Anatomical Landmark-Guided Deep Reinforcement Learning for Autonomous Gastric Navigation
This work addresses the problem of incomplete mucosal coverage and poor transferability of navigation methods in wireless capsule endoscopy, offering a practical solution for autonomous gastric navigation.
The paper proposes an anatomical landmark-guided deep reinforcement learning framework for autonomous gastric navigation in wireless capsule endoscopy, achieving over 97% coverage in simulations and 87% coverage in ex-vivo experiments with a 53% reduction in procedure time compared to expert manual control.
Wireless capsule endoscopy (WCE) enables painless visualization of the gastrointestinal tract, but its diagnostic potential is limited by incomplete mucosal coverage and poor transferability of existing navigation methods across patient anatomies. We propose a transferable, anatomical landmarkguided deep reinforcement learning (AL-DRL) framework for autonomous gastric navigation. Leveraging a lightweight edgecontour-depth fusion module, our policy operates on stable, lowdimensional landmark coordinates rather than high-dimensional video streams, effectively bridging the sim-to-real gap. In simulations across eight patient-derived models, the method achieves over 97% coverage within 50 seconds, significantly outperforming vanilla PPO, SAC, and DQN agents. A two-stage sim-to-real pipeline with an adaptive dynamic programming controller actively mitigates physical disturbances. Ex-vivo experiments demonstrate a mean coverage of 87% and a 53% reduction in procedure time compared with expert manual control.