ARCGym: Benchmarking Deep Reinforcement Learning in Autonomous Robotic Colonoscopy

Abstract:Simulations for learning-based autonomous colonoscopic navigation focus mainly on fully actuated capsule robots, failing to capture the contact-rich navigation of long and flexible clinical colonoscopes. We present the Autonomous Robotic Colonoscopy Gym (ARCGym), an open-source reinforcement learning environment and benchmark for image-based navigation in clinically derived deformable colon anatomies. ARCGym supports multiple types of colonoscope robots, spanning capsule robots and flexible endoscopes, with this work focusing on flexible endoscopes including magnetic-driven tip actuation and clinically used proximally translational actuation. This work includes five CT-reconstructed colons representing typical clinical scenarios, a set of clinically meaningful navigation subtasks, and unified success metrics. We introduce a reward combining depth-based lumen alignment with a lumen-visibility score to improve learning under occlusions. Experiments across tasks, robots, and anatomies show that autonomous navigation remains challenging for both magnetic-driven and proximal-insertion flexible robots, with proximal-insertion actuation remaining an open problem.

Robotics (cs.RO)

arXiv:2609.22803 [cs.RO]

(or arXiv:2609.22803v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.22803 arXiv-issued DOI via DataCite (pending registration)

G. Ji, M. Finocchiaro, K. Erleben, and H. Yin, "ARCGym: Benchmarking Deep Reinforcement Learning in Autonomous Robotic Colonoscopy," IEEE Robotics and Automation Letters, 2026

https://doi.org/10.1109/LRA.2026.3734868 DOI(s) linking to related resources