pith. sign in

arxiv: 2509.00319 · v1 · pith:N4SCLOSWnew · submitted 2025-08-30 · 💻 cs.RO · cs.AI· cs.SY· eess.SY

Contact-Aided Navigation of Flexible Robotic Endoscope Using Deep Reinforcement Learning in Dynamic Stomach

classification 💻 cs.RO cs.AIcs.SYeess.SY
keywords navigationstomachdynamicsuccesschallengingcontactcontact-aideddeep
0
0 comments X
read the original abstract

Navigating a flexible robotic endoscope (FRE) through the gastrointestinal tract is critical for surgical diagnosis and treatment. However, navigation in the dynamic stomach is particularly challenging because the FRE must learn to effectively use contact with the deformable stomach walls to reach target locations. To address this, we introduce a deep reinforcement learning (DRL) based Contact-Aided Navigation (CAN) strategy for FREs, leveraging contact force feedback to enhance motion stability and navigation precision. The training environment is established using a physics-based finite element method (FEM) simulation of a deformable stomach. Trained with the Proximal Policy Optimization (PPO) algorithm, our approach achieves high navigation success rates (within 3 mm error between the FRE's end-effector and target) and significantly outperforms baseline policies. In both static and dynamic stomach environments, the CAN agent achieved a 100% success rate with 1.6 mm average error, and it maintained an 85% success rate in challenging unseen scenarios with stronger external disturbances. These results validate that the DRL-based CAN strategy substantially enhances FRE navigation performance over prior methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BiliVLA: Scene-Aware Vision-Language-Action Model with Reinforcement Learning for Autonomous Biliary Endoscopic Navigation

    cs.RO 2026-06 unverdicted novelty 6.0

    BiliVLA reports 91.96% average action precision and 84.85% success rate on three ERCP subtasks in phantom experiments by combining scene-aware supervision, safety-aware recovery, and two-stage SFT+GRPO training.

  2. BiliVLA: Scene-Aware Vision-Language-Action Model with Reinforcement Learning for Autonomous Biliary Endoscopic Navigation

    cs.RO 2026-06 unverdicted novelty 5.0

    BiliVLA applies scene-aware VLA with grounding-enhanced SFT and GRPO to achieve 91.96% action precision and 84.85% success rate across three ERCP subtasks in phantom experiments.