Filters








41 Hits in 4.7 sec

Formal verification of ACAS X, an industrial airborne collision avoidance system

Jean-Baptiste Jeannin, Khalil Ghorbal, Yanni Kouskoulas, Ryan Gardner, Aurora Schmidt, Erik Zawadzki, Andre Platzer
2015 2015 International Conference on Embedded Software (EMSOFT)  
In this paper we present an overview of our experience using hybrid systems theorem proving to formally verify ACAS X, an airborne collision avoidance system for airliners scheduled to be operational around  ...  Formal verification of industrial systems is very challenging, due to reasons ranging from scalability issues to communication difficulties with engineering-focused teams.  ...  on all large passenger aircraft and whose design started in the late 1970s; and the Next-Generation Airborne Collision Avoidance System (ACAS X) [3, 6, 11] , a complete redesign of the TCAS system initiated  ... 
doi:10.1109/emsoft.2015.7318268 dblp:conf/emsoft/JeanninGKGSZP15 fatcat:nwijf4yhbzd6hhb5wtpek3umx4

A Formally Verified Hybrid System for the Next-Generation Airborne Collision Avoidance System [chapter]

Jean-Baptiste Jeannin, Khalil Ghorbal, Yanni Kouskoulas, Ryan Gardner, Aurora Schmidt, Erik Zawadzki, André Platzer
2015 Lecture Notes in Computer Science  
The next-generation Airborne Collision Avoidance System (ACAS X) is intended to be installed on all large aircraft to give advice to pilots and prevent mid-air collisions with other aircraft.  ...  how formal, hybrid approaches are helping ensure the safety of ACAS X.  ...  Lab at Carnegie Mellon University, and the ACAS X development team for interesting discussions and remarks.  ... 
doi:10.1007/978-3-662-46681-0_2 fatcat:xcxy3phwznho7dg27xrckmb6je

A formally verified hybrid system for safe advisories in the next-generation airborne collision avoidance system

Jean-Baptiste Jeannin, Khalil Ghorbal, Yanni Kouskoulas, Aurora Schmidt, Ryan Gardner, Stefan Mitsch, André Platzer
2016 International Journal on Software Tools for Technology Transfer (STTT)  
Airborne Collision Avoidance System ACAS X In order to prevent an NMAC with other aircraft, ACAS X uses various sensors to determine the position of the ownship, as well as the positions of any intruders  ...  Our approach of formally deriving safe regions then comparing them to the behavior of an industrial system is, as far as we are aware, the first of its kind in the formal verification of hybrid systems  ... 
doi:10.1007/s10009-016-0434-1 fatcat:fuv2hpxotzgkfohnetf7bd3eui

Formal Methods for the Certification of Autonomous Unmanned Aircraft Systems [chapter]

Matt Webster, Michael Fisher, Neil Cameron, Mike Jump
2011 Lecture Notes in Computer Science  
In this paper we assess the feasibility of using formal methods, and model checking in particular, for the certification of Unmanned Aircraft Systems (UAS) within civil airspace.  ...  We begin by modelling a basic UAS control system in PROMELA, and verify it against a selected subset of the CAA's Rules of the Air using the SPIN model checker.  ...  Acknowledgements The authors would like to thank Charles Patchett and Ben Gorry of BAE Systems (Warton) for their guidance and support.  ... 
doi:10.1007/978-3-642-24270-0_17 fatcat:7z6hlcpiwraijhu4qio7uyt5by

Airborne Separation Assurance Systems: towards a work programme to prove safety

Peter Brooker
2004 Safety Science  
ISBN 1 861940 91 2] "Content is a glimpse of something, an encounter like a flash. It is very tinyvery tiny, content." Attributed to Willem de Kooning.  ...  I would like to thank SRG staff and Ian Parker of National Air Traffic Services Ltd (NATS) for their comments on earlier drafts, and the referees for their cogent criticisms.  ...  The other processes by which the flight crews avoid collisions also contribute to reducing the risk of collision, but they do so in an unquantified way…The use of ACAS does not amount to separation provision  ... 
doi:10.1016/j.ssci.2003.12.002 fatcat:5rllbibj2jhtzfyyvlaeudpmbe

Free Flight Collision Risk Estimation by Sequential MC Simulation [chapter]

Henk Blom, Jaroslav Krystul, (Bert) Bakker, Margriet Klompstra, Bart Klein Obbink
2006 Automation and Control Engineering  
The authors thank Mariken Everdij (NLR) for valuable discussions and a thorough review of a draft version of this chapter.  ...  , does not yet incorporate other relevant agents such as Airborne Collision Avoidance System (ACAS), Airline Operations Centre (AOC), Air Traffic Control (ATC), or an environmental model.  ...  (FMS) flight plan -Airborne Global Positioning System (GPS) receiver -Airborne Inertial Reference System (IRS) -Altimeter -Horizontal position processing -Vertical position processing -ADS-B transmission  ... 
doi:10.1201/9781420008548.ch10 fatcat:pnochdve3rhqjdihlrfuj75b5a

Some recent advances in automated analysis

Erika Ábrahám, Klaus Havelund
2015 International Journal on Software Tools for Technology Transfer (STTT)  
Analysis of Systems (TACAS 2014).  ...  Due to the increasing complexity of software systems, there is a growing need for automated and scalable software synthesis and analysis.  ...  We are grateful to all authors for their contributions and to the reviewers of TACAS'14 and of this special issue for their thorough and valuable work.  ... 
doi:10.1007/s10009-015-0403-0 fatcat:hwu7b64kh5brrlm7spzyucxibe

A Review of Formal Methods applied to Machine Learning [article]

Caterina Urban, Antoine Miné
2021 arXiv   pre-print
We review state-of-the-art formal methods applied to the emerging field of the verification of machine learning systems.  ...  Finally, we offer perspectives for future research directions towards the formal verification of machine learning systems.  ...  The approach is applied to the verification of the ACAS Xu neural networks [90] , developed as early prototype for the next-generation airborne collision avoidance system for unmanned aircraft.  ... 
arXiv:2104.02466v2 fatcat:6ghs5huoynbc5h7lndajmsoxyu

Fast Falsification of Neural Networks using Property Directed Testing [article]

Moumita Das, Rajarshi Ray, Swarup Kumar Mohalik, Ansuman Banerjee
2021 arXiv   pre-print
We evaluate our algorithm on 45 trained neural network benchmarks of the ACAS Xu system against 10 safety properties.  ...  As an alternative to exhaustive and costly verification algorithms, lightweight falsification algorithms have been heavily used to search for an input to the system that produces an unsafe output, i.e.  ...  ACAS Xu Benchmarks Airborne Collision Avoidance System X Unmanned (ACAS Xu) is a set of neural network verification benchmarks [15] which are designed to avoid midair collisions of aircrafts by issuing  ... 
arXiv:2104.12418v1 fatcat:zboahpeum5faxowurhtf6rz3im

Welcome to the 38th Digital Avionics Sysytems Conference

2019 2019 IEEE/AIAA 38th Digital Avionics Systems Conference (DASC)  
This year's award is given to the Airborne Collision Avoidance System X (ACAS X) team with lead members Mykel Kochenderfer of Stanford University, James Kuchar and Wes Olson of MIT Lincoln Laboratory,  ...  The award citation reads "for the development of the Airborne Collision Avoidance System X using machine learning technology, statistical risk assessment and flight test campaigns."  ... 
doi:10.1109/dasc43569.2019.9081627 fatcat:nrfjjbdp55fojlk3nvquoq7f3a

Visual Detection of Small Unmanned Aircraft System: Modeling the Limits of Human Pilots

Gregory Stephen Woo, Dothang Truong, Woojin Choi
2020 Journal of Intelligent and Robotic Systems  
It provides a new tool for studying the difficult task of visually detecting airborne, small, unmanned aircraft targets in time to maneuver clear of a possible collision with them.  ...  Since small, unmanned aircraft continue to appear in v airspace where they do not belong, regulators and the industry need to accelerate the development and deployment of alternative methods for collision  ...  the ability of an observer to detect an airborne target.  ... 
doi:10.1007/s10846-020-01152-w fatcat:yesnqnsumbffbn35yfwreeuhxi

Architectural Design of a Safe Mission Manager for Unmanned Aircraft Systems

Hector Usach, Juan A. Vila, Christoph Torens, Florian Adolf
2018 Journal of systems architecture  
It integrates all the onboard sensors and information sources with a stochastic estimator to obtain an accurate and reliable estima-of a new Airborne Collision Avoidance System (ACAS) based on new logics  ...  , namely ACAS X.  ...  Another example is the Airborne Collision Avoidance subsystem (ACAS), which is able to detect collision threats autonomously.  ... 
doi:10.1016/j.sysarc.2018.09.003 fatcat:ijiasocshrfkpnu3ctuofd723y

Efficient Verification of ReLU-Based Neural Networks via Dependency Analysis

Elena Botoeva, Panagiotis Kouvaros, Jan Kronqvist, Alessio Lomuscio, Ruth Misener
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We present Venus, the resulting verification toolkit, and evaluate it on the ACAS collision avoidance networks and models trained on the MNIST and CIFAR-10 datasets.  ...  We introduce an efficient method for the verification of ReLU-based feed-forward neural networks.  ...  We used the most commonly used benchmarks in the context of FFNNs verification: ACAS Xu (Julian et al. 2016 ) comprises 45 ReLU-based FFNNs, which were developed as part of an airborne collision avoidance  ... 
doi:10.1609/aaai.v34i04.5729 fatcat:jsmbgbtofrcitnl4uhipew5qza

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review [article]

Florian Tambon, Gabriel Laberge, Le An, Amin Nikanjam, Paulina Stevia Nouwou Mindom, Yann Pequignot, Foutse Khomh, Giulio Antoniol, Ettore Merlo, François Laviolette
2021 arXiv   pre-print
In total, we identified 217 papers covering topics considered to be the main pillars of ML certification: Robustness, Uncertainty, Explainability, Verification, Safe Reinforcement Learning, and Direct  ...  It also emphasized the need to further develop connections between academia and industries to deepen the domain study.  ...  Many thanks also goes to Freddy Lécué from Thalès, who provided us feedback on an early version of this manuscript. They all contributed to improving this SLR.  ... 
arXiv:2107.12045v3 fatcat:43vqxywawbeflhs6ehzovvsevm

Machine Learning and Cognitive Ergonomics in Air Traffic Management: Recent Developments and Considerations for Certification

Trevor Kistan, Alessandro Gardi, Roberto Sabatini
2018 Aerospace (Basel)  
aspects of vendor verification, regulatory certification, and end-user acceptance.  ...  By considering a novel cognitive human–machine interface (HMI), configured via machine learning, we examined the requirements for such techniques to be deployed operationally in an ATM system, exploring  ...  The Federal Aviation Administration (FAA) is currently working on its successor, the airborne collision avoidance system (ACAS Xa).  ... 
doi:10.3390/aerospace5040103 fatcat:vjyg3cwkyrag7p35olkyzf4i74
« Previous Showing results 1 — 15 out of 41 results