{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:59:02Z","timestamp":1742947142725,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819986637"},{"type":"electronic","value":"9789819986644"}],"license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8664-4_17","type":"book-chapter","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T06:05:13Z","timestamp":1702533913000},"page":"298-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Run-Time Assured Reinforcement Learning for\u00a0Safe Spacecraft Rendezvous with\u00a0Obstacle Avoidance"],"prefix":"10.1007","author":[{"given":"Yingmin","family":"Xiao","sequence":"first","affiliation":[]},{"given":"Zhibin","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Zhiqiu","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,15]]},"reference":[{"key":"17_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: International Conference on Machine Learning, pp. 22\u201331. PMLR (2017)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Sreenath, K.: Discrete control barrier functions for safety-critical control of discrete systems with application to bipedal robot navigation. In: Robotics: Science and Systems, vol. 13, pp. 1\u201310. Cambridge, MA, USA (2017)","DOI":"10.15607\/RSS.2017.XIII.073"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Ames, A.D., Coogan, S., Egerstedt, M., Notomista, G., Sreenath, K., Tabuada, P.: Control barrier functions: theory and applications. In: 2019 18th European Control Conference (ECC), pp. 3420\u20133431. IEEE (2019)","DOI":"10.23919\/ECC.2019.8796030"},{"issue":"8","key":"17_CR5","doi-asserted-by":"publisher","first-page":"3861","DOI":"10.1109\/TAC.2016.2638961","volume":"62","author":"AD Ames","year":"2016","unstructured":"Ames, A.D., Xu, X., Grizzle, J.W., Tabuada, P.: Control barrier function based quadratic programs for safety critical systems. IEEE Trans. Autom. Control 62(8), 3861\u20133876 (2016)","journal-title":"IEEE Trans. Autom. Control"},{"key":"17_CR6","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"17_CR7","unstructured":"Broida, J., Linares, R.: Spacecraft rendezvous guidance in cluttered environments via reinforcement learning. In: 29th AAS\/AIAA Space Flight Mechanics Meeting, pp. 1\u201315. American Astronautical Society (2019)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Carr, S., Jansen, N., Junges, S., Topcu, U.: Safe reinforcement learning via shielding for pomdps. arXiv preprint (2022)","DOI":"10.1609\/aaai.v37i12.26723"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, R., Orosz, G., Murray, R.M., Burdick, J.W.: End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3387\u20133395 (2019)","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"17_CR10","unstructured":"Chow, Y., Nachum, O., Duenez-Guzman, E., Ghavamzadeh, M.: A lyapunov-based approach to safe reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"17_CR11","unstructured":"Chow, Y., Nachum, O., Faust, A., Duenez-Guzman, E., Ghavamzadeh, M.: Lyapunov-based safe policy optimization for continuous control. arXiv preprint arXiv:1901.10031 (2019)"},{"issue":"9","key":"17_CR12","doi-asserted-by":"publisher","first-page":"653","DOI":"10.2514\/8.8704","volume":"27","author":"W Clohessy","year":"1960","unstructured":"Clohessy, W., Wiltshire, R.: Terminal guidance system for satellite rendezvous. J. Aerosp. Sci. 27(9), 653\u2013658 (1960)","journal-title":"J. Aerosp. Sci."},{"issue":"1","key":"17_CR13","first-page":"25","volume":"20","author":"K Dunlap","year":"2023","unstructured":"Dunlap, K., Mote, M., Delsing, K., Hobbs, K.L.: Run time assured reinforcement learning for safe satellite docking. J. Aerosp. Inf. Syst. 20(1), 25\u201336 (2023)","journal-title":"J. Aerosp. Inf. Syst."},{"issue":"6","key":"17_CR14","doi-asserted-by":"publisher","first-page":"1774","DOI":"10.2514\/1.A35076","volume":"58","author":"L Federici","year":"2021","unstructured":"Federici, L., Benedikter, B., Zavoli, A.: Deep learning techniques for autonomous spacecraft guidance during proximity operations. J. Spacecr. Rocket. 58(6), 1774\u20131785 (2021)","journal-title":"J. Spacecr. Rocket."},{"issue":"1","key":"17_CR15","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":"17_CR16","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.actaastro.2020.01.007","volume":"169","author":"B Gaudet","year":"2020","unstructured":"Gaudet, B., Linares, R., Furfaro, R.: Adaptive guidance and integrated navigation with reinforcement meta-learning. Acta Astronaut. 169, 180\u2013190 (2020)","journal-title":"Acta Astronaut."},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Hamilton, N., Dunlap, K., Johnson, T.T., Hobbs, K.L.: Ablation study of how run time assurance impacts the training and performance of reinforcement learning agents. In: 2023 IEEE 9th International Conference on Space Mission Challenges for Information Technology (SMC-IT), pp. 45\u201355. IEEE (2023)","DOI":"10.1109\/SMC-IT56444.2023.00014"},{"issue":"1","key":"17_CR18","doi-asserted-by":"publisher","first-page":"5","DOI":"10.2307\/2369430","volume":"1","author":"GW Hill","year":"1878","unstructured":"Hill, G.W.: Researches in the lunar theory. Am. J. Math. 1(1), 5\u201326 (1878)","journal-title":"Am. J. Math."},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Hovell, K., Ulrich, S.: On deep reinforcement learning for spacecraft guidance. In: AIAA Scitech 2020 Forum, p. 1600 (2020)","DOI":"10.2514\/6.2020-1600"},{"issue":"9","key":"17_CR20","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.ifacol.2015.08.093","volume":"48","author":"C Jewison","year":"2015","unstructured":"Jewison, C., Erwin, R.S., Saenz-Otero, A.: Model predictive control with ellipsoid obstacle constraints for spacecraft rendezvous. IFAC-PapersOnLine 48(9), 257\u2013262 (2015)","journal-title":"IFAC-PapersOnLine"},{"key":"17_CR21","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Ma, H., et al.: Model-based constrained reinforcement learning using generalized control barrier function. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4552\u20134559. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636468"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Oestreich, C.E., Linares, R., Gondhalekar, R.: Autonomous six-degree-of-freedom spacecraft docking maneuvers via reinforcement learning. arXiv preprint arXiv:2008.03215 (2020)","DOI":"10.2514\/1.I010914"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Rivera, J.G., Danylyszyn, A.A., Weinstock, C.B., Sha, L., Gagliardi, M.J.: An architectural description of the simplex architecture. Carnegie Mellon University, Pittsburg, Pennsylvania, Technical report, Software Engineering Institute (1996)","DOI":"10.21236\/ADA307890"},{"key":"17_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"1","key":"17_CR26","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.asr.2022.08.002","volume":"71","author":"A Scorsoglio","year":"2023","unstructured":"Scorsoglio, A., Furfaro, R., Linares, R., Massari, M.: Relative motion guidance for near-rectilinear lunar orbits with path constraints via actor-critic reinforcement learning. Adv. Space Res. 71(1), 316\u2013335 (2023)","journal-title":"Adv. Space Res."},{"key":"17_CR27","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s10107-004-0559-y","volume":"106","author":"A W\u00e4chter","year":"2006","unstructured":"W\u00e4chter, A., Biegler, L.T.: On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming. Math. Program. 106, 25\u201357 (2006)","journal-title":"Math. Program."},{"key":"17_CR28","first-page":"9111","volume":"35","author":"L Yang","year":"2022","unstructured":"Yang, L., et al.: Constrained update projection approach to safe policy optimization. Adv. Neural. Inf. Process. Syst. 35, 9111\u20139124 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"17_CR29","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1109\/TII.2022.3192085","volume":"19","author":"Z Yang","year":"2023","unstructured":"Yang, Z., et al.: Model-based reinforcement learning and neural-network-based policy compression for spacecraft rendezvous on resource-constrained embedded systems. IEEE Trans. Industr. Inf. 19(1), 1107\u20131116 (2023)","journal-title":"IEEE Trans. Industr. Inf."}],"container-title":["Lecture Notes in Computer Science","Dependable Software Engineering. Theories, Tools, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8664-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T06:08:48Z","timestamp":1702534128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8664-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"ISBN":["9789819986637","9789819986644"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8664-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,15]]},"assertion":[{"value":"15 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SETTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Dependable Software Engineering: Theories, Tools, and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"setta2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lcs.ios.ac.cn\/setta2023\/","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":"78","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":"24","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":"31% - 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":"7","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)"}}]}}