{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:15:37Z","timestamp":1774455337493,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030938413","type":"print"},{"value":"9783030938420","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-93842-0_14","type":"book-chapter","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T18:25:30Z","timestamp":1641925530000},"page":"239-253","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MoveRL: To\u00a0a\u00a0Safer Robotic Reinforcement Learning Environment"],"prefix":"10.1007","author":[{"given":"Gaoyuan","family":"Liu","sequence":"first","affiliation":[]},{"given":"Joris","family":"De Winter","sequence":"additional","affiliation":[]},{"given":"Bram","family":"Vanderborght","sequence":"additional","affiliation":[]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]},{"given":"Denis","family":"Steckelmacher","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,11]]},"reference":[{"key":"14_CR1","unstructured":"Ahn, M., et al.: Robotics benchmarks for learning with low-cost robots. In: Conference on Robot Learning, pp. 1300\u20131313. PMLR (2020)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., et al.: Safe reinforcement learning via shielding. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"14_CR3","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"issue":"1","key":"14_CR4","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MRA.2011.2181749","volume":"19","author":"S Chitta","year":"2012","unstructured":"Chitta, S., Sucan, I., Cousins, S.: Moveit![ros topics]. IEEE Robot. Autom. Mag. 19(1), 18\u201319 (2012)","journal-title":"IEEE Robot. Autom. Mag."},{"key":"14_CR5","unstructured":"Dalal, G., Dvijotham, K., Vecerik, M., Hester, T., Paduraru, C., Tassa, Y.: Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757 (2018)"},{"key":"14_CR6","unstructured":"Delhaisse, B., Rozo, L., Caldwell, D.G.: Pyrobolearn: a python framework for robot learning practitioners. In :Conference on Robot Learning, pp. 1348\u20131358. PMLR (2020)"},{"key":"14_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/ACCESS.2014.2302442","volume":"2","author":"M Elbanhawi","year":"2014","unstructured":"Elbanhawi, M., Simic, M.: Sampling-based robot motion planning: a review. IEEE Access 2, 56\u201377 (2014)","journal-title":"IEEE Access"},{"key":"14_CR8","unstructured":"Fan, L., et al.: Surreal: open-source reinforcement learning framework and robot manipulation benchmark. In : Conference on Robot Learning, pp. 767\u2013782. PMLR (2018)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Ferigo, D., Traversaro, S., Metta, G., Pucci, D.: Gym-ignition: reproducible robotic simulations for reinforcement learning. In: 2020 IEEE\/SICE International Symposium on System Integration (SII), pp. 885\u2013890. IEEE (2020)","DOI":"10.1109\/SII46433.2020.9025951"},{"issue":"1","key":"14_CR10","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Grushko, S., et al.: Tuning perception and motion planning parameters for move it! Framework (2020)","DOI":"10.17973\/MMSJ.2020_11_2020064"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Hornung, A., Wurm, K.M., Bennewitz, M., Stachniss, C., Burgard, W.: Octomap: an efficient probabilistic 3d mapping framework based on octrees. Auton. Robot. 34(3), 189\u2013206 (2013)","DOI":"10.1007\/s10514-012-9321-0"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: Rlbench: the robot learning benchmark & learning environment. IEEE Robot. Autom. Lett. 5(2), 3019\u20133026 (2020)","DOI":"10.1109\/LRA.2020.2974707"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Kober, J., Bagnell, J.A., Peters. J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013)","DOI":"10.1177\/0278364913495721"},{"key":"14_CR15","unstructured":"Lopez, N.G., et al.: Gym-gazebo2, a toolkit for reinforcement learning using Ros 2 and gazebo. arXiv preprint arXiv:1903.06278 (2019)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Moll, M., Sucan, I.A., Kavraki, L.E.: Benchmarking motion planning algorithms: an extensible infrastructure for analysis and visualization. IEEE Robot. Autom. Mag. 22(3), 96\u2013102 (2015)","DOI":"10.1109\/MRA.2015.2448276"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Pan, J., Chitta, S., Manocha, D.: FCL: a general purpose library for collision and proximity queries. In: 2012 IEEE International Conference on Robotics and Automation, pp. 3859\u20133866. IEEE (2012)","DOI":"10.1109\/ICRA.2012.6225337"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Panerati, J., Zheng, H., Zhou, S., Xu, J., Prorok, A., Schoellig, A.P.: Learning to fly-a gym environment with pybullet physics for reinforcement learning of multi-agent quadcopter control. arXiv preprint arXiv:2103.02142 (2021)","DOI":"10.1109\/IROS51168.2021.9635857"},{"key":"14_CR19","doi-asserted-by":"publisher","unstructured":"Pecka, M., Svoboda, T.: Safe exploration techniques for reinforcement learning \u2013 an overview. In: Hodicky, J. (eds.) Modelling and Simulation for Autonomous Systems. MESAS 2014. LNCS, vol 8906, pp. 357\u2013375. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-13823-7_31s","DOI":"10.1007\/978-3-319-13823-7_31s"},{"key":"14_CR20","unstructured":"Plappert, M., et al.: Multi-goal reinforcement learning: challenging robotics environments and request for research. arXiv preprint arXiv:1802.09464 (2018)"},{"key":"14_CR21","unstructured":"Raffin, A., Hill, A., Ernestus, M., Gleave, A., Kanervisto, A., Dormann, A.: Stable baselines3. https:\/\/github.com\/DLR-RM\/stable-baselines3 (2019)"},{"key":"14_CR22","unstructured":"Ray, A., Achiam, J., Amodei, D.: Benchmarking safe exploration in deep reinforcement learning. arXiv preprint arXiv:1910.01708 (2019)"},{"key":"14_CR23","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Sucan, J.A., Moll, M., Kavraki, L.E.: The open motion planning library. IEEE Roboti. Autom. Mag. 19(4), 72\u201382 (2012)","DOI":"10.1109\/MRA.2012.2205651"},{"key":"14_CR25","unstructured":"Tassa, Y., et al.: Deepmind control suite. arXiv preprint arXiv:1801.00690 (2018)"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"14_CR27","unstructured":"Wachi, A., Sui, Y.: Safe reinforcement learning in constrained Markov decision processes. In: International Conference on Machine Learning, pp. 9797\u20139806. PMLR (2020)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Yang, X., Ji, Z., Wu, J., Lai, Y.-K.: An open-source multi-goal reinforcement learning environment for robotic manipulation with pybullet. arXiv preprint arXiv:2105.05985 (2021)","DOI":"10.1007\/978-3-030-89177-0_2"},{"key":"14_CR29","unstructured":"Zhu, Y., Wong, J., Mandlekar, A., Mart\u00edn-Mart\u00edn, R.: Robosuite: a modular simulation framework and benchmark for robot learning. arXiv preprint arXiv:2009.12293 (2020)"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence and Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-93842-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T16:29:17Z","timestamp":1674404957000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-93842-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030938413","9783030938420"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-93842-0_14","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BNAIC\/Benelearn","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Benelux Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Esch-sur-Alzette","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Luxembourg","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bnaic2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bnaic2021.uni.lu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"46","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}