{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T12:46:39Z","timestamp":1775825199356,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636175","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"4025-4031","source":"Crossref","is-referenced-by-count":35,"title":["Safe Reinforcement Learning using Formal Verification for Tissue Retraction in Autonomous Robotic-Assisted Surgery"],"prefix":"10.1109","author":[{"given":"Ameya","family":"Pore","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Corsi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Marchesini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Dall'Alba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alicia","family":"Casals","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro","family":"Farinelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Fiorini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","author":"moore","year":"1963","journal-title":"Interval arithmetic and automatic error analysis in digital computing"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref10","article-title":"A generalized algorithm for multi-objective reinforcement learning and policy adaptation","author":"yang","year":"2019","journal-title":"NeurIPS"},{"key":"ref11","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"ray","year":"2019","journal-title":"OpenAir"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970659"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509607"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SAMI.2018.8323986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989275"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794159"},{"key":"ref17","article-title":"Toward synergic learning for autonomous manipulation of deformable tissues via surgical robots: An approximate q-learning approach","author":"pedram","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196912"},{"key":"ref28","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SYSCON.2019.8836924"},{"key":"ref27","article-title":"Efficient formal safety analysis of neural networks","author":"wang","year":"2018","journal-title":"Conference on Neural Information Processing Systems"},{"key":"ref3","article-title":"Open-sourced reinforcement learning environments for surgical robotics","author":"richter","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196739"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341710"},{"key":"ref7","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013914"},{"key":"ref9","article-title":"Algorithms for verifying deep neural networks","author":"liu","year":"2019","journal-title":"Foundations and Trends in Optimization"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.surge.2013.06.004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2020.00062"},{"key":"ref24","article-title":"Interval arithmetic and automatic error analysis in digital computing","author":"moore","year":"1963","journal-title":"Stanford University"},{"key":"ref23","article-title":"Certifying some distributional robustness with principled adversarial training","author":"sinha","year":"2018"},{"key":"ref26","article-title":"Towards fast computation of certified robustness for relu networks","author":"weng","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref25","article-title":"Formal verification of neural networks for safety-critical tasks in deep reinforcement learning","author":"corsi","year":"2021","journal-title":"Conference on Uncertainty in Artificial Intelligence (UAI)"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636175.pdf?arnumber=9636175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:41Z","timestamp":1652201681000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636175","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}