Filters








128 Hits in 4.8 sec

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)  
To meet these new requirements, the FAA has decided to develop a new system: the Next-Generation Airborne Collision Avoidance System, known as ACAS X [4, 11, 15] .  ...  Airspace management will evolve significantly over the next decade with the introduction of the next-generation air traffic management system; this will create new requirements for collision avoidance.  ... 
doi:10.1007/s10009-016-0434-1 fatcat:fuv2hpxotzgkfohnetf7bd3eui

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  
In this paper we determine the geometric configurations under which the advice given by ACAS X is safe under a precise set of assumptions and formally verify these configurations using hybrid systems theorem  ...  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.  ...  , Neal Suchy, the Logical Systems 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

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  ...  More importantly, industrial systems are rarely designed for verification, but rather for operational needs.  ...  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

Generating probabilistic safety guarantees for neural network controllers

Sydney M. Katz, Kyle D. Julian, Christopher A. Strong, Mykel J. Kochenderfer
2021 Machine Learning  
We show that our method is able to generate meaningful probabilistic safety guarantees for aircraft collision avoidance neural networks that are loosely inspired by Airborne Collision Avoidance System  ...  X (ACAS X), a family of collision avoidance systems that formulates the problem as a partially observable Markov decision process (POMDP).  ...  Neural networks have been demonstrated as space-efficient controllers for a family of aircraft collision avoidance systems called the Airborne Collision Avoidance System X (ACAS X) (Julian et al., 2016  ... 
doi:10.1007/s10994-021-06065-9 fatcat:pqtuywwhenga5lvqzavd4nmhb4

Compositional Verification for Autonomous Systems with Deep Learning Components [article]

Corina S. Pasareanu, Divya Gopinath, Huafeng Yu
2018 arXiv   pre-print
We present a compositional approach for the scalable, formal verification of autonomous systems that contain Deep Neural Network components.  ...  As autonomy becomes prevalent in many applications, ranging from recommendation systems to fully autonomous vehicles, there is an increased need to provide safety guarantees for such systems.  ...  In [9] we applied the technique on the MNIST dataset [16] and on a neural network implementation of a controller for the next-generation Airborne Collision Avoidance System for unmanned aircraft (ACAS  ... 
arXiv:1810.08303v1 fatcat:ebmnxm2az5frrirb4zlzefllau

Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning

Ritchie Lee, Ole J. Mengshoel, Anshu Saksena, Ryan W. Gardner, Daniel Genin, Joshua Silbermann, Michael Owen, Mykel J. Kochenderfer
2020 The Journal of Artificial Intelligence Research  
We demonstrate the effectiveness of the approach on an aircraft collision avoidance application, where a prototype aircraft collision avoidance system is stress tested to find the most likely scenarios  ...  Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems  ...  The next-generation Airborne Collision Avoidance System (ACAS X) was created promising a number of improvements over TCAS including a reduction in collision risk while simultaneously reducing the number  ... 
doi:10.1613/jair.1.12190 fatcat:oxeeuyfcujdwznwxxseoas5cym

Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning [article]

Ritchie Lee, Ole J. Mengshoel, Anshu Saksena, Ryan Gardner, Daniel Genin, Joshua Silbermann, Michael Owen, Mykel J. Kochenderfer
2020 arXiv   pre-print
We demonstrate the effectiveness of the approach on an aircraft collision avoidance application, where a prototype aircraft collision avoidance system is stress tested to find the most likely scenarios  ...  Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems  ...  We demonstrate the effectiveness of AST and DAST for stress testing the next-generation Airborne Collision Avoidance System (ACAS X) (Kochenderfer et al., 2012) .  ... 
arXiv:1811.02188v3 fatcat:e2shtxom4vayfcmcyxtslfocby

Coloured Petri net-based traffic collision avoidance system encounter model for the analysis of potential induced collisions

Jun Tang, Miquel Angel Piera, Toni Guasch
2016 Transportation Research Part C: Emerging Technologies  
In this paper, an encounter model is formalised to identify all of the potential collision scenarios that can be induced by a resolution advisory that was generated previously by the TCAS without considering  ...  The Traffic Alert and Collision Avoidance System (TCAS) is a world-wide accepted lastresort means of reducing the probability and frequency of mid-air collisions between aircraft.  ...  Acknowledgment This research is partially supported by the Ministry of Economy and Competitiveness in the project "Fire Guided Unmanned Aircrafts and Resources Distribution-2 (Fire GUARD)", MINECO Spanish  ... 
doi:10.1016/j.trc.2016.03.001 fatcat:qdeb2vala5gnrpzkiai6u3wsym

Aviation safety

Neha Rungta, Guillaume Brat, William J. Clancey, Charlotte Linde, Franco Raimondi, Chin Seah, Michael Shafto
2013 Proceedings of the 3rd International Conference on Application and Theory of Automation in Command and Control Systems - ATACCS '13  
The on-going transformation from the current US Air Traffic System (ATS) to the Next Generation Air Traffic System (NextGen) will force the introduction of new automated systems and most likely will cause  ...  In this work, we present a verification approach based both on simulations and on model checking for evaluating the roles and responsibilities of humans and automation.  ...  We thank Ron van Hoof providing support for the Brahms simulation system.  ... 
doi:10.1145/2494493.2494498 dblp:conf/atacss/RungtaBCLRSS13 fatcat:c5w66cjwt5fwbaz3ymp3ujn7gq

A Fuzzy Logic Approach for Separation Assurance and Collision Avoidance for Unmanned Aerial Systems [chapter]

Brandon Cook, Tim Arnett, Kelly Cohen
2017 Modern Fuzzy Control Systems and Its Applications  
The avoidance logic was verified using formal methods and shown to select the correct action in all instances.  ...  Numerical testing demonstrated that the avoidance system was able to prevent a mid-air collision between two sUAS in all tested cases.  ...  In order to generate scenarios to test the sUAS's ability to avoid collisions, a realistic simulation environment was created.  ... 
doi:10.5772/68126 fatcat:wehvcrbcrzc4xmjgvsd4ainz4y

Self-Repairing Neural Networks: Provable Safety for Deep Networks via Dynamic Repair [article]

Klas Leino, Aymeric Fromherz, Ravi Mangal, Matt Fredrikson, Bryan Parno, Corina Păsăreanu
2021 arXiv   pre-print
Safe ordering properties relate requirements on the ordering of a network's output indices to conditions on their input, and are sufficient to express most useful notions of non-relational safety for classifiers  ...  We compose this layer with an existing network to construct a self-repairing network (SR-Net), and show that in addition to providing safe outputs, the SR-Net is guaranteed to preserve the accuracy of  ...  ACKNOWLEDGMENTS This material is based upon work supported by the Software Engineering Institute under its FFRDC Contract No. FA8702-15-D-0002 with the U.S.  ... 
arXiv:2107.11445v1 fatcat:6ppligqyqfh6fjnmw6gzl3245e

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks [chapter]

Guy Katz, Clark Barrett, David L. Dill, Kyle Julian, Mykel J. Kochenderfer
2017 Lecture Notes in Computer Science  
We evaluated our technique on a prototype deep neural network implementation of the next-generation airborne collision avoidance system for unmanned aircraft (ACAS Xu).  ...  However, a major obstacle in applying them to safety-critical systems is the great difficulty in providing formal guarantees about their behavior.  ...  We thank Neal Suchy from the Federal Aviation Administration, Lindsey Kuper from Intel and Tim King from Google for their valuable comments and support.  ... 
doi:10.1007/978-3-319-63387-9_5 fatcat:hxcg5htpxbecxeod2266awksju

Safety Verification of Neural Network Controlled Systems [article]

Arthur Clavière, Eric Asselin, Christophe Garion
2020 arXiv   pre-print
In this paper, we propose a system-level approach for verifying the safety of neural network controlled systems, combining a continuous-time physical system with a discrete-time neural network based controller  ...  We assume a generic model for the controller that can capture both simple and complex behaviours involving neural networks.  ...  For this purpose, the standardization group RTCA SC 147 [22] has recently developped a dedicated controller, namely the Airborne Collision Avoidance System for Unmanned Aircraft (ACAS Xu).  ... 
arXiv:2011.05174v1 fatcat:3spgdx5sszedtjvwxokuqiyime

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks [article]

Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer
2017 arXiv   pre-print
We evaluated our technique on a prototype deep neural network implementation of the next-generation airborne collision avoidance system for unmanned aircraft (ACAS Xu).  ...  However, a major obstacle in applying them to safety-critical systems is the great difficulty in providing formal guarantees about their behavior.  ...  Case Study: The ACAS Xu System Airborne collision avoidance systems are critical for ensuring the safe operation of aircraft.  ... 
arXiv:1702.01135v2 fatcat:y5hvnhyy2zfbjc5e4voergl2eq

Towards a framework for certification of reliable autonomous systems

Michael Fisher, Viviana Mascardi, Kristin Yvonne Rozier, Bernd-Holger Schlingloff, Michael Winikoff, Neil Yorke-Smith
2020 Autonomous Agents and Multi-Agent Systems  
We here analyse what is needed in order to provide verified reliable behaviour of an autonomous system, analyse what can be done as the state-of-the-art in automated verification, and propose a roadmap  ...  However, regulators grapple with how to deal with autonomous systems, for example how could we certify an Unmanned Aerial System for autonomous use in civilian airspace?  ...  Acknowledgements We thank the organisers and participants of the Dagstuhl 19112 workshop, and the anonymous reviewers of this article. Thanks to Simone Ancona for the drawings in Sect. 1.  ... 
doi:10.1007/s10458-020-09487-2 fatcat:gd6urk3nbrcwxkpffdtdpa5xha
« Previous Showing results 1 — 15 out of 128 results