Semi-Supervised Safe Visuomotor Policy Synthesis using Barrier Certificates

TL;DR

This paper introduces a semi-supervised approach for synthesizing safe visuomotor control policies in robotics, combining learning and control theory to ensure safety without extensive safety labels.

Contribution

It presents a novel barrier certificate-based framework that provides formal safety guarantees for visuomotor policies without needing complete safety labels.

Findings

Successfully applied to inverted pendulum system

Demonstrated obstacle avoidance in autonomous robot

Ensured safety guarantees with limited labels

Abstract

In modern robotics, addressing the lack of accurate state space information in real-world scenarios has led to a significant focus on utilizing visuomotor observation to provide safety assurances. Although supervised learning methods, such as imitation learning, have demonstrated potential in synthesizing control policies based on visuomotor observations, they require ground truth safety labels for the complete dataset and do not provide formal safety assurances. On the other hand, traditional control-theoretic methods like Control Barrier Functions (CBFs) and Hamilton-Jacobi (HJ) Reachability provide formal safety guarantees but depend on accurate knowledge of system dynamics, which is often unavailable for high-dimensional visuomotor data. To overcome these limitations, we propose a novel approach to synthesize a semi-supervised safe visuomotor policy using barrier certificates that integrate the strengths of model-free supervised learning and model-based control methods. This framework synthesizes a provably safe controller without requiring safety labels for the complete dataset and ensures completeness guarantees for both the barrier certificate and the policy. We validate our approach through distinct case studies: an inverted pendulum system and the obstacle avoidance of an autonomous mobile robot.