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

Resources

• Download Paper (PDF)
• Code on GitHub
• Other Work

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 8.02mm and a Security Score of 0.862, demonstrating performance comparable to human experts. The code will be publicly available once this paper is published. https://tokymin.github.io/hirde.index.

Results

This study addresses the challenges of safe and efficient navigation in automated robotic digestive endoscopy (RDE) within the unstructured and narrow confines of the digestive tract. We proposed a human intervention-based PPO framework by incorporating expert knowledge to address the safety and effectiveness of RDE. Experiments have shown that HI-PPO can safely guide RDE compared to existing RL algorithms, indicating its potential for more practical application. Future work will focus on validating the framework in real environments and exploring additional methods to further enhance its safety and practicality.