Safe Navigation for Robotic Digestive Endoscopy via Human Intervention-based Reinforcement Learning

TL;DR

This paper introduces HI-PPO, a reinforcement learning framework that integrates human expertise to improve the safety and efficiency of robotic digestive endoscopy navigation in complex environments.

Contribution

The paper presents a novel HI-PPO framework combining human intervention with reinforcement learning to enhance safety in robotic endoscopy navigation.

Findings

HI-PPO achieves an average trajectory error of 8.02 mm.

HI-PPO attains a security score of 0.862.

Performance is comparable to human experts.

Abstract

With the increasing application of automated robotic digestive endoscopy (RDE), ensuring safe and efficient navigation in the unstructured and narrow digestive tract has become a critical challenge. Existing automated reinforcement learning navigation algorithms often result in potentially risky collisions due to the absence of essential human intervention, which significantly limits the safety and effectiveness of RDE in actual clinical practice. To address this limitation, we proposed a Human Intervention (HI)-based Proximal Policy Optimization (PPO) framework, dubbed HI-PPO, which incorporates expert knowledge to enhance RDE's safety. Specifically, HI-PPO combines Enhanced Exploration Mechanism (EEM), Reward-Penalty Adjustment (RPA), and Behavior Cloning Similarity (BCS) to address PPO's exploration inefficiencies for safe navigation in complex gastrointestinal environments. Comparative experiments were conducted on a simulation platform, and the results showed that HI-PPO achieved a mean ATE (Average Trajectory Error) of \(8.02\ \text{mm}\) and a Security Score of \(0.862\), demonstrating performance comparable to human experts. The code will be publicly available once this paper is published.