Neural Controller Synthesis for Signal Temporal Logic Specifications Using Encoder-Decoder Structured Networks

TL;DR

This paper introduces a neural network control synthesis method for signal temporal logic specifications using encoder-decoder architectures with attention, enabling flexible handling of various STL formulas without retraining.

Contribution

It proposes a novel encoder-decoder neural network framework with attention for STL control synthesis, allowing generalization across different specifications.

Findings

Encoder-decoder NNs effectively synthesize control signals for STL specifications.

Three NN structures (sequential, tree, graph) are compared and evaluated.

Numerical experiments demonstrate improved control performance and flexibility.

Abstract

In this paper, we propose a control synthesis method for signal temporal logic (STL) specifications with neural networks (NNs). Most of the previous works consider training a controller for only a given STL specification. These approaches, however, require retraining the NN controller if a new specification arises and needs to be satisfied, which results in large consumption of memory and inefficient training. To tackle this problem, we propose to construct NN controllers by introducing encoder-decoder structured NNs with an attention mechanism. The encoder takes an STL formula as input and encodes it into an appropriate vector, and the decoder outputs control signals that will meet the given specification. As the encoder, we consider three NN structures: sequential, tree-structured, and graph-structured NNs. All the model parameters are trained in an end-to-end manner to maximize the expected robustness that is known to be a quantitative semantics of STL formulae. We compare the control performances attained by the above NN structures through a numerical experiment of the path planning problem, showing the efficacy of the proposed approach.