{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:30:37Z","timestamp":1774449037354,"version":"3.50.1"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"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":["Int J Intell Robot Appl"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s41315-025-00496-6","type":"journal-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:35:41Z","timestamp":1761374141000},"page":"273-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement learning for hexapod robot trajectory control: a study of Q-learning and SARSA algorithms"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9238-1909","authenticated-orcid":false,"given":"Ahmed","family":"Benyoucef","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2059-8324","authenticated-orcid":false,"given":"Youcef","family":"Zennir","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1927-9366","authenticated-orcid":false,"given":"Ammar","family":"Belatreche","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0593-2865","authenticated-orcid":false,"given":"Manuel F.","family":"Silva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2527-8741","authenticated-orcid":false,"given":"Mohamed","family":"Benghanem","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,25]]},"reference":[{"key":"496_CR1","unstructured":"Aissaoui, A., Mahfoudi, C., Djeffal, S.: \u2018A General Kinematic-Based Walking Algorithm of a Hexapod Robot on Irregular Terrain\u2019 (2024)."},{"key":"496_CR2","doi-asserted-by":"publisher","unstructured":"AlMahamid, F., Grolinger, K.: \u2018Reinforcement learning algorithms: An overview and classification\u2019, in 2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pp. 1\u20137. (2021). https:\/\/doi.org\/10.1109\/CCECE53047.2021.9569056.","DOI":"10.1109\/CCECE53047.2021.9569056"},{"issue":"7","key":"496_CR3","doi-asserted-by":"publisher","first-page":"2781","DOI":"10.1007\/s13042-023-02063-6","volume":"15","author":"E Amhraoui","year":"2024","unstructured":"Amhraoui, E., Masrour, T.: Expected Lenient Q-learning: a fast variant of the Lenient Q-learning algorithm for cooperative stochastic Markov games. Int. J. Mach. Learn. Cybern. 15(7), 2781\u20132797 (2024). https:\/\/doi.org\/10.1007\/s13042-023-02063-6","journal-title":"Int. J. Mach. Learn. Cybern."},{"issue":"01","key":"496_CR4","first-page":"1","volume":"02","author":"A Benyoucef","year":"2024","unstructured":"Benyoucef, A., Amrane, A., Zennir, Y., Belatreche, A.: Autonomous obstacle avoidance for a hexapod robot using proximity sensors. Int. J. Autom. Saf 02(01), 1\u20136 (2024)","journal-title":"Int. J. Autom. Saf"},{"key":"496_CR5","doi-asserted-by":"publisher","unstructured":"Benyoucef, A., Zennir, Y.: \u2018Enhancing Hexapod Robot Locomotion Control Through PID Controller Optimization Using Genetic Algorithm\u2019, in 2023 IEEE 11th International Conference on Systems and Control (ICSC), Sousse, Tunisia: IEEE, pp. 556\u2013561 (2023). https:\/\/doi.org\/10.1109\/ICSC58660.2023.10449774.","DOI":"10.1109\/ICSC58660.2023.10449774"},{"key":"496_CR6","doi-asserted-by":"publisher","unstructured":"Bjelonic,M., Homberger, T., Kottege, N., Borges, P., Chli, M., Beckerle, P.: \u2018Autonomous navigation of hexapod robots with vision-based controller adaptation\u2019, in 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, Singapore: IEEE, pp. 5561\u20135568 (2017). https:\/\/doi.org\/10.1109\/ICRA.2017.7989655.","DOI":"10.1109\/ICRA.2017.7989655"},{"key":"496_CR7","doi-asserted-by":"crossref","unstructured":"Boaventura, T., Medrano-Cerda, G. A., Semini, C., Buchli, J., Caldwell, D. G. (2013). Stability and performance of the compliance controller of the quadruped robot HyQ. In\u00a02013 IEEE\/RSJ international conference on intelligent robots and systems\u00a0(pp. 1458-1464). IEEE.","DOI":"10.1109\/IROS.2013.6696541"},{"key":"496_CR8","doi-asserted-by":"publisher","unstructured":"Brooks, R.A.: \u2018A robot that walks; emergent behaviors from a carefully evolved network\u2019, in Proceedings, 1989 International Conference on Robotics and Automation, Scottsdale, AZ, USA: IEEE Comput. Soc. Press, pp. 692\u20134+2 (1989). https:\/\/doi.org\/10.1109\/ROBOT.1989.100065.","DOI":"10.1109\/ROBOT.1989.100065"},{"issue":"1","key":"496_CR9","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1754\/1\/012157","volume":"1754","author":"Z Cai","year":"2021","unstructured":"Cai, Z., Gao, Y., Wei, W., Gao, T., Xie, Z.: Model design and gait planning of hexapod climbing robot. J. Phys. Conf. Ser. 1754(1), 012157 (2021). https:\/\/doi.org\/10.1088\/1742-6596\/1754\/1\/012157","journal-title":"J. Phys. Conf. Ser."},{"key":"496_CR10","unstructured":"Celaya, E., Porta, J.M.: \u2018Force-based control of a six-legged robot on abrupt terrain using the subsumption architecture\u2019, pp. 1\u201310, (2000)."},{"issue":"21","key":"496_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/s20216295","volume":"20","author":"C Chen","year":"2020","unstructured":"Chen, C., et al.: Attitude trajectory optimization to ensure balance hexapod locomotion. Sensors 20(21), 1\u201331 (2020). https:\/\/doi.org\/10.3390\/s20216295","journal-title":"Sensors"},{"issue":"7","key":"496_CR12","doi-asserted-by":"publisher","DOI":"10.3390\/s24072061","volume":"24","author":"L Chen","year":"2024","unstructured":"Chen, L., Wang, Q., Deng, C., Xie, B., Tuo, X., Jiang, G.: Improved double deep Q-network algorithm applied to multi-dimensional environment path planning of hexapod robots. Sensors 24(7), 2061 (2024). https:\/\/doi.org\/10.3390\/s24072061","journal-title":"Sensors"},{"issue":"3","key":"496_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/robotics10030100","volume":"10","author":"J Coelho","year":"2021","unstructured":"Coelho, J., Ribeiro, F., Dias, B., Lopes, G., Flores, P.: Trends in the control of hexapod robots: a survey. Robotics 10(3), 1\u201322 (2021). https:\/\/doi.org\/10.3390\/robotics10030100","journal-title":"Robotics"},{"key":"496_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0_2","volume-title":"Deep Reinforcement Learning","author":"Z Ding","year":"2020","unstructured":"Ding, Z., Huang, Y., Yuan, H., Dong, H.: \u2018Introduction to Reinforcement Learning.\u2019 In: Dong, H., Ding, Z., Zhang, S. (eds.) Deep Reinforcement Learning, pp. 47\u2013123. Springer Singapore, Singapore (2020). https:\/\/doi.org\/10.1007\/978-981-15-4095-0_2"},{"key":"496_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.fraope.2024.100077","volume":"6","author":"S Djeffal","year":"2024","unstructured":"Djeffal, S., Morakchi, M.R., Ghoul, A., Kargin, T.C.: DDPG-based reinforcement learning for controlling a spatial three-section continuum robot. Frankl. Open 6, 100077 (2024). https:\/\/doi.org\/10.1016\/j.fraope.2024.100077","journal-title":"Frankl. Open"},{"key":"496_CR16","doi-asserted-by":"publisher","unstructured":"Dobrevski M., Skocaj, D.: \u2018Adaptive dynamic window approach for local navigation\u2019, in 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA: IEEE, pp. 6930\u20136936 (2020). https:\/\/doi.org\/10.1109\/IROS45743.2020.9340927.","DOI":"10.1109\/IROS45743.2020.9340927"},{"issue":"9","key":"496_CR17","doi-asserted-by":"publisher","first-page":"2419","DOI":"10.1007\/s10994-021-05961-4","volume":"110","author":"G Dulac-Arnold","year":"2021","unstructured":"Dulac-Arnold, G., et al.: Challenges of real-world reinforcement learning: definitions, benchmarks and analysis. Mach. Learn. 110(9), 2419\u20132468 (2021). https:\/\/doi.org\/10.1007\/s10994-021-05961-4","journal-title":"Mach. Learn."},{"key":"496_CR18","doi-asserted-by":"publisher","unstructured":"Fu H.,et al.: \u2018Deep Reinforcement Learning for Multi-contact Motion Planning of Hexapod Robots\u2019, in Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, Montreal, Canada: International Joint Conferences on Artificial Intelligence Organization, Aug. 2021, pp. 2381\u20132388. https:\/\/doi.org\/10.24963\/ijcai.2021\/328.","DOI":"10.24963\/ijcai.2021\/328"},{"key":"496_CR19","doi-asserted-by":"publisher","unstructured":"Fuchs, \u2018Intersegmental coordination of cockroach locomotion: adaptive control of centrally coupled pattern generator circuits\u2019, Front. Neural Circuits, 2010, https:\/\/doi.org\/10.3389\/fncir.2010.00125.","DOI":"10.3389\/fncir.2010.00125"},{"key":"496_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107130","volume":"126","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Liu, Q., Zhu, F.: Hierarchical reinforcement learning with adaptive scheduling for robot control. Eng. Appl. Artif. Intell. 126, 107130 (2023). https:\/\/doi.org\/10.1016\/j.engappai.2023.107130","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"4","key":"496_CR21","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1016\/j.neunet.2008.03.014","volume":"21","author":"AJ Ijspeert","year":"2008","unstructured":"Ijspeert, A.J.: Central pattern generators for locomotion control in animals and robots: a review. Neural Netw 21(4), 642\u2013653 (2008). https:\/\/doi.org\/10.1016\/j.neunet.2008.03.014","journal-title":"Neural Netw"},{"key":"496_CR22","unstructured":"Ivo, H., Patrik, K.: \u2018Reinforcement Learning In Control Systems for Walking Hexapod Robots.\u2019, ResearchGate, pp. 1\u201313, (2005)"},{"key":"496_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fbioe.2020.621560","volume":"8","author":"Q Ji","year":"2021","unstructured":"Ji, Q., Qian, Z., Ren, L., Ren, L.: Simulation analysis of impulsive ankle push-off on the walking speed of a planar biped robot. Front. Bioeng. Biotechnol. 8, 1\u201311 (2021). https:\/\/doi.org\/10.3389\/fbioe.2020.621560","journal-title":"Front. Bioeng. Biotechnol."},{"key":"496_CR24","doi-asserted-by":"publisher","unstructured":"Kingsley, D., Quinn, R., Ritzmann, R.: \u2018A Cockroach Inspired Robot With Artificial Muscles\u2019, in 2006 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Beijing, China: IEEE, Oct. pp. 1837\u20131842. (2006) https:\/\/doi.org\/10.1109\/IROS.2006.282229.","DOI":"10.1109\/IROS.2006.282229"},{"key":"496_CR25","doi-asserted-by":"publisher","unstructured":"Kirchner, F.: \u2018Q-learning of complex behaviours on a six-legged walking machine\u2019, in Proceedings Second EUROMICRO Workshop on Advanced Mobile Robots, Brescia, Italy: IEEE Comput. Soc, pp. 51\u201358 (1997). https:\/\/doi.org\/10.1109\/EURBOT.1997.633565.","DOI":"10.1109\/EURBOT.1997.633565"},{"key":"496_CR26","unstructured":"Lagaza, K.P., Pandey, A.: \u2018Review Article Mechanical Engineering\u2019, (2018)."},{"key":"496_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2022.104917","volume":"174","author":"H Li","year":"2022","unstructured":"Li, H., Qi, C., Gao, F., Chen, X., Zhao, Y., Chen, Z.: Mechanism design and workspace analysis of a hexapod robot. Mech. Mach. Theory 174, 104917 (2022). https:\/\/doi.org\/10.1016\/j.mechmachtheory.2022.104917","journal-title":"Mech. Mach. Theory"},{"key":"496_CR28","doi-asserted-by":"publisher","first-page":"2439","DOI":"10.1109\/ACCESS.2016.2570255","volume":"4","author":"J-L Lin","year":"2016","unstructured":"Lin, J.-L., Hwang, K.-S., Jiang, W.-C., Chen, Y.-J.: Gait balance and acceleration of a biped robot based on Q-learning. IEEE Access 4, 2439\u20132449 (2016). https:\/\/doi.org\/10.1109\/ACCESS.2016.2570255","journal-title":"IEEE Access"},{"key":"496_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.7717\/peerj-cs.556","volume":"7","author":"E L\u00f3pez-Lozada","year":"2021","unstructured":"L\u00f3pez-Lozada, E., Rubio-Espino, E., Sossa-Azuela, J.H., Ponce-Ponce, V.H.: Reactive navigation under a fuzzy rules-based scheme and reinforcement learning for mobile robots. PeerJ Comput. Sci. 7, 1\u201325 (2021). https:\/\/doi.org\/10.7717\/peerj-cs.556","journal-title":"PeerJ Comput. Sci."},{"issue":"9","key":"496_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/mi13091404","volume":"13","author":"J Ma","year":"2022","unstructured":"Ma, J., Qiu, G., Guo, W., Li, P., Ma, G.: Design, Analysis and Experiments of Hexapod Robot with Six-Link Legs for High Dynamic Locomotion. Micromachines 13(9), 1\u201320 (2022). https:\/\/doi.org\/10.3390\/mi13091404","journal-title":"Micromachines"},{"key":"496_CR31","doi-asserted-by":"crossref","unstructured":"Margolis, G.B., Yang, G., Paigwar, K., Chen, T., Agrawal, P.: \u2018Rapid Locomotion via Reinforcement Learning\u2019, Robot. Sci. Syst., p. 12, (2022).","DOI":"10.15607\/RSS.2022.XVIII.022"},{"issue":"62","key":"496_CR32","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822","volume":"7","author":"T Miki","year":"2022","unstructured":"Miki, T., Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning robust perceptive locomotion for quadrupedal robots in the wild. Sci. Robot. 7(62), eabk2822 (2022). https:\/\/doi.org\/10.1126\/scirobotics.abk2822","journal-title":"Sci. Robot."},{"key":"496_CR33","doi-asserted-by":"publisher","unstructured":"Nishigai, K., Ito, K.: \u2018Control of multi-legged robot using reinforcement learning with body image and application to a real robot\u2019, in 2011 IEEE International Conference on Robotics and Biomimetics, Karon Beach, Thailand: IEEE 2011, pp. 2511\u20132516. https:\/\/doi.org\/10.1109\/ROBIO.2011.6181682.","DOI":"10.1109\/ROBIO.2011.6181682"},{"issue":"4","key":"496_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073602","volume":"36","author":"XB Peng","year":"2017","unstructured":"Peng, X.B., Berseth, G., Yin, K., Van De Panne, M.: Deeploco: dynamic locomotion skills using hierarchical deep reinforcement learning. ACM Trans. Graph. 36(4), 1\u201313 (2017). https:\/\/doi.org\/10.1145\/3072959.3073602","journal-title":"ACM Trans. Graph."},{"key":"496_CR35","unstructured":"Porta, J., Celaya, E.: \u2018Body and Leg Coordination for Omni-Directional Walking in Rough Terrain\u2019, Inst. Rob\u00f2tica Inform\u00e0tica Ind. UPC-CSIC Barc. SPAIN, pp. 1\u20138, (2000)."},{"issue":"2","key":"496_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/act12020075","volume":"12","author":"Z Qiu","year":"2023","unstructured":"Qiu, Z., Wei, W., Liu, X.: Adaptive Gait Generation for Hexapod Robots Based on Reinforcement Learning and Hierarchical Framework. Actuators 12(2), 1\u201315 (2023). https:\/\/doi.org\/10.3390\/act12020075","journal-title":"Actuators"},{"key":"496_CR37","unstructured":"Qu, T., Li, D., Zakhor, A., Yu, W., Zhang, T.: \u2018Versatile Locomotion Skills for Hexapod Robots\u2019."},{"key":"496_CR38","doi-asserted-by":"publisher","unstructured":"Ribeiro, T., Goncalves, F., Garcia, I., Lopes, G., Ribeiro, A.F.: \u2018Q-Learning for Autonomous Mobile Robot Obstacle Avoidance\u2019, in 2019 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), Porto, Portugal: IEEE, pp. 1\u20137. (2019) https:\/\/doi.org\/10.1109\/ICARSC.2019.8733621.","DOI":"10.1109\/ICARSC.2019.8733621"},{"key":"496_CR39","unstructured":"Rummery, G., Niranjan, M.: \u2018On-Line Q-Learning Using Connectionist Systems\u2019, Camb. Univ. Eng. Dep. Trumpington, p. 19, (1994)."},{"key":"496_CR40","doi-asserted-by":"publisher","unstructured":"Schilling, M., Melnik, A.: \u2018An Approach to Hierarchical Deep Reinforcement Learning for a Decentralized Walking Control Architecture\u2019, in Biologically Inspired Cognitive Architectures 2018, vol. 848, A. V. Samsonovich, Ed., in Advances in Intelligent Systems and Computing, vol. 848. Cham: Springer International Publishing, pp. 272\u2013282. (2019) https:\/\/doi.org\/10.1007\/978-3-319-99316-4_36.","DOI":"10.1007\/978-3-319-99316-4_36"},{"key":"496_CR41","doi-asserted-by":"publisher","unstructured":"Siciliano, B., Khatib, O., Eds., Springer Handbook of Robotics. in Springer Handbooks. Cham: Springer International Publishing, (2016). https:\/\/doi.org\/10.1007\/978-3-319-32552-1.","DOI":"10.1007\/978-3-319-32552-1"},{"issue":"1","key":"496_CR42","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1017\/S0263574707003554","volume":"26","author":"MF Silva","year":"2008","unstructured":"Silva, M.F., Machado, J.A.T.: Kinematic and dynamic performance analysis of artificial legged systems. Robotica 26(1), 19\u201339 (2008). https:\/\/doi.org\/10.1017\/S0263574707003554","journal-title":"Robotica"},{"issue":"12","key":"496_CR43","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.1177\/1077546311403180","volume":"18","author":"MF Silva","year":"2012","unstructured":"Silva, M.F., Machado, J.T.: A literature review on the optimization of legged robots. J. Vib. Control 18(12), 1753\u20131767 (2012). https:\/\/doi.org\/10.1177\/1077546311403180","journal-title":"J. Vib. Control"},{"issue":"5","key":"496_CR44","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1017\/S0263574704001195","volume":"23","author":"MF Silva","year":"2005","unstructured":"Silva, M.F., Machado, J.A.T., Lopes, A.M.: Modelling and simulation of artificial locomotion systems. Robotica 23(5), 595\u2013606 (2005). https:\/\/doi.org\/10.1017\/S0263574704001195","journal-title":"Robotica"},{"issue":"6","key":"496_CR45","first-page":"95","volume":"4","author":"DSK Singh","year":"2017","unstructured":"Singh, D.S.K.: A literature survey of hexapod robots. Int. J. Eng. Res. Comput. Sci. Eng. 4(6), 95\u2013104 (2017)","journal-title":"Int. J. Eng. Res. Comput. Sci. Eng."},{"issue":"2","key":"496_CR46","doi-asserted-by":"publisher","first-page":"743","DOI":"10.61841\/turcomat.v11i2.14417","volume":"11","author":"O Singh","year":"2020","unstructured":"Singh, O., Barodiya, V.K., Paridwal, A., Makhija, A.: Reinforcement learning in robotics: challenges and applications. Turk. J. Comput. Math. Educ. TURCOMAT 11(2), 743\u2013745 (2020). https:\/\/doi.org\/10.61841\/turcomat.v11i2.14417","journal-title":"Turk. J. Comput. Math. Educ. TURCOMAT"},{"key":"496_CR47","doi-asserted-by":"crossref","unstructured":"Singh, S.P., Sutton, R.S.: \u2018Reinforcement learning with replacing eligibility traces\u2019, 1996 Kluwer Acad., pp. 123\u2013158, 196AD.","DOI":"10.1007\/978-0-585-33656-5_7"},{"issue":"4","key":"496_CR48","doi-asserted-by":"publisher","first-page":"141","DOI":"10.12700\/APH.13.4.2016.4.9","volume":"13","author":"V Socha","year":"2016","unstructured":"Socha, V., Kutilek, P., Stefek, A., Socha, L., Schlenker, J., Hana, K.: Decision Making Process of Hexapods in a Model of Complex Terrains. Acta Polytech. Hung. 13(4), 141\u2013157 (2016). https:\/\/doi.org\/10.12700\/APH.13.4.2016.4.9","journal-title":"Acta Polytech. Hung."},{"key":"496_CR49","unstructured":"Sutton\u00a0R. S., Barto A. G., Reinforcement Learning: An Introduction. 2014."},{"key":"496_CR50","unstructured":"Sutton\u00a0R. S., Barto A. G, Reinforcement learning: an introduction, Second edition. in Adaptive computation and machine learning series. Cambridge, Massachusetts: The MIT Press, 2018."},{"key":"496_CR51","doi-asserted-by":"publisher","unstructured":"Tan J\u00a0et al., \u2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robots\u2019 2018, arXiv: arXiv:1804.10332. https:\/\/doi.org\/10.48550\/arXiv.1804.10332.","DOI":"10.48550\/arXiv.1804.10332"},{"issue":"2","key":"496_CR52","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1038\/s42256-022-00444-0","volume":"4","author":"M Thor","year":"2022","unstructured":"Thor, M., Manoonpong, P.: Versatile modular neural locomotion control with fast learning. Nat. Mach. Intell. 4(2), 169\u2013179 (2022). https:\/\/doi.org\/10.1038\/s42256-022-00444-0","journal-title":"Nat. Mach. Intell."},{"key":"496_CR53","doi-asserted-by":"publisher","unstructured":"Travers, M., Ansari, A., Choset, H.: \u2018A dynamical systems approach to obstacle navigation for a series-elastic hexapod robot\u2019, in 2016 IEEE 55th Conference on Decision and Control (CDC), Las Vegas, NV, USA: IEEE, pp. 5152\u20135157 (2016). https:\/\/doi.org\/10.1109\/CDC.2016.7799057.","DOI":"10.1109\/CDC.2016.7799057"},{"issue":"11","key":"496_CR54","doi-asserted-by":"publisher","first-page":"10901","DOI":"10.1109\/TII.2023.3240758","volume":"19","author":"X Wang","year":"2023","unstructured":"Wang, X., Fu, H., Deng, G., Liu, C., Tang, K., Chen, C.: Hierarchical free gait motion planning for hexapod robots using deep reinforcement learning. IEEE Trans. Ind. Inform 19(11), 10901\u201310912 (2023a). https:\/\/doi.org\/10.1109\/TII.2023.3240758","journal-title":"IEEE Trans. Ind. Inform"},{"issue":"1","key":"496_CR55","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1108\/IR-01-2022-0028","volume":"50","author":"Z Wang","year":"2023","unstructured":"Wang, Z., Gao, F., Zhao, Y., Yin, Y., Wang, L.: Improved A* algorithm and model predictive control- based path planning and tracking framework for hexapod robots. Ind. Robot. Int. J. Robot. Res. Appl 50(1), 135\u2013144 (2023b). https:\/\/doi.org\/10.1108\/IR-01-2022-0028","journal-title":"Ind. Robot. Int. J. Robot. Res. Appl"},{"key":"496_CR56","doi-asserted-by":"publisher","unstructured":"Wang T, Taghvaei A, Mehta PG, \u2018Q-learning for POMDP: An application to learning locomotion gaits\u2019, in 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France: IEEE,2019, pp. 2758\u20132763. https:\/\/doi.org\/10.1109\/CDC40024.2019.9030143.","DOI":"10.1109\/CDC40024.2019.9030143"},{"issue":"5","key":"496_CR57","doi-asserted-by":"publisher","DOI":"10.1177\/17298814211050190","volume":"18","author":"X Wenxia","year":"2021","unstructured":"Wenxia, X., Yu, B., Cheng, L., Li, Y., Cao, X.: Multi-fuzzy Sarsa learning-based sit-to-stand motion control for walking-support assistive robot. Int. J. Adv. Robot. Syst 18(5), 17298814211050190 (2021). https:\/\/doi.org\/10.1177\/17298814211050190","journal-title":"Int. J. Adv. Robot. Syst"},{"key":"496_CR58","doi-asserted-by":"publisher","unstructured":"Yang, Q., Gao, Y., Li, S.: \u2018Terrain-adaptive Central Pattern Generators with Reinforcement Learning for Hexapod Locomotion\u2019 (2023), arXiv: arXiv:2310.07744. https:\/\/doi.org\/10.48550\/arXiv.2310.07744.","DOI":"10.48550\/arXiv.2310.07744"},{"key":"496_CR59","doi-asserted-by":"publisher","unstructured":"Yang, M.-C., Samani, H., Zhu, K.: \u2018Emergency-Response Locomotion of Hexapod Robot with Heuristic Reinforcement Learning Using Q-Learning\u2019, in Interactive Collaborative Robotics, vol. 11659, A. Ronzhin, G. Rigoll, and R. Meshcheryakov, Eds., in Lecture Notes in Computer Science, vol. 11659. , Cham: Springer International Publishing, pp. 320\u2013329 (2019). https:\/\/doi.org\/10.1007\/978-3-030-26118-4_31.","DOI":"10.1007\/978-3-030-26118-4_31"},{"key":"496_CR60","volume-title":"Apprentissage par renforcement et syst\u00e8mes distribu\u00e9s : application \u00e0 l\u2019apprentissage de la marche d\u2019un robot hexapode","author":"Y Zennir","year":"2004","unstructured":"Zennir, Y.: Apprentissage par renforcement et syst\u00e8mes distribu\u00e9s\u202f: application \u00e0 l\u2019apprentissage de la marche d\u2019un robot hexapode. Phd these, INSA de Lyon (2004)"},{"issue":"8","key":"496_CR61","doi-asserted-by":"publisher","first-page":"965","DOI":"10.3166\/jesa.39.965-993","volume":"39","author":"Y Zennir","year":"2005","unstructured":"Zennir, Y., Couturier, P.: Approche distribu\u00e9e de l\u2019apprentissage. Application au contr\u00f4le de la trajectoire d\u2019un robot hexapode. Journal Europ\u00e9en des Syst\u00e8mes Automatis\u00e9s 39(8), 965\u2013993 (2005a). https:\/\/doi.org\/10.3166\/jesa.39.965-993","journal-title":"Journal Europ\u00e9en des Syst\u00e8mes Automatis\u00e9s"},{"key":"496_CR62","doi-asserted-by":"publisher","unstructured":"Zennir, Y.. Couturier, P.: \u2018Multiactor approach and hexapod robot learning\u2019, in 2005 International Symposium on Computational Intelligence in Robotics and Automation, Espoo, Finland: IEEE, pp. 665\u2013671 (2005b). https:\/\/doi.org\/10.1109\/CIRA.2005.1554353.","DOI":"10.1109\/CIRA.2005.1554353"},{"key":"496_CR63","doi-asserted-by":"publisher","unstructured":"Zennir, Y., Coutourier, P., B\u00e9temps, M.: \u2018Distributed Reinforcement Learning of a Six-Legged Robot to Walk\u2019, in The Fourth International Conference on Control and Automation 2003 ICCA Final Program and Book of Abstracts ICCA-03, Montreal, Que., Canada: IEEE, pp. 896\u2013900 (2003a). https:\/\/doi.org\/10.1109\/ICCA.2003.1595152.","DOI":"10.1109\/ICCA.2003.1595152"},{"key":"496_CR64","unstructured":"Zennir, Y., Coutourier, P., B\u00e9temps, M.: \u2018Apprentissage De La Marche D\u2019un Robot Hexapode Selon une Approche Distrib\u00e9e du Q-Learning\u2019, Conf\u00e9rence Int. En Sci. Electron. Technol. Inf. T\u00e9l\u00e9communications Bouhlel MS Solaiman B Kamoun Eds Sousse Tunis. 17\u201321 Mars 2003b, pp. 1\u20138."},{"issue":"1","key":"496_CR65","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2386\/1\/012037","volume":"2386","author":"X Zhou","year":"2022","unstructured":"Zhou, X.: Optimal values selection of Q-learning parameters in stochastic mazes. J. Phys. Conf. Ser. 2386(1), 012037 (2022). https:\/\/doi.org\/10.1088\/1742-6596\/2386\/1\/012037","journal-title":"J. Phys. Conf. Ser."}],"container-title":["International Journal of Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-025-00496-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41315-025-00496-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41315-025-00496-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T13:07:15Z","timestamp":1774444035000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41315-025-00496-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,25]]},"references-count":65,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["496"],"URL":"https:\/\/doi.org\/10.1007\/s41315-025-00496-6","relation":{},"ISSN":["2366-5971","2366-598X"],"issn-type":[{"value":"2366-5971","type":"print"},{"value":"2366-598X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,25]]},"assertion":[{"value":"8 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}