Learning to Navigate Endoscopic Capsule Robots

Mehmet Turan, Yasin Almalioglu, Hunter B. Gilbert, Faisal Mahmood, Nicholas J. Durr, Helder Araujo, Alp Eren Sarı, Anurag Ajay, Metin Sitti

Abstract:

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.