Recurrent Neural Network Controllers for Signal Temporal Logic Specifications Subject to Safety Constraints
This work addresses control synthesis for systems with temporal logic and safety constraints, which is incremental as it combines existing RNN and CBF methods.
The authors tackled the problem of synthesizing control strategies for discrete-time systems under Signal Temporal Logic (STL) specifications with safety constraints, using Recurrent Neural Networks (RNNs) to predict policies and Control Barrier Functions (CBFs) to ensure safety, and validated the approach through simulations.
We propose a framework based on Recurrent Neural Networks (RNNs) to determine an optimal control strategy for a discrete-time system that is required to satisfy specifications given as Signal Temporal Logic (STL) formulae. RNNs can store information of a system over time, thus, enable us to determine satisfaction of the dynamic temporal requirements specified in STL formulae. Given a STL formula, a dataset of satisfying system executions and corresponding control policies, we can use RNNs to predict a control policy at each time based on the current and previous states of system. We use Control Barrier Functions (CBFs) to guarantee the safety of the predicted control policy. We validate our theoretical formulation and demonstrate its performance in an optimal control problem subject to partially unknown safety constraints through simulations.