Lapgym: an open source framework for reinforcement learning in robot-assisted laparoscopic surgery

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 sk...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Scheikl, Paul Maria (VerfasserIn) , Gyenes, Balácz (VerfasserIn) , Younis, Rayan (VerfasserIn) , Haas, Christoph (VerfasserIn) , Neumann, Gerhard (VerfasserIn) , Wagner, Martin (VerfasserIn) , Mathis-Ullrich, Franziska (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 12/23
In: Journal of machine learning research
Year: 2023, Jahrgang: 24, Pages: 1-43
ISSN:1533-7928
Online-Zugang:Verlag, kostenfrei, Volltext: https://dl.acm.org/doi/pdf/10.5555/3648699.3649067
Verlag, kostenfrei, Volltext: https://jmlr.org/papers/v24/23-0207.html
Volltext
Verfasserangaben:Paul Maria Scheikl, Balázs Gyenes, Rayan Younis, Christoph Haas, Gerhard Neumann, Martin Wagner, Franziska Mathis-Ullrich

MARC

LEADER 00000caa a2200000 c 4500
001 1896451896
003 DE-627
005 20241205154505.0
007 cr uuu---uuuuu
008 240725s2023 xx |||||o 00| ||eng c
035 |a (DE-627)1896451896 
035 |a (DE-599)KXP1896451896 
035 |a (OCoLC)1475304301 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Scheikl, Paul Maria  |e VerfasserIn  |0 (DE-588)1302319159  |0 (DE-627)1859352022  |4 aut 
245 1 0 |a Lapgym  |b an open source framework for reinforcement learning in robot-assisted laparoscopic surgery  |c Paul Maria Scheikl, Balázs Gyenes, Rayan Younis, Christoph Haas, Gerhard Neumann, Martin Wagner, Franziska Mathis-Ullrich 
264 1 |c 12/23 
300 |b Illustrationen, Diagramme 
300 |a 43 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Online veröffentlicht: 12/23 
500 |a Gesehen am 25.07.2024 
520 |a 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 
700 1 |a Gyenes, Balácz  |e VerfasserIn  |4 aut 
700 1 |a Younis, Rayan  |e VerfasserIn  |0 (DE-588)1322594686  |0 (DE-627)1882526449  |4 aut 
700 1 |a Haas, Christoph  |e VerfasserIn  |4 aut 
700 1 |a Neumann, Gerhard  |e VerfasserIn  |4 aut 
700 1 |a Wagner, Martin  |d 1988-  |e VerfasserIn  |0 (DE-588)1060231980  |0 (DE-627)799324337  |0 (DE-576)416324282  |4 aut 
700 1 |a Mathis-Ullrich, Franziska  |d 1987-  |e VerfasserIn  |0 (DE-588)112418614X  |0 (DE-627)877887276  |0 (DE-576)482386347  |4 aut 
773 0 8 |i Enthalten in  |t Journal of machine learning research  |d Brookline, MA : Microtome Publishing, 2001  |g 24(2023), Artikel-ID 368, Seite 1-43  |h Online-Ressource  |w (DE-627)327304472  |w (DE-600)2042762-1  |w (DE-576)112815766  |x 1533-7928  |7 nnas  |a Lapgym an open source framework for reinforcement learning in robot-assisted laparoscopic surgery 
773 1 8 |g volume:24  |g year:2023  |g elocationid:368  |g pages:1-43  |g extent:43  |a Lapgym an open source framework for reinforcement learning in robot-assisted laparoscopic surgery 
856 4 0 |u https://dl.acm.org/doi/pdf/10.5555/3648699.3649067  |x Verlag  |z kostenfrei  |3 Volltext 
856 4 0 |u https://jmlr.org/papers/v24/23-0207.html  |x Verlag  |z kostenfrei  |3 Volltext 
951 |a AR 
992 |a 20240725 
993 |a Article 
994 |a 2023 
998 |g 1060231980  |a Wagner, Martin  |m 1060231980:Wagner, Martin  |d 50000  |e 50000PW1060231980  |k 0/50000/  |p 6 
998 |g 1322594686  |a Younis, Rayan  |m 1322594686:Younis, Rayan  |d 50000  |e 50000PY1322594686  |k 0/50000/  |p 3 
998 |g 1302319159  |a Scheikl, Paul Maria  |m 1302319159:Scheikl, Paul Maria  |d 50000  |e 50000PS1302319159  |k 0/50000/  |p 3 
999 |a KXP-PPN1896451896  |e 4557194834 
BIB |a Y 
SER |a journal 
JSO |a {"title":[{"title_sort":"Lapgym","title":"Lapgym","subtitle":"an open source framework for reinforcement learning in robot-assisted laparoscopic surgery"}],"language":["eng"],"id":{"eki":["1896451896"]},"physDesc":[{"noteIll":"Illustrationen, Diagramme","extent":"43 S."}],"relHost":[{"title":[{"subtitle":"JMLR","title":"Journal of machine learning research","title_sort":"Journal of machine learning research"}],"part":{"volume":"24","year":"2023","text":"24(2023), Artikel-ID 368, Seite 1-43","pages":"1-43","extent":"43"},"language":["eng"],"pubHistory":["1.2001 -"],"recId":"327304472","origin":[{"publisherPlace":"Brookline, MA ; New York, NY ; Cambridge, Mass.","publisher":"Microtome Publishing ; Association for Computing Machinery ; MIT Press","dateIssuedDisp":"2001-","dateIssuedKey":"2001"}],"titleAlt":[{"title":"JMLR"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"disp":"Lapgym an open source framework for reinforcement learning in robot-assisted laparoscopic surgeryJournal of machine learning research","physDesc":[{"extent":"Online-Ressource"}],"id":{"zdb":["2042762-1"],"issn":["1533-7928"],"eki":["327304472"]},"note":["Gesehen am 14.06.2023","Fortsetzung der Druck-Ausgabe"]}],"note":["Online veröffentlicht: 12/23","Gesehen am 25.07.2024"],"recId":"1896451896","origin":[{"dateIssuedKey":"2023","dateIssuedDisp":"12/23"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"person":[{"family":"Scheikl","given":"Paul Maria","role":"aut","display":"Scheikl, Paul Maria"},{"role":"aut","given":"Balácz","display":"Gyenes, Balácz","family":"Gyenes"},{"family":"Younis","display":"Younis, Rayan","role":"aut","given":"Rayan"},{"family":"Haas","role":"aut","given":"Christoph","display":"Haas, Christoph"},{"family":"Neumann","role":"aut","given":"Gerhard","display":"Neumann, Gerhard"},{"family":"Wagner","display":"Wagner, Martin","role":"aut","given":"Martin"},{"family":"Mathis-Ullrich","given":"Franziska","role":"aut","display":"Mathis-Ullrich, Franziska"}],"name":{"displayForm":["Paul Maria Scheikl, Balázs Gyenes, Rayan Younis, Christoph Haas, Gerhard Neumann, Martin Wagner, Franziska Mathis-Ullrich"]}} 
SRT |a SCHEIKLPAULAPGYM1223