Filters








8,578 Hits in 6.4 sec

Towards a Framework for Safety Assurance of Autonomous Systems

John McDermid, Yan Jia, Ibrahim Habli
2019 International Joint Conference on Artificial Intelligence  
This paper discusses the challenges of safety assurance of autonomous systems and proposes a novel framework for safety assurance that, inter alia, uses machine learning to provide evidence for a system  ...  However, they also pose problems for safety assurance, whether fully autonomous or remotely operated (semi-autonomous).  ...  Acknowledgements This work was supported by the Assuring Autonomy International Programme.  ... 
dblp:conf/ijcai/McDermidJH19 fatcat:5zfjqsfiendqvbe3dcend7522m

Distributing Intelligence among Cloud, Fog and Edge in Industrial Cyber-physical Systems

Jonas Queiroz, Paulo Leitão, José Barbosa, Eugénio Oliveira
2019 Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics  
In this context, this work discusses the distribution of intelligence along Cloud, Fog and Edge computing layers in industrial CPS, leveraging some research challenges and future directions.  ...  However, this is not a straightforward task, posing several challenges and demanding new approaches and technologies.  ...  ACKNOWLEDGEMENTS This work is part of the GO0D MAN project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement N o 723764.  ... 
doi:10.5220/0007979404470454 dblp:conf/icinco/QueirozLBO19 fatcat:xryk5kmlwba5jebcdfsxgqesai

Using Formal Methods for Autonomous Systems: Five Recipes for Formal Verification [article]

Matt Luckcuck
2021 arXiv   pre-print
Formal Methods are mathematically-based techniques for software design and engineering, which enable the unambiguous description of and reasoning about a system's behaviour.  ...  The recipes are examples of how Formal Methods can be an effective tool for the development and verification of autonomous systems.  ...  Both of these elements pose challenges for verification. Autonomy can be implemented using, broadly, two different styles of Artificial Intelligence (AI): symbolic and sub-symbolic.  ... 
arXiv:2012.00856v2 fatcat:hatdgqwbabbfdbngmjt4q2rroi

Enabling Trustworthiness in Artificial Intelligence - A Detailed Discussion

Siddhartha Vadlamudi, Vintech Solutions
2015 Engineering International  
We further draw on these five standards to build up a data-driven analysis for TAI and present its application by portraying productive paths for future research, especially as to the distributed ledger  ...  With this article, we aim to present the idea of TAI and its five essential standards (1) usefulness, (2) non-maleficence, (3) autonomy, (4) justice, and (5) logic.  ...  Another challenge for trustworthy AI is that AI is portable across various fields all over the world.  ... 
doi:10.18034/ei.v3i2.519 fatcat:x77yracvqvbzpni43oipu3hzgu

The Societal Implications of Deep Reinforcement Learning

Jess Whittlestone, Kai Arulkumaran, Matthew Crosby
2021 The Journal of Artificial Intelligence Research  
potential for real-world application.  ...  Deep Reinforcement Learning (DRL) is an avenue of research in Artificial Intelligence (AI) that has received increasing attention within the research community in recent years, and is beginning to show  ...  for helpful discussions and comments.  ... 
doi:10.1613/jair.1.12360 fatcat:bkyc75ipfzd67govvztfvsd6oi

Safe AI – How is this Possible? [article]

Harald Rueß, Simon Burton
2022 arXiv   pre-print
We outline some of underlying challenges of safe AI and suggest a rigorous engineering framework for minimizing uncertainty, thereby increasing confidence, up to tolerable levels, in the safe behavior  ...  of AI systems.  ...  on challenging real-world AI systems.  ... 
arXiv:2201.10436v2 fatcat:lu5ibn3qc5hormd4w6zjmszplq

Toward verified artificial intelligence

Sanjit A. Seshia, Dorsa Sadigh, S. Shankar Sastry
2022 Communications of the ACM  
Making AI more trustworthy with a formal methods-based approach to AI system verification and validation.  ...  Acknowledgments Our work has been supported in part by the National Science Foundation (NSF), the Defense Advanced Research Projects Agency (DARPA), the Semiconductor Research Corporation (SRC), and several  ...  We gratefully acknowledge the many people with whom our conversations and collaborations have helped shape this article.  ... 
doi:10.1145/3503914 fatcat:ggc543oemfah3mboiftldvotuq

Enhanced Manufacturing Execution System "MES" Through a Smart Vision System [chapter]

Chawki El Zant, Quentin Charrier, Khaled Benfriha, Patrick Le Men
2021 Lecture Notes in Mechanical Engineering  
This smart CPS represents the 1st level of calculation and analysis in real time due to embedded intelligence.  ...  This novel technological brick, combined with the flexibility of production, contributes to optimizing the system in terms of autonomy and responsiveness to detect anomalies, already encountered, or even  ...  the effectiveness of using ML to assure in real time visual inspection and rapid decision-making process.  ... 
doi:10.1007/978-3-030-70566-4_52 fatcat:o7nj7qrmqzhnfaeqydlrktpada

Sense–Assess–eXplain (SAX): Building Trust in Autonomous Vehicles in Challenging Real-World Driving Scenarios

Matthew Gadd, Daniele de Martini, Letizia Marchegiani, Paul Newman, Lars Kunze
2020 2020 IEEE Intelligent Vehicles Symposium (IV)  
This paper discusses ongoing work in demonstrating research in mobile autonomy in challenging driving scenarios.  ...  In our approach, we address fundamental technical issues to overcome critical barriers to assurance and regulation for largescale deployments of autonomous systems.  ...  ACKNOWLEDGMENTS This work was supported by the Assuring Autonomy International Programme, a partnership between Lloyd's Register Foundation and the University of York.  ... 
doi:10.1109/iv47402.2020.9304819 fatcat:ztj5y5yk55cfxkin2yvacx6lbm

Sense-Assess-eXplain (SAX): Building Trust in Autonomous Vehicles in Challenging Real-World Driving Scenarios [article]

Matthew Gadd, Daniele De Martini, Letizia Marchegiani, Paul Newman, Lars Kunze
2020 arXiv   pre-print
This paper discusses ongoing work in demonstrating research in mobile autonomy in challenging driving scenarios.  ...  In our approach, we address fundamental technical issues to overcome critical barriers to assurance and regulation for large-scale deployments of autonomous systems.  ...  ACKNOWLEDGMENTS This work was supported by the Assuring Autonomy International Programme, a partnership between Lloyd's Register Foundation and the University of York.  ... 
arXiv:2005.02031v1 fatcat:ji6j6kbpgjeutixtdve3ptgn6q

An Explainable Artificial Intelligence (xAI) Framework for Improving Trust in Automated ATM Tools

Carolina Sanchez Hernandez, Samuel Ayo, Dimitrios Panagiotakopoulos
2021 2021 IEEE/AIAA 40th Digital Avionics Systems Conference (DASC)  
Although there is a wide amount of research on the technologies themselves, there seem to be a gap between research projects and practical implementation due to different regulatory and practical challenges  ...  including the need for transparency and explainability of solutions.  ...  ACKNOWLEDGMENTS This work has been completed as part of the Future of Flight UK challenge sponsored by the UK Research and Innovation.  ... 
doi:10.1109/dasc52595.2021.9594341 fatcat:y5rr3bjpbfgdhejzet3jtfzz2a

Achieving a trusted, reliable, AI-ready infrastructure for military medicine and civilian trauma care

Cindy Crump, Loretta M. Schlachta-Fairchild, Tien Pham, Latasha Solomon, Katie Rainey
2020 Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II  
Achieving a trusted, reliable, AI-ready infrastructure for military medicine and civilian care," Proc.  ...  Drivers towards greater use of Artificial Intelligence (AI) and Medical Autonomy to solve anticipated gaps in forward resuscitative and stabilization care, as well as associated relevance and implications  ...  an event will happen, or autonomously providing medical care in the same way that AI/ML can assist in navigating challenging terrain for the first time.  ... 
doi:10.1117/12.2557514 fatcat:tky5lww5g5f6lhfnwmljxwdq54

Towards Verified Artificial Intelligence [article]

Sanjit A. Seshia, Dorsa Sadigh, S. Shankar Sastry
2020 arXiv   pre-print
This paper considers Verified AI from a formal methods perspective. We describe five challenges for achieving Verified AI, and five corresponding principles for addressing these challenges.  ...  Verified artificial intelligence (AI) is the goal of designing AI-based systems that that have strong, ideally provable, assurances of correctness with respect to mathematically-specified requirements.  ...  and Assured Autonomy programs, by Toyota under the iCyPhy center, and by Berkeley Deep Drive.  ... 
arXiv:1606.08514v4 fatcat:ozoldsdnzjghddhwz5xju6zqvu

Guest Editors' Introduction: Special Issue on Autonomous Systems Design

Selma Saidi, Dirk Ziegenbein, Jyotirmoy V. Deshmukh, Rolf Ernst
2022 IEEE design & test  
In "Real-Time Requirements for ADAS Platforms Featuring Shared Memory Hierarchies," a team of researchers from the University of Modena and Reggio Emilia led by Marko Bertogna address nonfunctional properties  ...  Dirk Ziegenbein is a Chief Expert for open con- text systems engineering and leads a research group developing methods and technologies for software systems engineering at Bosch Corporate Research, Stuttgart  ... 
doi:10.1109/mdat.2021.3104818 fatcat:dwrrt7eidrbf5ae3vztu7zdesq

RELIABILITY RESEARCH ROADMAPPING WORKSHOP: IMPLICATIONS FOR ENGINEERING DESIGN

F. Campean, D. Delaux, S. Sharma, J. Bridges
2020 Proceedings of the Design Society: DESIGN Conference  
and research gaps and to define directions for future research and skills development.  ...  This paper presents the outcomes of an European Reliability Research Roadmapping workshop, collating the views of automotive, aerospace and defence industries to identify current reliability challenges  ...  Right first time through design -summary of challenges and research directions Industry challenges Research directions Methods for risk assessment in early design Develop model-based methods and tools  ... 
doi:10.1017/dsd.2020.337 fatcat:t6a67zdizfernk3rxmat3eu734
« Previous Showing results 1 — 15 out of 8,578 results