Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot

TL;DR

This paper introduces DEX, a demonstration-guided reinforcement learning algorithm that enhances exploration efficiency and success rates in surgical robot automation by effectively utilizing expert demonstrations, validated through simulation and real robot experiments.

Contribution

The paper presents a novel RL method that leverages expert demonstrations with higher value estimation and non-parametric regression to improve exploration in surgical automation tasks.

Findings

Significant improvement in exploration efficiency and success rates in simulation tasks.

Effective transfer of learned policies from simulation to real surgical robot.

Demonstrated robustness across 10 diverse surgical manipulation tasks.

Abstract

Task automation of surgical robot has the potentials to improve surgical efficiency. Recent reinforcement learning (RL) based approaches provide scalable solutions to surgical automation, but typically require extensive data collection to solve a task if no prior knowledge is given. This issue is known as the exploration challenge, which can be alleviated by providing expert demonstrations to an RL agent. Yet, how to make effective use of demonstration data to improve exploration efficiency still remains an open challenge. In this work, we introduce Demonstration-guided EXploration (DEX), an efficient reinforcement learning algorithm that aims to overcome the exploration problem with expert demonstrations for surgical automation. To effectively exploit demonstrations, our method estimates expert-like behaviors with higher values to facilitate productive interactions, and adopts non-parametric regression to enable such guidance at states unobserved in demonstration data. Extensive experiments on $10$ surgical manipulation tasks from SurRoL, a comprehensive surgical simulation platform, demonstrate significant improvements in the exploration efficiency and task success rates of our method. Moreover, we also deploy the learned policies to the da Vinci Research Kit (dVRK) platform to show the effectiveness on the real robot. Code is available at https://github.com/med-air/DEX.