Worst-case Satisfaction of STL Specifications Using Feedforward Neural Network Controllers
| Autor: | Shakiba Yaghoubi, Georgios Fainekos |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
010506 paleontology
0209 industrial biotechnology Computer science 02 engineering and technology 01 natural sciences Computer Science::Robotics symbols.namesake 020901 industrial engineering & automation Control theory Robustness (computer science) 0202 electrical engineering electronic engineering information engineering Reinforcement learning 0601 history and archaeology 0105 earth and related environmental sciences 060102 archaeology Artificial neural network 06 humanities and the arts Maximization Nonlinear system Hardware and Architecture Lagrange multiplier symbols Feedforward neural network 020201 artificial intelligence & image processing Minification Software |
| Zdroj: | ITA |
| ISSN: | 1558-3465 1539-9087 |
| DOI: | 10.1145/3358239 |
| Popis: | In this paper, a reinforcement learning approach for designing feedback neural network controllers for nonlinear systems is proposed. Given a Signal Temporal Logic (STL) specification which needs to be satisfied by the system over a set of initial conditions, the neural network parameters are tuned in order to maximize the satisfaction of the STL formula. The framework is based on a max-min formulation of the robustness of the STL formula. The maximization is solved through a Lagrange multipliers method, while the minimization corresponds to a falsification problem. We present our results on a vehicle and a quadrotor model and demonstrate that our approach reduces the training time more than 50 percent compared to the baseline approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|