Abstract
AbstractWe present , a tool that uses neural networks for predicting reachable sets from executions of a dynamical system. Unlike existing reachability tools, computes areachability functionthat outputs an accurate over-approximation of the reachable set foranyinitial set in a parameterized family. Such reachability functions are useful for online monitoring, verification, and safe planning. implements empirical risk minimization for learning reachability functions. We discuss the design rationale behind the optimization problem and establish that the computed output is probably approximately correct. Our experimental evaluations over a variety of systems show promise. can learn accurate reachability functions for complex nonlinear systems, including some that are beyond existing methods. From a learned reachability function, arbitrary reachtubes can be computed in milliseconds. is available athttps://github.com/sundw2014/NeuReach.
Publisher
Springer International Publishing
Reference44 articles.
1. dReach. http://dreal.github.io/dReach/
2. Althoff, M., Grebenyuk, D.: Implementation of interval arithmetic in CORA 2016. In: Proc. of the 3rd International Workshop on Applied Verification for Continuous and Hybrid Systems. pp. 91–105 (2016)
3. Althoff, M., Grebenyuk, D., Kochdumper, N.: Implementation of Taylor models in cora 2018. In: Proc. of the 5th International Workshop on Applied Verification for Continuous and Hybrid Systems (2018). https://doi.org/10.29007/zzc7
4. Aylward, E.M., Parrilo, P.A., Slotine, J.J.E.: Stability and robustness analysis of nonlinear systems via contraction metrics and sos programming. Automatica 44(8), 2163–2170 (2008)
5. Bak, S., Duggirala, P.S.: Hylaa: A tool for computing simulation-equivalent reachability for linear systems. In: Proceedings of the 20th International Conference on Hybrid Systems: Computation and Control. pp. 173–178. ACM (2017)
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献