The escalating complexity of System-on-Chip (SoC) designs has created a bottleneck in verification, with traditional techniques struggling to achieve complete coverage. Existing techniques, such as Constrained Random Verification (CRV) and coverage-driven methodologies, rely on time-consuming and redundant simulation regression, leading to higher verification costs and longer time-to-market due to the manual effort required to adjust constraints and drive the stimuli to achieve coverage objectives. To address this challenge, we propose a novel methodology that leverages supervised Machine Learning (ML) to optimize simulation regressions, resulting in reduced simulation run-time and the number of test simulations required to achieve target coverage goals. We also investigate and compare the effectiveness of various supervised learning algorithms from scikit-learn. Our results demonstrate that these algorithms can achieve at least 99% coverage regain with significantly reduced simulation cycles. We utilize Python Universal Verification Methodology (PyUVM) over SystemVerilog-Universal Verification Methodology (SV-UVM) for testbench creation, enabling simpler constructs using Python and facilitating the reuse of existing ML libraries. Our methodology is applied to three diverse designs, and our results show that it can significantly reduce verification costs, manual efforts, and time-to-market, while enhancing verification productivity and completeness, by automating the testbench update process and achieving target coverage goals.

The transport ministry will launch priority lanes for autonomous vehicles on a roughly 100-kilometer section of the Shin-Tomei Expressway to conduct test runs of self-driving trucks, starting on March 3. The trial is expected to last about one year. The move is part of a plan to create a road network that can handle so-called Level 4 autonomous driving, or unmanned driving under certain conditions, amid labor shortages in the logistics industry. The lanes will run from the Surugawan-Numazu rest area to the Hamamatsu rest area, both in Shizuoka Prefecture. One of the three lanes in both the eastbound and westbound directions of the expressway will be designated priority lanes between 10 p.m. on weekdays and 5 a.m. the following morning.

We introduce GPTreeO, a flexible R package for scalable Gaussian process (GP) regression, particularly tailored to continual learning problems. GPTreeO builds upon the Dividing Local Gaussian Processes (DLGP) algorithm, in which a binary tree of local GP regressors is dynamically constructed using a continual stream of input data. In GPTreeO we extend the original DLGP algorithm by allowing continual optimisation of the GP hyperparameters, incorporating uncertainty calibration, and introducing new strategies for how the local partitions are created. Moreover, the modular code structure allows users to interface their favourite GP library to perform the local GP regression in GPTreeO. The flexibility of GPTreeO gives the user fine-grained control of the balance between computational speed, accuracy, stability and smoothness. We conduct a sensitivity analysis to show how GPTreeO's configurable features impact the regression performance in a continual learning setting.

Ever get your McDonald's order mixed up at an AI-powered drive-through? The experiment behind the fast food giant's current automated order taker will soon be coming to a close. McDonald's confirmed Monday that it decided to end a global partnership with IBM, which has been testing this artificial intelligence technology at select McDonald's drive-throughs since 2021. That doesn't mean you'll never encounter some sort of chatbot while picking up fries on your car ride home again. While the IBM partnership for McDonald's current automated order taker test is winding down, the Chicago-based company suggested that it wasn't ruling other any other potential AI drive-throughs plans down the road -- pointing to "an opportunity to explore voice ordering solutions more broadly."

Adapting to regularities of the environment is critical for biological organisms to anticipate events and plan. A prominent example is the circadian rhythm corresponding to the internalization by organisms of the $24$-hour period of the Earth's rotation. In this work, we study the emergence of circadian-like rhythms in deep reinforcement learning agents. In particular, we deployed agents in an environment with a reliable periodic variation while solving a foraging task. We systematically characterize the agent's behavior during learning and demonstrate the emergence of a rhythm that is endogenous and entrainable. Interestingly, the internal rhythm adapts to shifts in the phase of the environmental signal without any re-training. Furthermore, we show via bifurcation and phase response curve analyses how artificial neurons develop dynamics to support the internalization of the environmental rhythm. From a dynamical systems view, we demonstrate that the adaptation proceeds by the emergence of a stable periodic orbit in the neuron dynamics with a phase response that allows an optimal phase synchronisation between the agent's dynamics and the environmental rhythm.

The promise of increased road safety is a key motivator for the development of automated vehicles (AV). Yet, demonstrating that an AV is as safe as, or even safer than, a human-driven vehicle has proven to be challenging. Should an AV be examined purely virtually, allowing large numbers of fully controllable tests? Or should it be tested under real environmental conditions on a proving ground? Since different test setups have different strengths and weaknesses, it is still an open question how virtual and real tests should be combined. On the way to answer this question, this paper proposes transfer importance sampling (TIS), a risk estimation method linking different test setups. Fusing the concepts of transfer learning and importance sampling, TIS uses a scalable, cost-effective test setup to comprehensively explore an AV's behavior. The insights gained then allow parameterizing tests in a more trustworthy test setup accurately reflecting risks. We show that when using a trustworthy test setup alone is prohibitively expensive, linking it to a scalable test setup can increase efficiency $\unicode{x2013}$ without sacrificing the result's validity. Thus, the test setups' individual deficiencies are compensated for by their systematic linkage.

NYPD canceled its contract with Boston Dynamics last week after its test run of the company's Spot robot sparked concerns of misuse of city funds and potential police abuse. NYPD canceled its contract with Boston Dynamics last week after its test run of the company's Spot robot sparked concerns of misuse of city funds and potential police abuse. After a public outcry, a robotic dog once hailed by the New York Police Department a high-tech crime-fighting sidekick is getting sent back to its owner. The police canceled a $94,000 contract with the robot's maker Boston Dynamics following a growing backlash tied to calls to cut the police budget and concerns of police militarization and abuses of force. The department introduced the public to the "Digidog" in December after acquiring the device in a test program.

Climate models play a crucial role in understanding the effect of environmental and man-made changes on climate to help mitigate climate risks and inform governmental decisions. Large global climate models such as the Community Earth System Model (CESM), developed by the National Center for Atmospheric Research, are very complex with millions of lines of code describing interactions of the atmosphere, land, oceans, and ice, among other components. As development of the CESM is constantly ongoing, simulation outputs need to be continuously controlled for quality. To be able to distinguish a "climate-changing" modification of the code base from a true climate-changing physical process or intervention, there needs to be a principled way of assessing statistical reproducibility that can handle both spatial and temporal high-dimensional simulation outputs. Our proposed work uses probabilistic classifiers like tree-based algorithms and deep neural networks to perform a statistically rigorous goodness-of-fit test of high-dimensional spatio-temporal data.

Japan Post Co. unveiled Wednesday a self-driving mail delivery robot as demand grows for minimizing human contact amid the coronavirus pandemic. Using built-in cameras and sensors, the robot -- which is the size of a wheelchair -- operated on a sidewalk in Tokyo's Chiyoda Ward, dodging obstacles such as utility poles, and crossed an intersection with traffic lights. The robot is in the middle of a series of test runs that began on Sept. 18 and runs through late October. One of the tests involves the robot traveling 700 meters from a convenience store in a hospital to a local post office in about 25 minutes. The red DeliRo robot developed by ZMP Inc. is capable of carrying packages weighing up to 30 kilograms at a speed of 6 kilometers per hour, according to Japan Post, which aims to put the self-driving delivery robots into practical use in fiscal 2021.

However, manually copy data from multiple sources for retrieval in a central place can be very tedious and time-consuming. "Web scraping," also called crawling or spidering, is the automated gathering of data from an online source usually from a website. While scraping is a great way to get massive amounts of data in relatively short timeframes, it does add stress to the server where the source hosted. However, as long as it does not disrupt the primary function of the online source, it is relatively acceptable. Despite its legal challenges, web scraping remains popular even in 2019.