检索结果-内蒙古大学图书馆

Properties of singular solutions in optimal control problems under input dynamic extension

学校读者我要写书评

暂无评论

Properties of singular solutions in optimal control problems...

IEEE Conference on Decision and control

作者： Paolo Di Giamberardino Daniela Iacoviello Dept. of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome via Ariosto 25 Rome Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

关键词： Optimal control Cost function

Deep Reinforcement Learning Platooning control of Non-Cooperative Autonomous Vehicles in a Mixed Traffic Environment

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Platooning Control of Non-Cooper...

IEEE International Conference on Automation Science and engineering (CASE)

作者： Danilo Menegatti Andrea Wrona antonio Di Paola Simone Gentile Alessandro Giuseppi Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Rome Italy Dept. of Electrical and Information Engineering Polytechnic of Bari Bari Italy

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Ensuring secure spacing between vehicles is vital for road safety, efficient traffic flow, and system stability in autonomous driving. While traditional cooperative platooning approach, relying on centralized coordination exploiting wireless network, faces practical implementation challenges due to communication constraints and diverse driving behaviors, this work introduces a scalable non-cooperative multi-agent platooning strategy based on Deep Reinforcement Learning, leveraging on decentralized decision-making principles. The agents’ aim is to adjust their velocities dynamically to ensure safe following distances and adapt to surrounding vehicle behavior, without the possibility of exchanging information over a wireless network. Extensive simulations validate the effectiveness and robustness of the proposed approach, making it suitable for real-world autonomous driving scenarios.

关键词： Wireless networks Deep reinforcement learning control systems Aerodynamics Robustness Stability analysis Sensors Vehicle dynamics Autonomous vehicles Optimization

Precise Orbit Determination on LEO Satellite using Pseudorange and Pseudorange-Rate Measurements

学校读者我要写书评

暂无评论

Precise Orbit Determination on LEO Satellite using Pseudoran...

Mediterranean Conference on control and Automation (MED)

作者： Andrea Tantucci Andrea Wrona antonio Pietrabissa Dept. of Computer Control and Management Engineering “Antonio Ruberti” - (DIAG) University of Rome “La Sapienza” Rome Italy

Nowadays, along with the trend of developing highly autonomous satellites, there is a strong motivation to improve real-time Precise Orbit Determination (POD), in particular for Low Earth Orbit (LEO) satellites. The development of Global Navigation Satellite System (GNSS) sensors allows to obtain low-noise measurements and provide a satellite with autonomous continuous tracking onboard. Following the deactivation of Selective Availability, a representative real-time positioning accuracy of 10 m is presently achieved by means of Global Positioning System (GPS) receivers on LEO satellites. The introduction of dynamical filtering methods has opened a new way to improve this accuracy by making use of measurements such as pseudorange or carrier-phase. This paper presents a Kalman filtering approach using pseudorange and pseudorange-rate measurements instead of pseudorange and carrier-phase ones, with advantages in terms of storage and processing requirements. An error of around 0.2 m and 1e-3 m/s for position and velocity is obtained, which is in line if not better w.r.t. other approaches.

关键词：

Cooperation and mental states neurophysiological assessment for pilots' training and expertise evaluation

学校读者我要写书评

暂无评论

Cooperation and mental states neurophysiological assessment ...

2023 IEEE International Workshop on Technologies for Defense and Security, TechDefense 2023

作者： Borghini, Gianluca Giorgi, Andrea Ronca, Vincenzo Mezzadri, Lorenzo Capotorto, Rossella Arico, Pietro Di Flumeri, Gianluca Babiloni, Fabio Sapienza University of Rome Dept. of Molecular Medicine Rome Italy Sapienza University of Rome Dept. of Anatomical Histological Forensic and Orthopaedic Sciences Rome Italy Sapienza University of Rome Dept. of Computer Control and Management Engineering Antonio Ruberti Rome Italy Urbe Aero Ato Flight Training School Rome Italy

ISBN: (纸本)9798350319392

The aim of the study was to validate a methodology for professional pilots' neurophysiological assessment to improve training program tailoring and management. In particular, the assessment focused on quantifying (i) mental workload, (ii) stress level (iii) and the cooperation degree between the two members of the crews. Two groups of pilots were involved in the experiments: Experienced and Unexperienced. Additionally, the Instructor was responsible to provide subjective evaluation about the pilots' mental states and cooperation. During the entire flight simulations, the pilots' brain activity was acquired through the Electroencephalography (EEG). The results demonstrated that it is possible to quantify operators' mental states and degree of cooperation while dealing with flight simulations under realistic settings. Pilots' mental workload and stress behavioral levels resulted to be positively and significantly correlated with the corresponding neurophysiological measurements (all R > 0.6, all p © 2023 IEEE.

关键词： Electroencephalography

Semi-Supervised GCN for learning Molecular Structure-Activity Relationships

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ragno, Alessio Savoia, Dylan Capobianco, Roberto Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Sony AI

Since the introduction of artificial intelligence in medicinal chemistry, the necessity has emerged to analyse how molecular property variation is modulated by either single atoms or chemical groups. In this paper, we propose to train graph-to-graph neural network using semi-supervised learning for attributing structure-property relationships. As initial case studies we apply the method to solubility and molecular acidity while checking its consistency in comparison with known experimental chemical data. As final goal, our approach could represent a valuable tool to deal with problems such as activity cliffs, lead optimization and de-novo drug design. © 2022, CC BY.

关键词： Graph neural networks

Molecule Generation from Input-Attributions over Graph Convolutional Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Savoia, Dylan Ragno, Alessio Capobianco, Roberto Dept. of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Sony AI

It is well known that Drug Design is often a costly process both in terms of time and economic effort. While good Quantitative Structure-Activity Relationship models (QSAR) can help predicting molecular properties without the need to synthesize them, it is still required to come up with new molecules to be tested. This is mostly done in lack of tools to determine which modifications are more promising or which aspects of a molecule are more influential for the final activity/property. Here we present an automatic process which involves Graph Convolutional Network models and input-attribution methods to generate new molecules. We also explore the problems of over-optimization and applicability, recognizing them as two important aspects in the practical use of such automatic tools. © 2022, CC BY.

关键词： Molecules

An Approach for Improving Automatic Mouth Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Biondi, Giulio Franzoni, Valentina Gervasi, Osvaldo Perri, Damiano University of Florence Dept. of Mathematics and Computer Science Florence Italy University of Perugia Dept. of Mathematics and Computer Science Perugia Italy Sapienza University of Rome Department of Computer Control and Management Engineering "Antonio Ruberti" Rome Italy

The study proposes and tests a technique for automated emotion recognition through mouth detection via Convolutional Neural Networks (CNN), meant to be applied for supporting people with health disorders with communication skills issues (e.g. muscle wasting, stroke, autism, or, more simply, pain) in order to recognize emotions and generate real-time feedback, or data feeding supporting systems. The software system starts the computation identifying if a face is present on the acquired image, then it looks for the mouth location and extracts the corresponding features. Both tasks are carried out using Haar Feature-based Classifiers, which guarantee fast execution and promising performance. If our previous works focused on visual micro-expressions for personalized training on a single user, this strategy aims to train the system also on generalized faces data sets. © 2022, CC BY-NC-ND.

关键词： Emotion Recognition

Cooperation and mental states neurophysiological assessment for pilots’ training and expertise evaluation

学校读者我要写书评

暂无评论

Cooperation and mental states neurophysiological assessment ...

Technologies for Defense and Security (TechDefense), IEEE International Workshop on

作者： Gianluca Borghini Andrea Giorgi Vincenzo Ronca Lorenzo Mezzadri Rossella Capotorto Pietro Aricò Gianluca Di Flumeri Fabio Babiloni Dept. of Molecular Medicine Sapienza University of Rome Rome Italy Dept. of Anatomical Histological Forensic and Orthopaedic Sciences Sapienza University of Rome Rome Italy Dept. of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Rome Italy Flight Training School Urbe Aero ATO Rome Italy

The aim of the study was to validate a methodology for professional pilots’ neurophysiological assessment to improve training program tailoring and management. In particular, the assessment focused on quantifying (i) mental workload, (ii) stress level (iii) and the cooperation degree between the two members of the crews. Two groups of pilots were involved in the experiments: Experienced and Unexperienced. Additionally, the Instructor was responsible to provide subjective evaluation about the pilots’ mental states and cooperation. During the entire flight simulations, the pilots’ brain activity was acquired through the Electroencephalography (EEG). The results demonstrated that it is possible to quantify operators’ mental states and degree of cooperation while dealing with flight simulations under realistic settings. Pilots’ mental workload and stress behavioral levels resulted to be positively and significantly correlated with the corresponding neurophysiological measurements (all R > 0.6, all p < 0.05), while cooperation was observed to be higher (p < 0.05) for the Experienced than the Unexperienced. Although the results are preliminary, they show how the capability of quantifying pilots’ mental states and cooperation while dealing with tasks will provide the instructors with additional and objective information. In particular, this information would allow for tailoring the training sessions based on crew’s behavior.

关键词：

Submodular Maximization subject to a Knapsack Constraint: CombinatorialAlgorithmswithNear-optimalAdaptiveComplexity

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Amanatidis, Georgios Fusco, Federico Lazos, Philip Leonardi, Stefano Spaccamela, Alberto Marchetti Reiffenhäuser, Rebecca Dept. of Mathematical Sciences University of Essex United Kingdom Archimedes Unit Athena Research Center Greece Dept. of Computer Control and Management Eng. "Antonio Ruberti" Sapienza University of Rome Italy Input Output United Kingdom Institute for Logic Language and Computation University of Amsterdam Netherlands

Submodular maximization is a classic algorithmic problem with multiple applications in data mining and machine learning;there, the growing need to deal with massive instances motivates the design of algorithms balancing the quality of the solution with applicability. For the latter, an important measure is the adaptive complexity, which captures the number of sequential rounds of parallel computation needed by an algorithm to terminate. In this work we obtain the first constant factor approximation algorithm for non-monotone submodular maximization subject to a knapsack constraint with near-optimal O(log n) adaptive complexity. Low adaptivity by itself, however, is not enough: a crucial feature to account for is represented by the total number of function evaluations (or value queries). Our algorithm asks Õ(n2) value queries, but can be modified to run with only Õ(n) instead, while retaining a low adaptive complexity of O(log2 n). Besides the above improvement in adaptivity, this is also the first combinatorial approach with sublinear adaptive complexity for the problem and yields algorithms comparable to the state-of-the-art even for the special cases of cardinality constraints or monotone objectives. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning