Learning to Navigate Endoscopic Capsule Robots

摘要

Deep reinforcement learning (DRL) techniques have been successful in several domains, such as physical simulations, computer games, and simulated robotic tasks, yet the transfer of these successful learning concepts from simulations into the real world scenarios remains still a challenge. In this letter, a DRL approach is proposed to learn the continuous control of a magnetically actuated soft capsule endoscope (MASCE). Proposed controller approach can alleviate the need for tedious modeling of complex and highly nonlinear physical phenomena, such as magnetic interactions, robot body dynamics and tissue-robot interactions. Experiments performed in real ex-vivo porcine stomachs prove the successful control of the MASCE with trajectory tracking errors on the order of millimeter.