ASO Author Reflections: The Role of the Robot in Pancreatoduodenectomy

Machado, Marcel Autran; Makdissi, Fábio F.

doi:10.1245/s10434-021-09786-2

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motivation Robot-assisted laparoscopic surgery (RALS) is nowadays gold-standard and has proven benefits in prostate surgery (Sood et al, 2014;Stolzenburg et al, 2021). Because of its faster learning curve it became de facto standard of minimally invasive surgery for example in gynecology (Jørgensen et al, 2019) and advanced minimally invasive oncological visceral surgery (Machado and Makdissi, 2021). From a technical perspective, reinforcement learning (RL) has seen a rapid increase in research interest in the robotics community across a large range of applications such as legged locomotion and grasping (Ibarz et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

LapGym -- An Open Source Framework for Reinforcement Learning in Robot-Assisted Laparoscopic Surgery

Scheikl¹,

Gyenes²,

Younis³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent advances in reinforcement learning (RL) have increased the promise of introducing cognitive assistance and automation to robot-assisted laparoscopic surgery (RALS). However, progress in algorithms and methods depends on the availability of standardized learning environments that represent skills relevant to RALS. We present LapGym, a framework for building RL environments for RALS that models the challenges posed by surgical tasks, and sofa env, a diverse suite of 12 environments. Motivated by surgical training, these environments are organized into 4 tracks: Spatial Reasoning, Deformable Object Manipulation & Grasping, Dissection, and Thread Manipulation. Each environment is highly parametrizable for increasing difficulty, resulting in a high performance ceiling for new algorithms. We use Proximal Policy Optimization (PPO) to establish a baseline for model-free RL algorithms, investigating the effect of several environment parameters on task difficulty. Finally, we show that many environments and parameter configurations reflect well-known, open problems in RL research, allowing researchers to continue exploring these fundamental problems in a surgical context. We aim to provide a challenging, standard environment suite for further development of RL for RALS, ultimately helping to realize the full potential of cognitive surgical robotics. LapGym is publicly accessible through GitHub (https://github.com/ScheiklP/lap_gym).

show abstract