Data-Driven Safety Filter: An Input-Output Perspective

TL;DR

This paper introduces a Data-Driven Safety Filter (DDSF) based on Behavioral System Theory that ensures safety in learning-based control without explicit models, using only offline data and input-output information.

Contribution

It presents a novel safety filter that guarantees safety for learning algorithms without requiring state estimation or explicit models, applicable to systems with delays and uncertainties.

Findings

Successfully applied to a 6-DOF aerial robot in simulation

Effective in systems with unknown time delays

Ensures safety without explicit prediction models

Abstract

Implementation of learning-based control remains challenging due to the absence of safety guarantees. Safe control methods have turned to model-based safety filters to address these challenges, but this is paradoxical when the ultimate goal is a model-free, data-driven control solution. Addressing the core question of "Can we ensure the safety of any learning-based algorithm without explicit prediction models and state estimation?" this paper proposes a Data-Driven Safety Filter (DDSF) grounded in Behavioral System Theory (BST). The proposed method needs only a single system trajectory available in an offline dataset to modify unsafe learning inputs to safe inputs. This contribution addresses safe control in the input-output framework and therefore does not require full state measurements or explicit state estimation. Since no explicit model is required, the proposed safe control solution is not affected by unmodeled dynamics and unstructured uncertainty and can provide a safe solution for systems with unknown time delays. The effectiveness of the proposed DDSF is illustrated in simulation for a high-order six-degree-of-freedom aerial robot and a time-delay adaptive cruise control system.