Towards Data-Driven Model-Free Safety-Critical Control

2025-06-07

AI Summary

Model-free control barrier functions (CBFs) for robotic safe velocity control suffer from manual tuning of parameters—e.g., the decay rate α—due to unknown exponential convergence rates of embedded velocity controllers. Method: We propose a data-driven, probabilistic CBF framework that learns a Lyapunov function via neural networks and employs the Chernoff bound to estimate a confidence upper bound on the decay rate, thereby establishing the first probabilistic safety condition with explicit confidence guarantees. The resulting model-free CBF requires no system dynamics knowledge and ensures probabilistic safety. Contribution/Results: Our approach eliminates the need for prior knowledge of the decay rate and manual parameter tuning, significantly enhancing robustness and safety under uncertainty. Extensive experiments on a UR5e robot across multiple scenarios validate the method’s effectiveness, hardware compatibility, and generalization capability.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Intelligent Robots: State Estimation
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper presents a framework for enabling safe velocity control of general robotic systems using data-driven model-free Control Barrier Functions (CBFs). Model-free CBFs rely on an exponentially stable velocity controller and a design parameter (e.g. alpha in CBFs); this design parameter depends on the exponential decay rate of the controller. However, in practice, the decay rate is often unavailable, making it non-trivial to use model-free CBFs, as it requires manual tuning for alpha. To address this, a Neural Network is used to learn the Lyapunov function from data, and the maximum decay rate of the systems built-in velocity controller is subsequently estimated. Furthermore, to integrate the estimated decay rate with model-free CBFs, we derive a probabilistic safety condition that incorporates a confidence bound on the violation rate of the exponential stability condition, using Chernoff bound. This enhances robustness against uncertainties in stability violations. The proposed framework has been tested on a UR5e robot in multiple experimental settings, and its effectiveness in ensuring safe velocity control with model-free CBFs has been demonstrated.

Problem

• Enabling safe velocity control for robots without system models
• Estimating decay rates for model-free Control Barrier Functions
• Ensuring robust safety with probabilistic stability conditions

Innovation

• Neural Network learns Lyapunov function from data
• Estimates maximum decay rate of velocity controller
• Derives probabilistic safety condition using Chernoff bound