| Online-Ressource |
Verfasst von: | Scheikl, Paul Maria [VerfasserIn]  |
| Gyenes, Balácz [VerfasserIn]  |
| Younis, Rayan [VerfasserIn]  |
| Haas, Christoph [VerfasserIn]  |
| Neumann, Gerhard [VerfasserIn]  |
| Wagner, Martin [VerfasserIn]  |
| Ullrich, Franziska [VerfasserIn]  |
Titel: | Lapgym |
Titelzusatz: | an open source framework for reinforcement learning in robot-assisted laparoscopic surgery |
Verf.angabe: | Paul Maria Scheikl, Balázs Gyenes, Rayan Younis, Christoph Haas, Gerhard Neumann, Martin Wagner, Franziska Mathis-Ullrich |
E-Jahr: | 2023 |
Jahr: | 12/23 |
Umfang: | 43 S. |
Illustrationen: | Illustrationen, Diagramme |
Fussnoten: | Online veröffentlicht: 12/23 ; Gesehen am 25.07.2024 |
Titel Quelle: | Enthalten in: Journal of machine learning research |
Ort Quelle: | Brookline, MA : Microtome Publishing, 2001 |
Jahr Quelle: | 2023 |
Band/Heft Quelle: | 24(2023), Artikel-ID 368, Seite 1-43 |
ISSN Quelle: | 1533-7928 |
Abstract: | Recent advances in reinforcement learning (RL) have increased the promise of introduc ing 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 frame work 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 explor ing 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 |
URL: | Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.
kostenfrei: Volltext: https://dl.acm.org/doi/pdf/10.5555/3648699.3649067 |
| kostenfrei: Volltext: https://jmlr.org/papers/v24/23-0207.html |
Datenträger: | Online-Ressource |
Sprache: | eng |
K10plus-PPN: | 1896451896 |
Verknüpfungen: | → Zeitschrift |