Learning to Navigate Endoscopic Capsule Robots

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 study, 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 modelling of complex and highly non-linear physical phenomena such as magnetic interactions, robot body dynamics and tissuerobot 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.