Learning from Demonstrations for Autonomous Soft-tissue Retraction

TL;DR

This paper introduces a GAIL-based Learning from Demonstrations approach for autonomous soft-tissue retraction in robotic surgery, achieving human-like behavior with fewer demonstrations and successful transfer to real robots.

Contribution

It presents a novel GAIL-based LfD method within a DRL framework for surgical tasks, improving sample efficiency and generalization over existing approaches.

Findings

The method achieves human-like tissue retraction behavior.

It requires fewer demonstrations than baseline methods.

Policies transfer successfully from simulation to real robot.

Abstract

The current research focus in Robot-Assisted Minimally Invasive Surgery (RAMIS) is directed towards increasing the level of robot autonomy, to place surgeons in a supervisory position. Although Learning from Demonstrations (LfD) approaches are among the preferred ways for an autonomous surgical system to learn expert gestures, they require a high number of demonstrations and show poor generalization to the variable conditions of the surgical environment. In this work, we propose an LfD methodology based on Generative Adversarial Imitation Learning (GAIL) that is built on a Deep Reinforcement Learning (DRL) setting. GAIL combines generative adversarial networks to learn the distribution of expert trajectories with a DRL setting to ensure generalisation of trajectories providing human-like behaviour. We consider automation of tissue retraction, a common RAMIS task that involves soft tissues manipulation to expose a region of interest. In our proposed methodology, a small set of expert trajectories can be acquired through the da Vinci Research Kit (dVRK) and used to train the proposed LfD method inside a simulated environment. Results indicate that our methodology can accomplish the tissue retraction task with human-like behaviour while being more sample-efficient than the baseline DRL method. Towards the end, we show that the learnt policies can be successfully transferred to the real robotic platform and deployed for soft tissue retraction on a synthetic phantom.