Constrained Reinforcement Learning and Formal Verification for Safe Colonoscopy Navigation

TL;DR

This paper introduces a safe and robust navigation strategy for robotic colonoscopy using constrained reinforcement learning and formal verification, eliminating lumen tracking and ensuring safety before deployment.

Contribution

It presents a novel combination of constrained reinforcement learning and formal verification for safe robotic colonoscopy navigation, which was not previously explored.

Findings

Out of 300 policies, 3 were verified as entirely safe.

The approach improves robustness and safety in virtual colonoscopy environments.

The method eliminates the need for lumen tracking in navigation.

Abstract

The field of robotic Flexible Endoscopes (FEs) has progressed significantly, offering a promising solution to reduce patient discomfort. However, the limited autonomy of most robotic FEs results in non-intuitive and challenging manoeuvres, constraining their application in clinical settings. While previous studies have employed lumen tracking for autonomous navigation, they fail to adapt to the presence of obstructions and sharp turns when the endoscope faces the colon wall. In this work, we propose a Deep Reinforcement Learning (DRL)-based navigation strategy that eliminates the need for lumen tracking. However, the use of DRL methods poses safety risks as they do not account for potential hazards associated with the actions taken. To ensure safety, we exploit a Constrained Reinforcement Learning (CRL) method to restrict the policy in a predefined safety regime. Moreover, we present a model selection strategy that utilises Formal Verification (FV) to choose a policy that is entirely safe before deployment. We validate our approach in a virtual colonoscopy environment and report that out of the 300 trained policies, we could identify three policies that are entirely safe. Our work demonstrates that CRL, combined with model selection through FV, can improve the robustness and safety of robotic behaviour in surgical applications.