments on the geometry shape parameters. The optimum shape may then be computed by using a gradient-based optimizer coupled with the trained DNN. Subsequently, we also perform a gradient-free Bayesian optimization, where the trained DNN is used as the prior mean. We observe that the latter framework (DNN-BO) improves upon the DNN-only based optimization strategy for the same computational cost. Overall, this framework predicts the true optimum with very high accuracy, while requiring far fewer high-fidelity function calls compared to the adjoint-based method. Furthermore, we show that multiple optimization problems can be solved with the same machine learning model with high accuracy, to amortize the offline costs associated with constructing our models.

A UK boat has just provided an impressive demonstration of the future of robotic maritime operations. The 12m-long Uncrewed Surface Vessel (USV) Maxlimer has completed a 22-day-long mission to map an area of seafloor in the Atlantic. SEA-KIT International, which developed the craft, "skippered" the entire outing via satellite from its base in Tollesbury in eastern England. The mission was part-funded by the European Space Agency. Robot boats promise a dramatic change in the way we work at sea. Already, many of the big survey companies that run traditional crewed vessels have started to invest heavily in the new, remotely operated technologies.

The state of Michigan wants to build the autonomous roadway of the future. Normally that in itself would be interesting enough, but there's also the company it's partnering with to make the project a reality. The state will work with a firm called Cavnue. Cavnue's parent company is Sidewalk Infrastructure Partners (SIP), which itself is a spinoff of Alphabet's Sidewalk Labs. If you've followed Engadget's coverage of the recently canceled Toronto Smart City project, you'll know all about Sidewalk Labs.

Part of the evolution of self-driving cars is deploying the vehicles in geofenced areas: Instead of putting them out into the entirety of the world, they're kept within a geographic area that has been mapped and determined to work well with the capabilities of an autonomous vehicle. Some of those areas might be special lanes specifically for vehicles that are driven by robots. Michigan is looking into creating such a lane. The state of Michigan and Cavenue (a company founded by Sidewalk Infrastructure Partners, which is part of Alphabet, the parent company of Google) has partnered up to explore building a 40-mile driverless corridor between Detroit and Ann Arbor. The route would be along Michigan Avenue and I-94 and would connect to Detroit Metropolitan Airport, Detroit's Central Station, and the University of Michigan.

The service requires full cookie support in order to view this website. Please enable cookies on your browser and try again.

For decades, Hollywood has made millions off of our fears that artificial intelligences such as HAL in 2001: A Space Odyssey and Skynet in The Terminator could one day control us or even wipe out humanity. Today, we have kindler, gentler, real-life AIs like iPhone's Siri and Amazon's Alexa, and according to a new survey overseen by a team of University of Delaware researchers, many of us are more than happy to include this technology in our daily lives. The results of the survey, released this month, show that almost half of all Americans say they use a voice-activated personal assistant such as Siri or Alexa. Those who use such assistants are particularly likely to support developing AI (63%) and public funding for research on it (46%), while those who do not utilize these services show less support (51% and 37%, respectively). Furthermore, people who use voice assistants are especially likely to see AI as having positive effects on society and to feel hopeful about the technology.

Grammy award-winning artist Beck took an ethereal journey to the stars for his 2019 record "Hyperspace." Now, he has taken this cosmic journey a giant leap forward in a collaboration with NASA's Jet Propulsion Laboratory and artificial intelligence creatives OSK. The result: A visual album experience titled "Hyperspace: A.I. Exploration." The new visual album, unveiled today (Aug. To launch "Hyperspace: A.I. Explorations," Beck premiered a bonus track from "Hyperspace" titled "I Am The Cosmos (42420)," on Aug. 12 on Youtube along with videos for the rest of the songs.

When a bald eagle tangled unexpectedly with a government drone last month in Michigan, it won, emerging from the scene unscathed. Officials say it is somewhere in Lake Michigan. The Michigan Department of Environment, Great Lakes and Energy disclosed the attack on Thursday, almost one month after the eagle sent the $950 drone into the Great Lake. The trouble began when Hunter King, an environmental quality analyst with the department, sent a drone over Michigan's Upper Peninsula to map shoreline erosion, the department said. Delta flight returns to Austin airport after striking what may have been birds or a drone, officials say His drone's reception started to sputter, so he commanded it to return home.

More than 200 million Amazon Alexa devices were at risk of cyber attacks due to a bug found lurking in the smart assistant. Security researchers found a vulnerability that lets cybercriminals obtain voice history data, along with deleting and installing commands and apps. The team discovered a misconfiguration in the system the permitted them to perform actions on the victim's behalf and view personal information. Amazon has since rolled out a patch after the issue was reported to the tech giant and notes it is not aware of any incidents related to the bug. More than 200 million Amazon Alexa devices were at risk of cyber attacks due to a bug found lurking in the smart assistant.