SymAR: Symmetry Abstractions and Refinement for Accelerating Scenarios with Neural Network Controllers Verification

We present a Symmetry-based abstraction refinement algorithm SymAR that is directed towards safety verification of large-scale scenarios with complex dynamical systems. The abstraction maps modes with symmetric dynamics to a single abstract mode and refinements recursively split the modes when safety checks fail. We show how symmetry abstractions can be applied effectively to closed-loop control systems, including non-symmetric deep neural network (DNN) controllers. For such controllers, we transform their inputs and outputs to enforce symmetry and make the closed loop system amenable for abstraction. We implemented SymAR in Python and used it to verify paths with 100s of segments in 2D and 3D scenarios followed by a six dimensional DNN-controlled quadrotor, and also a ground vehicle. Our experiments show significant savings, up to 10x in some cases, in verification time over existing methods.

[1]  Matthias Althoff,et al.  An Introduction to CORA 2015 , 2015, ARCH@CPSWeek.

[2]  Mahesh Viswanathan,et al.  Automatic Reachability Analysis for Nonlinear Hybrid Models with C2E2 , 2016, CAV.

[3]  Sayan Mitra,et al.  Symmetry Abstractions for Hybrid Systems and their Applications , 2020, ArXiv.

[4]  Thomas A. Henzinger,et al.  The theory of hybrid automata , 1996, Proceedings 11th Annual IEEE Symposium on Logic in Computer Science.

[5]  Mahesh Viswanathan,et al.  Meeting a Powertrain Verification Challenge , 2015, CAV.

[6]  J. Slotine,et al.  Symmetries, stability, and control in nonlinear systems and networks. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  Xin Chen,et al.  Flow*: An Analyzer for Non-linear Hybrid Systems , 2013, CAV.

[8]  Weiming Xiang,et al.  NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems , 2020, CAV.

[9]  Sayan Mitra,et al.  A verification framework for hybrid systems , 2007 .

[10]  Ashish Tiwari,et al.  Sherlock - A tool for verification of neural network feedback systems: demo abstract , 2019, HSCC.

[11]  Insup Lee,et al.  Verisig: verifying safety properties of hybrid systems with neural network controllers , 2018, HSCC.

[12]  Mahesh Viswanathan,et al.  Statistical Verification of the Toyota Powertrain Control Verification Benchmark , 2017, HSCC.

[13]  Antoine Girard,et al.  SpaceEx: Scalable Verification of Hybrid Systems , 2011, CAV.

[14]  Christel Baier,et al.  Proceedings of the 21st International Conference on Tools and Algorithms for the Construction and Analysis of Systems - Volume 9035 , 2015 .

[15]  Xin Chen,et al.  Flow* 1.2: More Effective to Play with Hybrid Systems , 2015, ARCH@CPSWeek.

[16]  S. LaValle.  Rapidly-exploring random trees : a new tool for path planning , 1998 .

[17]  Chuchu Fan,et al.  Fast and Guaranteed Safe Controller Synthesis for Nonlinear Vehicle Models , 2020, CAV.

[18]  Thomas A. Henzinger,et al.  Hybrid Automata: An Algorithmic Approach to the Specification and Verification of Hybrid Systems , 1992, Hybrid Systems.

[19]  Mahesh Viswanathan,et al.  DryVR: Data-Driven Verification and Compositional Reasoning for Automotive Systems , 2017, CAV.

[20]  Stanley Bak,et al.  HyLAA: A Tool for Computing Simulation-Equivalent Reachability for Linear Systems , 2017, HSCC.

[21]  Mahesh Viswanathan,et al.  C2E2: A Verification Tool for Stateflow Models , 2015, TACAS.

[22]  Nancy A. Lynch,et al.  The Theory of Timed I/o Automata , 2003 .