| Presentation | 2020-03-10 Temporal Logic Falsification for Simulink models based on the hybrid robustness using ChainerRL Ryota Owaki, Shoji Yuen, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We present a method of falsification for the hybrid property of Simulink model using deep reinforcement learning. This study realizes falsification based on hybrid robustness reflecting the dependence between continuous variables and discrete variables. We propose hybrid robustness reflecting discrete robustness by updating continuous variables. Reward values derived from such robustness are expected to be effective for stable convergence so thatthe number of simulations is reduced. This paper provides an experimental implementation of falsification using Python’s reinforcement learning library ChainerRL in Simulink. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Simulink / hybrid robustness / Falsification / Reinforcement Learning |
| Paper # | MSS2019-67 |
| Date of Issue | 2020-03-02 (MSS) |
| Conference Information | |
| Committee | MSS / NLP |
|---|---|
| Conference Date | 2020/3/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | SICE-DES, IEICE-MSS, IEICE-NLP |
| Chair | Shigemasa Takai(Osaka Univ.) / Hiroaki Kurokawa(Tokyo Univ. of Tech.) |
| Vice Chair | Atsuo Ozaki(Osaka Inst. of Tech.) / Kiyohisa Natsume(Kyushu Inst. of Tech.) |
| Secretary | Atsuo Ozaki(Osaka Univ.) / Kiyohisa Natsume(Hokkaido Univ.) |
| Assistant | Naoki Hayashi(Osaka Univ.) / Yutaka Shimada(Saitama Univ.) / Toshikaza Samura(Yamaguchi Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Mathematical Systems Science and its applications / Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Temporal Logic Falsification for Simulink models based on the hybrid robustness using ChainerRL |
| Sub Title (in English) | |
| Keyword(1) | Simulink |
| Keyword(2) | hybrid robustness |
| Keyword(3) | Falsification |
| Keyword(4) | Reinforcement Learning |
| 1st Author's Name | Ryota Owaki |
| 1st Author's Affiliation | Nagoya University(NU) |
| 2nd Author's Name | Shoji Yuen |
| 2nd Author's Affiliation | Nagoya University(NU) |
| Date | 2020-03-10 |
| Paper # | MSS2019-67 |
| Volume (vol) | vol.119 |
| Number (no) | MSS-470 |
| Page | pp.pp.53-58(MSS), |
| #Pages | 6 |
| Date of Issue | 2020-03-02 (MSS) |