REINVENT 4 is a modern open-source generative AI framework for the design of small molecules. The software utilizes recurrent neural networks and transformer architectures to drive molecule generation. These generators are seamlessly embedded within general machine learning optimization algorithms, transfer learning, reinforcement curriculum learning. enables facilitates de novo design, R-group replacement, library linker scaffold hopping optimization. This contribution gives an overview...

The Grand Cooperative Driving Challenge (GCDC), with the aim to boost introduction of cooperative automated vehicles by means wireless communication, is presented. Experiences from previous edition GCDC, which was held in Helmond Netherlands 2011, are summarized, and an overview expectations challenges 2016 discussed. Two challenge scenarios, platoon merge intersection passing, specified One demonstration scenario for emergency designed showcase benefits driving. Communications closely...

Machine-learning (ML) and deep-learning (DL) approaches to predict the molecular properties of small molecules are increasingly deployed within design-make-test-analyze (DMTA) drug design cycle interest. Despite this uptake, there only a few automated packages aid their development deployment that also support uncertainty estimation, model explainability, other key aspects usage. This represents unmet need field, large number representations algorithms (and associated parameters) means it is...

Recently, we have released the de novo design platform REINVENT in version 2.0. This improved and extended iteration supports far more features scoring function components, which allows bespoke tailor-made protocols to maximize impact small molecule drug discovery projects. A major obstacle of generative models is producing active compounds, predictive (QSAR) been applied enrich target activity. However, QSAR are inherently limited by their applicability domains. To overcome these...

REINVENT4 is a modern open–source generative AI framework for the design of small molecules. The software utilizes recurrent neural networks and transformer architectures to drive molecule generation. These generators are seamlessly embedded within general machine learning optimization algorithms transfer learning, reinforcement curriculum learning. enables facilitates de novo design, R-group replacement, library linker scaffold hopping optimization. This contribution gives an overview...

Cooperative adaptive cruise control and platooning are well-known applications in the field of cooperative automated driving. However, extension toward maneuvering is desired to accommodate common highway maneuvers, such as merging, enable urban applications. To this end, a layered architecture adopted. In architecture, tactical layer hosts interaction protocols, describing wireless information exchange initiate vehicle supported by novel message set, whereas operational involves controllers...

Free-floating car-sharing (FFCS) allows users to book a vehicle through their phone, use it and return anywhere within designated area in the city. FFCS has potential contribute transition low-carbon mobility if vehicles are electric, usage does not displace active travel or public transport use. The aim of this paper is study what time patterns among early adopters service reveal about these two issues. We base our analysis on dataset containing rentals from 2014 2017, for 12 cities Europe...

A de novo molecular design workflow can be used together with technologies such as reinforcement learning to navigate the chemical space. bottleneck in that remains solved is how integrate human feedback exploration of space optimize molecules. drug designer still needs goal, expressed a scoring function for molecules captures designer's implicit knowledge about optimization task. Little support this task exists and, consequently, chemist usually resorts iteratively building objective...

An interaction protocol for cooperative platoon merge on highways is proposed. The facilitates a challenge scenario the Grand Cooperative Driving Challenge (GCDC) 2016, where two platoons running separate lanes into one due to roadwork in of lanes. Detailed procedures, described with state machines each vehicle are presented. A communication message set designed support controllers perform safe and efficient manoeuvres.

Matched molecular pairs (MMPs) are nowadays a commonly applied concept in drug design. They used many computational tools for structure-activity relationship analysis, biological activity prediction, or optimization of physicochemical properties. However, until now it has not been shown rigorous way that MMPs, is, changing only one substituent between two molecules, can be predicted with higher accuracy and precision contrast to any other chemical compound pair. It is expected model should...

Machine-learning (ML) and Deep-Learning (DL) approaches to predict the molecular properties of small molecules are increasingly deployed within design-make-test-analyse (DMTA) drug design cycle interest. Despite this uptake, there only a few automated packages aid their development deployment that also support uncertainty estimation, model explainability other key aspects usage. This represents unmet need field large number representations algorithms (and associated parameters) means it is...

In order to decrease time market for products it is important the implementation and debugging of control logic that are used manufacture products. this paper, an approach based on a high-level specification relations between process operations resources use formal verification presented. By using possible find potential errors within at early stage in development process. work shown how specifications may be translated into extended finite automata, these automata efficiently verified...

Cooperative speed harmonization based on floating car data aiming at improving manoeuvrability in a highly utilized intersection is presented. Intelligent Transportation Systems (C-ITS) aims gather information about the current traffic situation wireless communication and provide aggregated back to road users order improve e.g. efficiency, safety and/or comfort. Simulations show that proposed application capable of lowering CO2 emissions with up 11%, increasing average 14% reducing travel...

Recently, we have released the de novo design platform REINVENT in version 2.0. This improved and extended iteration supports far more features scoring function components, which allows bespoke tailor-made protocols to maximize impact small molecule drug discovery projects. A major obstacle of generative models is producing active compounds, predictive (QSAR) been applied enrich target activity. However, QSAR are inherently limited by their applicability domains. To overcome these...

Machine-learning (ML) and Deep-Learning (DL) approaches to predict the molecular properties of small molecules are increasingly deployed within design-make-test-analyse (DMTA) drug design cycle interest. Despite this uptake, there only a few automated packages aid their development deployment that also support uncertainty estimation, model explainability other key aspects usage. This represents unmet need field large number representations algorithms (and associated parameters) means it is...

Long haulage trucks consume large amounts of fuel, and fuel savings are desired both from economical environmental aspects. When the upcoming road topology is known, speed gear shifts can be optimized in order to minimize consumption by e.g. minimizing braking truck. Three different optimal control approaches evaluated compared for shift optimization problem. The results based on simulations, but two three solvers also implemented on-board a truck using rapid prototyping investigate...

Recently, we have released the de novo design platform REINVENT in version 2.0. This improved and extended iteration supports far more features scoring function components, which allows bespoke tailor-made protocols to maximize impact small molecule drug discovery projects. A major obstacle of generative models is producing active compounds, predictive (QSAR) been applied enrich target activity. However, QSAR are inherently limited by their applicability domains. To overcome these...

Despite the existing regulation efforts and measures, vehicles with dangerous goods still pose significant risks on public safety, especially in road tunnels. Solutions based cooperative intelligent transportation system (C-ITS) are promising however, they have received limited attention. We propose C-ITS applications that coordinate to minimize risk by maintaining safe distances between them Different mechanisms, including global centralized coordination, distributed local proposed...