nncontroller swMATH ID: 39887 Software Authors: Zhao, Hengjun; Zeng, Xia; Chen, Taolue; Liu, Zhiming; Woodcock, Jim Description: Learning safe neural network controllers with barrier certificates. We provide a new approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier functions, which are represented by NNs as well. We train the controller-NN and barrier-NN simultaneously, achieving a verification-in-the-loop synthesis. We provide a prototype tool nncontroller with a number of case studies. The experiment results confirm the feasibility and efficacy of our approach. Homepage: https://link.springer.com/article/10.1007%2Fs00165-021-00544-5 Keywords: continuous dynamical systems; controller synthesis; neural networks; safety verification; barrier certificates Related Software: Reluplex; Spacer; CLN2INV; AI2; Adam; Sherlock; ReachNN; GitHub; PENBMI; Safety Gym; VERIFAI; NNV; HSolver; Benchmarks; RSOLVER Cited in: 4 Publications Standard Articles 1 Publication describing the Software, including 1 Publication in zbMATH Year Learning safe neural network controllers with barrier certificates. Zbl 07388000Zhao, Hengjun; Zeng, Xia; Chen, Taolue; Liu, Zhiming; Woodcock, Jim 2021 all top 5 Cited by 14 Authors 3 Liu, Zhiming 3 Zeng, Xia 2 Chen, Taolue 2 Woodcock, James C. P. 2 Zhao, Hengjun 1 Kobayashi, Naoki 1 Lin, Wang 1 Sato, Issei 1 Sekiyama, Taro 1 Tang, Xiaochao 1 Unno, Hiroshi 1 Yang, Zhengfeng 1 Zeng, Zhenbing 1 Zhang, Yidan Cited in 1 Serial 1 Formal Aspects of Computing Cited in 2 Fields 4 Computer science (68-XX) 2 Systems theory; control (93-XX) Citations by Year