STLCG++: A Masking Approach for Differentiable Signal Temporal Logic Specification

TL;DR

STLCG++ introduces a parallelized, masking-based method for evaluating and differentiating Signal Temporal Logic robustness, significantly accelerating computations and enabling broader gradient-based optimization in robotics.

Contribution

The paper presents STLCG++, a novel masking approach that speeds up STL robustness evaluation and differentiability, with added smoothing for interval bounds, enhancing robotics applications.

Findings

Over 1000x faster robustness computation than recurrent methods

Enables differentiation of time interval bounds for spatial-temporal optimization

Demonstrates effectiveness in three robotics use cases

Abstract

Signal Temporal Logic (STL) offers a concise yet expressive framework for specifying and reasoning about spatio-temporal behaviors of robotic systems. Attractively, STL admits the notion of robustness, the degree to which an input signal satisfies or violates an STL specification, thus providing a nuanced evaluation of system performance. In particular, the differentiability of STL robustness enables direct integration to robotic workflows that rely on gradient-based optimization, such as trajectory optimization and deep learning. However, existing approaches to evaluating and differentiating STL robustness rely on recurrent computations, which become inefficient with longer sequences, limiting their use in time-sensitive applications. In this paper, we present STLCG++, a masking-based approach that parallelizes STL robustness evaluation and backpropagation across timesteps, \revised{achieving more than 1000$\times$ faster computation time than the recurrent approach (STLCG++).}{achieving significant speed-ups compared to a recurrent approach.} We also introduce a smoothing technique to enable the differentiation of time interval bounds, thereby expanding STL's applicability in gradient-based optimization tasks involving spatial and temporal variables. Finally, we demonstrate STLCG++'s benefits through three robotics use cases and provide JAX and PyTorch libraries for seamless integration into modern robotics workflows. Project website with demo and code: https://uw-ctrl.github.io/stlcg/.