Title | ||
---|---|---|
Worst-case Satisfaction of STL Specifications Using Feedforward Neural Network Controllers: A Lagrange Multipliers Approach |
Abstract | ||
---|---|---|
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.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3358239 | ACM Transactions on Embedded Computing Systems (TECS) |
Keywords | Field | DocType |
Reinforcement learning, neural network controller, signal temporal logic | Feedforward neural network,Nonlinear system,Lagrange multiplier,Control theory,Computer science,Parallel computing,Robustness (computer science),Minification,Artificial neural network,Maximization,Reinforcement learning | Journal |
Volume | Issue | ISSN |
18 | 5s | 1539-9087 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shakiba Yaghoubi | 1 | 13 | 2.96 |
Georgios E. Fainekos | 2 | 804 | 52.65 |