SYLGMar 29, 2021

Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networks

arXiv:2103.15938v311 citations
Originality Incremental advance
AI Analysis

This work addresses safety and efficiency in model-based control for systems with temporal logic constraints, representing an incremental improvement by integrating learned models with control barrier functions.

The authors tackled the problem of learning controllers from Signal Temporal Logic specifications for unknown affine control systems, achieving satisfaction of specifications within very few system runs and enabling on-line control.

We propose a policy search approach to learn controllers from specifications given as Signal Temporal Logic (STL) formulae. The system model, which is unknown but assumed to be an affine control system, is learned together with the control policy. The model is implemented as two feedforward neural networks (FNNs) - one for the drift, and one for the control directions. To capture the history dependency of STL specifications, we use a recurrent neural network (RNN) to implement the control policy. In contrast to prevalent model-free methods, the learning approach proposed here takes advantage of the learned model and is more efficient. We use control barrier functions (CBFs) with the learned model to improve the safety of the system. We validate our algorithm via simulations and experiments. The results show that our approach can satisfy the given specification within very few system runs, and can be used for on-line control.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes