{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:01:46Z","timestamp":1743044506401,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030625535"},{"type":"electronic","value":"9783030625542"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-62554-2_14","type":"book-chapter","created":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T17:02:35Z","timestamp":1604250155000},"page":"185-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Applied to Hexapod Robot Locomotion: An Overview"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1339-534X","authenticated-orcid":false,"given":"Espinosa","family":"Jorge","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2636-9642","authenticated-orcid":false,"given":"Gorrostieta","family":"Efren","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4593-5208","authenticated-orcid":false,"given":"Vargas-Soto","family":"Emilio","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2604-9692","authenticated-orcid":false,"given":"Ramos-Arregu\u00edn Juan","family":"Manuel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,28]]},"reference":[{"issue":"2","key":"14_CR1","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3390\/robotics3020181","volume":"3","author":"F Tedeschi","year":"2014","unstructured":"Tedeschi, F., Carbone, G.: Design issues for hexapod walking robots. Robotics 3(2), 181\u2013206 (2014). https:\/\/doi.org\/10.3390\/robotics3020181","journal-title":"Robotics"},{"issue":"4","key":"14_CR2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/0094-114X(83)90114-3","volume":"18","author":"EA Devjanin","year":"1983","unstructured":"Devjanin, E.A., et al.: The six-legged walking robot capable of terrain adaptation. Mech. Mach. Theory 18(4), 257\u2013260 (1983). https:\/\/doi.org\/10.1016\/0094-114X(83)90114-3","journal-title":"Mech. Mach. Theory"},{"issue":"7553","key":"14_CR3","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1038\/nature14422","volume":"521","author":"A Cully","year":"2015","unstructured":"Cully, A., Clune, J., Tarapore, D., Mouret, J.B.: Robots that can adapt like animals. Nature 521(7553), 503\u2013507 (2015). https:\/\/doi.org\/10.1038\/nature14422","journal-title":"Nature"},{"key":"14_CR4","unstructured":"Kume, A., Matsumoto, E., Takahashi, K., Ko, W., Tan, J.: Map-based multi-policy reinforcement learning: enhancing adaptability of robots by deep reinforcement learning. arXiv:1710.06117 (2017)"},{"key":"14_CR5","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, London (1998)"},{"key":"14_CR6","unstructured":"Watkins, C.J.C.H..: Learning with delayed rewards. Ph.D. thesis, King\u2019s College (1989)"},{"issue":"11","key":"14_CR7","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013). https:\/\/doi.org\/10.1177\/0278364913495721","journal-title":"Int. J. Robot. Res."},{"issue":"3\u20134","key":"14_CR8","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"14_CR9","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv:1312.5602 [cs] (2013)"},{"issue":"7587","key":"14_CR10","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"issue":"7540","key":"14_CR11","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"issue":"1","key":"14_CR12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/S0921-8890(99)00062-7","volume":"30","author":"F Delcomyn","year":"2000","unstructured":"Delcomyn, F., Nelson, M.E.: Architectures for a biomimetic hexapod robot. Robot. Auton. Syst. 30(1), 5\u201315 (2000). https:\/\/doi.org\/10.1016\/S0921-8890(99)00062-7","journal-title":"Robot. Auton. Syst."},{"issue":"3","key":"14_CR13","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1080\/10798587.1995.10750637","volume":"1","author":"F Pfeiffer","year":"1995","unstructured":"Pfeiffer, F., Eltze, J., Weidemann, H.-J.: The tum-walking machine. Intell. Autom. Soft Comput. 1(3), 307\u2013323 (1995). https:\/\/doi.org\/10.1080\/10798587.1995.10750637","journal-title":"Intell. Autom. Soft Comput."},{"issue":"1","key":"14_CR14","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/BF00693548","volume":"81","author":"D Graham","year":"1972","unstructured":"Graham, D.: A behavioural analysis of the temporal organisation of walking movements in the 1st instar and adult stick insect (Carausius morosus). J. Comp. Physiol. 81(1), 23\u201352 (1972). https:\/\/doi.org\/10.1007\/BF00693548","journal-title":"J. Comp. Physiol."},{"issue":"3","key":"14_CR15","first-page":"260","volume":"11","author":"E Gorrostieta","year":"2008","unstructured":"Gorrostieta, E., Vargas-Soto, E.: Algoritmo difuso de locomoci\u00f3n libre para un robot caminante de seis patas. Comput. Sist. 11(3), 260\u2013287 (2008)","journal-title":"Comput. Sist."},{"issue":"3","key":"14_CR16","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1299\/jsmec.46.881","volume":"46","author":"K Nonami","year":"2003","unstructured":"Nonami, K., et al.: Development and control of mine detection robot COMET-II and COMET-III. JSME Int J. Ser. C 46(3), 881\u2013890 (2003). https:\/\/doi.org\/10.1299\/jsmec.46.881","journal-title":"JSME Int J. Ser. C"},{"key":"14_CR17","series-title":"Mechanisms and Machine Science","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/978-3-319-14705-5_15","volume-title":"Motion and Operation Planning of Robotic Systems","author":"F Tedeschi","year":"2015","unstructured":"Tedeschi, F., Carbone, G.: Hexapod walking robot locomotion. In: Carbone, G., Gomez-Bravo, F. (eds.) Motion and Operation Planning of Robotic Systems. MMS, vol. 29, pp. 439\u2013468. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-14705-5_15"},{"issue":"2","key":"14_CR18","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/027836498300200201","volume":"2","author":"CA Klein","year":"2016","unstructured":"Klein, C.A., Olson, K.W., Pugh, D.R.: Use of force and attitude sensors for locomotion of a legged vehicle over irregular terrain. Int. J. Robot. Res. 2(2), 3\u201317 (2016). https:\/\/doi.org\/10.1177\/027836498300200201","journal-title":"Int. J. Robot. Res."},{"key":"14_CR19","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.robot.2018.01.007","volume":"103","author":"Y Zhao","year":"2018","unstructured":"Zhao, Y., Chai, X., Gao, F., Qi, C.: Obstacle avoidance and motion planning scheme for a hexapod robot Octopus-III. Robot. Auton. Syst. 103, 199\u2013212 (2018). https:\/\/doi.org\/10.1016\/j.robot.2018.01.007","journal-title":"Robot. Auton. Syst."},{"key":"14_CR20","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1016\/j.protcy.2012.03.037","volume":"3","author":"MC Garc\u00eda-L\u00f3pez","year":"2012","unstructured":"Garc\u00eda-L\u00f3pez, M.C., Gorrostieta-Hurtado, E., Vargas-Soto, E., Ramos-Arregu\u00edn, J.M., Sotomayor-Olmedo, A., Morales, J.C.M.: Kinematic analysis for trajectory generation in one leg of a hexapod robot. Proc. Technol. 3, 342\u2013350 (2012). https:\/\/doi.org\/10.1016\/j.protcy.2012.03.037","journal-title":"Proc. Technol."},{"issue":"4","key":"14_CR21","doi-asserted-by":"publisher","first-page":"144:1","DOI":"10.1145\/3197517.3201397","volume":"37","author":"W Yu","year":"2018","unstructured":"Yu, W., Turk, G., Liu, C.K.: Learning symmetric and low-energy locomotion. ACM Trans. Graph. 37(4), 144:1\u2013144:12 (2018). https:\/\/doi.org\/10.1145\/3197517.3201397","journal-title":"ACM Trans. Graph."},{"issue":"10","key":"14_CR22","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1016\/j.robot.2006.04.009","volume":"54","author":"TD Barfoot","year":"2006","unstructured":"Barfoot, T.D., Earon, E.J.P., D\u2019Eleuterio, G.M.T.: Experiments in learning distributed control for a hexapod robot. Robot. Auton. Syst. 54(10), 864\u2013872 (2006). https:\/\/doi.org\/10.1016\/j.robot.2006.04.009","journal-title":"Robot. Auton. Syst."},{"key":"14_CR23","volume-title":"Introduction to Probability Models","author":"SM Ross","year":"2014","unstructured":"Ross, S.M.: Introduction to Probability Models. Academic Press, Berkeley (2014)"},{"issue":"3","key":"14_CR24","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/S0921-8890(98)00054-2","volume":"25","author":"F Kirchner","year":"1998","unstructured":"Kirchner, F.: Q-learning of complex behaviours on a six-legged walking machine. Robot. Auton. Syst. 25(3), 253\u2013262 (1998). https:\/\/doi.org\/10.1016\/S0921-8890(98)00054-2","journal-title":"Robot. Auton. Syst."},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Youcef, Z., Pierre, C.: Control of the trajectory of a hexapod robot based on distributed Q-learning. In: 2004 IEEE International Symposium on Industrial Electronics, vol. 1, pp. 277\u2013282 (2004)","DOI":"10.1109\/ISIE.2004.1571820"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Shahriari, M., Khayyat, A.A.: Gait analysis of a six-legged walking robot using fuzzy reward reinforcement learning. In: 2013 13th Iranian Conference on Fuzzy Systems (IFSC), pp. 1\u20134 (2013)","DOI":"10.1109\/IFSC.2013.6675621"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Hong, J., Tang, K., Chen, C.: Obstacle avoidance of hexapod robots using fuzzy Q-learning. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1\u20136 (2017)","DOI":"10.1109\/SSCI.2017.8280907"},{"key":"14_CR28","unstructured":"Konen, K., Korthals, T., Melnik, A., Schilling, M.: Biologically-inspired deep reinforcement learning of modular control for a six-legged robot. In: 2019 IEEE International Conference on Robotics and Automation Workshop. Montreal, CA (2019)"},{"key":"14_CR29","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: Xing, E.P., Jebara, T. (eds.) Proceedings of the 31st International Conference on Machine Learning, pp. 387\u2013395. PMLR, Bejing (2014)"},{"key":"14_CR30","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)"},{"key":"14_CR31","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1561\/2200000071","volume":"11","author":"V Francois-Lavet","year":"2018","unstructured":"Francois-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J.: An introduction to deep reinforcement learning. FNT Mach. Learn. 11, 219\u2013354 (2018). https:\/\/doi.org\/10.1561\/2200000071","journal-title":"FNT Mach. Learn."},{"key":"14_CR32","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv:1509.02971 [cs, stat] (2019)"},{"key":"14_CR33","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv:1801.01290 (2018)"},{"key":"14_CR34","unstructured":"Ha, S., Xu, P., Tan, Z., Levine, S., Tan, J.: Learning to walk in the real world with minimal human effort. arXiv:2002.08550 (2020)"},{"key":"14_CR35","first-page":"1107","volume":"4","author":"MG Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-Squares Policy Iteration. J. Mach. Learn. Res. 4, 1107\u20131149 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR36","unstructured":"Gazebo Homepage. http:\/\/gazebosim.org\/. Accessed 07 Apr 2020"}],"container-title":["Communications in Computer and Information Science","Telematics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-62554-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T09:45:11Z","timestamp":1619257511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-62554-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030625535","9783030625542"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-62554-2_14","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"28 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WITCOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Congress of Telematics and Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Puerto Vallarta","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexico","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 November 2020","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":"witcom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.witcom.upiita.ipn.mx\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"79","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":"28","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":"3","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":"35% - 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":"-","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)"}},{"value":"Due to the COVID-19 pandemic the conference was held online","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}