Surgical Gym: A high-performance GPU-based platform for reinforcement learning with surgical robots
Preprint
Abstract
Recent advances in robot-assisted surgery have resulted in progressively more precise, efficient, and minimally invasive procedures, sparking a new era of robotic surgical intervention. This enables doctors, in collaborative interaction with robots, to perform traditional or minimally invasive surgeries with improved outcomes through smaller incisions. Recent efforts are working toward making robotic surgery more autonomous which has the potential to reduce variability of surgical outcomes and reduce complication rates. Deep reinforcement learning methodologies offer scalable solutions for surgical automation, but their effectiveness relies on extensive data acquisition due to the absence of prior knowledge in successfully accomplishing tasks. Due to the intensive nature of simulated data collection, previous works have focused on making existing algorithms more efficient. In this work, we focus on making the simulator more efficient, making training data much more accessible than previously possible. We introduce Surgical Gym, an open-source high performance platform for surgical robot learning where both the physics simulation and reinforcement learning occur directly on the GPU. We demonstrate between 100-5000x faster training times compared with previous surgical learning platforms. The code is available at: https://github.com/SamuelSchmidgall/SurgicalGym.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot2023
- Sim-to-Real Surgical Robot Learning and Autonomous Planning for Internal Tissue Points Manipulation Using Reinforcement LearningIEEE Robotics and Automation Letters, 2023
- Sim-to-Real Transfer for Visual Reinforcement Learning of Deformable Object Manipulation for Robot-Assisted SurgeryIEEE Robotics and Automation Letters, 2022
- Control of Magnetic Surgical Robots With Model-Based Simulators and Reinforcement LearningIEEE Transactions on Medical Robotics and Bionics, 2022
- Toward Synergic Learning for Autonomous Manipulation of Deformable Tissues via Surgical Robots: An Approximate Q-Learning Approach2020
- SuPer: A Surgical Perception Framework for Endoscopic Tissue Manipulation With Surgical RoboticsIEEE Robotics and Automation Letters, 2020
- Learning to Navigate Endoscopic Capsule RobotsIEEE Robotics and Automation Letters, 2019
- Autonomy for Surgical Robots: Concepts and ParadigmsIEEE Transactions on Medical Robotics and Bionics, 2019
- Smart Tissue Anastomosis Robot (STAR): A Vision-Guided Robotics System for Laparoscopic SuturingIEEE Transactions on Biomedical Engineering, 2014
- Development of a colon endoscope robot that adjusts its locomotion through the use of reinforcement learningInternational Journal of Computer Assisted Radiology and Surgery, 2010