Problem
Research questions and friction points this paper is trying to address.
backup-based safety filters
Control Barrier Functions
Model Predictive Shielding
gatekeeper
safety verification
Backup-Based Safety Filters: A Comparative Review of Backup CBF, Model Predictive Shielding, and gatekeeper
🤖 AI Summary
This work addresses the lack of a unified comparative framework among existing backup safety filter methods—such as Backup Control Barrier Functions (Backup CBFs), Model Predictive Shielding (MPS), and Gatekeeper—which has led to ambiguous theoretical connections. The paper introduces a common abstraction and shared notation to systematically analyze the structural, algorithmic, and inactivity set characteristics of these three approaches. Its key contribution lies in demonstrating that MPS is a special case of Gatekeeper and in establishing an intrinsic relationship between the inactivity sets of Gatekeeper and Backup CBFs. This analysis clarifies the source of conservatism inherent in safety assessments based on backup maneuver feasibility. By integrating control barrier functions, model predictive shielding, and set-theoretic reasoning, the study provides a coherent theoretical foundation and practical design guidance for safe reinforcement learning and autonomous systems.
📝 Abstract
This paper revisits three backup-based safety filters -- Backup Control Barrier Functions (Backup CBF), Model Predictive Shielding (MPS), and gatekeeper -- through a unified comparative framework. Using a common safety-filter abstraction and shared notation, we make explicit both their common backup-policy structure and their key algorithmic differences. We compare the three methods through their filter-inactive sets, i.e., the states where the nominal policy is left unchanged. In particular, we show that MPS is a special case of gatekeeper, and we further relate gatekeeper to the interior of the Backup CBF inactive set within the implicit safe set. This unified view also highlights a key source of conservatism in backup-based safety filters: safety is often evaluated through the feasibility of a backup maneuver, rather than through the nominal policy's continued safe execution. The paper is intended as a compact tutorial and review that clarifies the theoretical connections and differences among these methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
backup-based safety filters
Control Barrier Functions
Model Predictive Shielding
gatekeeper
safety verification
🔎 Similar Papers
No similar papers found.
