Bayesian Meta-Learning on Control Barrier Functions with Data from On-Board Sensors

TL;DR

This paper introduces a Bayesian meta-learning approach to quickly adapt control barrier functions for safe robot navigation in unknown environments using sensor data, enabling efficient online control synthesis with probabilistic safety guarantees.

Contribution

It proposes a novel Bayesian meta-learning framework for CBFs that adapts rapidly to new environments with limited data, improving generalization and re-synthesis efficiency.

Findings

Efficient online synthesis of safe controllers demonstrated in simulations.

Provides probabilistic safety guarantees for the learned controllers.

Enhances adaptability of CBFs to diverse environments.

Abstract

In this paper, we consider a way to safely navigate the robots in unknown environments using measurement data from sensory devices. The control barrier function (CBF) is one of the promising approaches to encode safety requirements of the system and the recent progress on learning-based approaches for CBF realizes online synthesis of CBF-based safe controllers with sensor measurements. However, the existing methods are inefficient in the sense that the trained CBF cannot be generalized to different environments and the re-synthesis of the controller is necessary when changes in the environment occur. Thus, this paper considers a way to learn CBF that can quickly adapt to a new environment with few amount of data by utilizing the currently developed Bayesian meta-learning framework. The proposed scheme realizes efficient online synthesis of the controller as shown in the simulation study and provides probabilistic safety guarantees on the resulting controller.