{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T07:55:32Z","timestamp":1767772532095,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T00:00:00Z","timestamp":1713312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["11372270","11372270"],"award-info":[{"award-number":["11372270","11372270"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s10514-024-10160-w","type":"journal-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T13:02:03Z","timestamp":1713358923000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement learning with imitative behaviors for humanoid robots navigation: synchronous planning and control"],"prefix":"10.1007","volume":"48","author":[{"given":"Xiaoying","family":"Wang","sequence":"first","affiliation":[]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"10160_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.\u00a0S., Davis, A., Dean, J., Devin, M., & Ghemawat, S. (2016). Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467."},{"key":"10160_CR2","doi-asserted-by":"crossref","unstructured":"Abedi, E., Alamirpour, P., & Mirshahvalad, R. (2017). Control humanoid robot using intelligent optimization algorithms fusion with fourier series. In 2017 9th international conference on computational intelligence and communication networks (CICN) (pp. 181\u2013185). IEEE.","DOI":"10.1109\/CICN.2017.8319381"},{"key":"10160_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2020.103497","volume":"128","author":"NG Aldana-Murillo","year":"2020","unstructured":"Aldana-Murillo, N. G., Sandoval, L., Hayet, J.-B., Esteves, C., & Becerra, H. M. (2020). Coupling humanoid walking pattern generation and visual constraint feedback for pose-regulation and visual path-following. Robotics and Autonomous Systems, 128, 103497.","journal-title":"Robotics and Autonomous Systems"},{"key":"10160_CR4","unstructured":"Amos, B., Jimenez, I., Sacks, J., Boots, B., & Kolter, J.\u00a0Z. (2018). Differentiable MPC for end-to-end planning and control. In Advances in neural information processing systems (Vol.\u00a031)."},{"key":"10160_CR5","doi-asserted-by":"crossref","unstructured":"Ayari, A., & Knani, J. (2018). The generation of a stable walking trajectory of a bipedal robot based on the COG based gain pattern and ZMP constraint. International Journal of Advanced Computer Science and Applications (IJASCA), 9(9).","DOI":"10.14569\/IJACSA.2018.090945"},{"issue":"01","key":"10160_CR6","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1142\/S0219843607000960","volume":"4","author":"Y Ayaz","year":"2007","unstructured":"Ayaz, Y., Munawar, K., Malik, M. B., Konno, A., & Uchiyama, M. (2007). Human-like approach to footstep planning among obstacles for humanoid robots. International Journal of Humanoid Robotics, 4(01), 125\u2013149.","journal-title":"International Journal of Humanoid Robotics"},{"key":"10160_CR7","doi-asserted-by":"crossref","unstructured":"Brandenburger, A., Rodriguez, D., & Behnke, S. (2021). Mapless humanoid navigation using learned latent dynamics. In 2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 1555\u20131561). IEEE.","DOI":"10.1109\/IROS51168.2021.9636593"},{"key":"10160_CR8","doi-asserted-by":"crossref","unstructured":"Chebotar, Y., Handa, A., Makoviychuk, V., Macklin, M., Issac, J., Ratliff, N., & Fox, D. (2019). Closing the sim-to-real loop: Adapting simulation randomization with real world experience. In 2019 international conference on robotics and automation (ICRA) (pp. 8973\u20138979). IEEE.","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"10160_CR9","doi-asserted-by":"crossref","unstructured":"Chestnutt, J., Lau, M., Cheung, G., Kuffner, J., Hodgins, J., & Kanade, T. (2005). Footstep planning for the honda asimo humanoid. In Proceedings of the 2005 IEEE international conference on robotics and automation (pp. 629\u2013634). IEEE.","DOI":"10.1109\/ROBOT.2005.1570188"},{"key":"10160_CR10","doi-asserted-by":"crossref","unstructured":"Chestnutt, J., Nishiwaki, K., Kuffner, J., & Kagami, S. (2007). An adaptive action model for legged navigation planning. In 2007 7th IEEE-RAS international conference on humanoid robots (pp. 196\u2013202). IEEE.","DOI":"10.1109\/ICHR.2007.4813868"},{"key":"10160_CR11","doi-asserted-by":"crossref","unstructured":"Chestnutt, J., & Kuffner, J.\u00a0J. (2004). A tiered planning strategy for biped navigation. In 4th IEEE\/RAS international conference on humanoid robots, (Vol.\u00a01, pp. 422\u2013436). IEEE.","DOI":"10.1109\/ICHR.2004.1442135"},{"issue":"11","key":"10160_CR12","doi-asserted-by":"publisher","first-page":"1701","DOI":"10.3390\/electronics11111701","volume":"11","author":"R-L Chung","year":"2022","unstructured":"Chung, R.-L., Hsueh, Y., Chen, S.-L., & Abu, P. A. R. (2022). Efficient and accurate cordic pipelined architecture chip design based on binomial approximation for biped robot. Electronics, 11(11), 1701.","journal-title":"Electronics"},{"key":"10160_CR13","doi-asserted-by":"crossref","unstructured":"Diedam, H., Dimitrov, D., Wieber, P.-B., Mombaur, K., & Diehl, M. (2008). Online walking gait generation with adaptive foot positioning through linear model predictive control. In 2008 IEEE\/RSJ international conference on intelligent robots and systems (pp. 1121\u20131126). IEEE.","DOI":"10.1109\/IROS.2008.4651055"},{"issue":"4\u20135","key":"10160_CR14","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1177\/0278364914550891","volume":"34","author":"M Garcia","year":"2015","unstructured":"Garcia, M., Stasse, O., Hayet, J.-B., Dune, C., Esteves, C., & Laumond, J.-P. (2015). Vision-guided motion primitives for humanoid reactive walking: Decoupled versus coupled approaches. The International Journal of Robotics Research, 34(4\u20135), 402\u2013419.","journal-title":"The International Journal of Robotics Research"},{"key":"10160_CR15","doi-asserted-by":"crossref","unstructured":"Gutmann, J.-S., Fukuchi, M., & Fujita, M. (2005). A modular architecture for humanoid robot navigation. In 5th IEEE-RAS international conference on humanoid robots (pp. 26\u201331). IEEE.","DOI":"10.1109\/ICHR.2005.1573540"},{"key":"10160_CR16","doi-asserted-by":"crossref","unstructured":"Ha, I., Tamura, Y., & Asama, H. (2011). Gait pattern generation and stabilization for humanoid robot based on coupled oscillators. In 2011 IEEE\/RSJ international conference on intelligent robots and systems (pp. 3207\u20133212). IEEE.","DOI":"10.1109\/IROS.2011.6095061"},{"key":"10160_CR17","doi-asserted-by":"crossref","unstructured":"Herdt, A., Perrin, N., & Wieber, P.-B. (2010). Walking without thinking about it. In IEEE\/RSJ international conference on intelligent robots and systems (pp. 190\u2013195). IEEE.","DOI":"10.1109\/IROS.2010.5654429"},{"issue":"5\u20136","key":"10160_CR18","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1163\/016918610X493552","volume":"24","author":"A Herdt","year":"2010","unstructured":"Herdt, A., Diedam, H., Wieber, P.-B., Dimitrov, D., Mombaur, K., & Diehl, M. (2010). Online walking motion generation with automatic footstep placement. Advanced Robotics, 24(5\u20136), 719\u2013737.","journal-title":"Advanced Robotics"},{"key":"10160_CR19","unstructured":"Hildebrandt, A.-C., Wahrmann, D., Wittmann, R., & Rixen, D., (2016). Autonomous robotics: Application on legged and agricultural robots. In DGR-Days."},{"key":"10160_CR20","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wu, J., & Lv, C. (2022). Efficient deep reinforcement learning with IMITAtive expert principles for autonomous driving. In IEEE transactions on neural networks and learning systems.","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"10160_CR21","unstructured":"Jaderberg, M., Mnih, V., Czarnecki, W.\u00a0M., Schaul, T., Leibo, J.\u00a0Z., Silver, D., & Kavukcuoglu, K. (2016). Reinforcement learning with unsupervised auxiliary tasks. arXiv preprint arXiv:1611.05397."},{"key":"10160_CR22","doi-asserted-by":"crossref","unstructured":"Kahn, G., Villaflor, A., Ding, B., Abbeel, P., & Levine, S. (2018). Self-supervised deep reinforcement learning with generalized computation graphs for robot navigation. In IEEE international conference on robotics and automation (ICRA) (pp. 5129\u20135136). IEEE.","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"10160_CR23","doi-asserted-by":"crossref","unstructured":"Kajita, S., Hirukawa, H., Harada, K., & Yokoi, K. (2014). Introduction to humanoid robotics (Vol. 101). Springer.","DOI":"10.1007\/978-3-642-54536-8"},{"key":"10160_CR24","doi-asserted-by":"crossref","unstructured":"Kajita, S., Hirukawa, H., Harada, K., & Yokoi, K. (2014). Introduction to humanoid robotics.","DOI":"10.1007\/978-3-642-54536-8"},{"key":"10160_CR25","doi-asserted-by":"crossref","unstructured":"Kuffner, J.\u00a0J., Nishiwaki, K., Kagami, S., Inaba, M., & Inoue, H. (2001). Footstep planning among obstacles for biped robots. In Proceedings 2001 IEEE\/RSJ international conference on intelligent robots and systems. Expanding the societal role of robotics in the the next millennium (cat. no. 01CH37180) (Vol.\u00a01, pp. 500\u2013505). IEEE.","DOI":"10.1109\/IROS.2001.973406"},{"key":"10160_CR26","doi-asserted-by":"crossref","unstructured":"Kuffner, J., Nishiwaki, K., Kagami, S., Inaba, M., & Inoue, H. (2005). Motion planning for humanoid robots. In Robotics research. The 11th international symposium: With 303 figures (pp. 365\u2013374). Springer.","DOI":"10.1007\/11008941_39"},{"key":"10160_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106088","volume":"89","author":"PB Kumar","year":"2020","unstructured":"Kumar, P. B., Muni, M. K., & Parhi, D. R. (2020). Navigational analysis of multiple humanoids using a hybrid regression-fuzzy logic control approach in complex terrains. Applied Soft Computing, 89, 106088.","journal-title":"Applied Soft Computing"},{"key":"10160_CR28","doi-asserted-by":"crossref","unstructured":"Kusuma, M., & Machbub, C. (2019). Humanoid robot path planning and rerouting using a\u2014star search algorithm. In 2019 IEEE international conference on signals and systems (ICSigSys) (pp. 110\u2013115). IEEE.","DOI":"10.1109\/ICSIGSYS.2019.8811093"},{"key":"10160_CR29","unstructured":"Lillicrap, T.\u00a0P., Hunt, J.\u00a0J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971."},{"issue":"4","key":"10160_CR30","doi-asserted-by":"publisher","first-page":"3247","DOI":"10.1109\/LRA.2018.2851148","volume":"3","author":"K Lobos-Tsunekawa","year":"2018","unstructured":"Lobos-Tsunekawa, K., Leiva, F., & Ruiz-delSolar, J. (2018). Visual navigation for biped humanoid robots using deep reinforcement learning. IEEE Robotics and Automation Letters, 3(4), 3247\u20133254.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10160_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119251","volume":"213","author":"A Mahapatro","year":"2023","unstructured":"Mahapatro, A., Dhal, P. R., Parhi, D. R., Muni, M. K., Sahu, C., & Patra, S. K. (2023). Towards stabilization and navigational analysis of humanoids in complex arena using a hybridized fuzzy embedded pid controller approach. Expert Systems with Applications, 213, 119251.","journal-title":"Expert Systems with Applications"},{"issue":"6","key":"10160_CR32","doi-asserted-by":"publisher","first-page":"1928","DOI":"10.1002\/oca.2601","volume":"41","author":"MR Maximo","year":"2020","unstructured":"Maximo, M. R., & Afonso, R. J. (2020). Mixed-integer quadratic programming for automatic walking footstep placement, duration, and rotation. Optimal Control Applications and Methods, 41(6), 1928\u20131963.","journal-title":"Optimal Control Applications and Methods"},{"issue":"12","key":"10160_CR33","doi-asserted-by":"publisher","first-page":"5177","DOI":"10.1016\/j.eswa.2015.02.033","volume":"42","author":"O Montiel","year":"2015","unstructured":"Montiel, O., Orozco-Rosas, U., & Sep\u00falveda, R. (2015). Path planning for mobile robots using bacterial potential field for avoiding static and dynamic obstacles. Expert Systems with Applications, 42(12), 5177\u20135191.","journal-title":"Expert Systems with Applications"},{"key":"10160_CR34","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Kanoulas, D., Caldwell, D.\u00a0G., & Tsagarakis, N.\u00a0G. (2016). Detecting object affordances with convolutional neural networks. In 2016 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 2765\u20132770). IEEE.","DOI":"10.1109\/IROS.2016.7759429"},{"key":"10160_CR35","doi-asserted-by":"crossref","unstructured":"Okada, K., Ogura, T., Haneda, A., & Inaba, M. (2005). Autonomous 3d walking system for a humanoid robot based on visual step recognition and 3d foot step planner. In Proceedings of the 2005 IEEE international conference on robotics and automation (pp. 623\u2013628). IEEE.","DOI":"10.1109\/ROBOT.2005.1570187"},{"key":"10160_CR36","doi-asserted-by":"crossref","unstructured":"Peng, M., Gong, Z., Sun, C., Chen, L., & Cao, D. (2020). Imitative reinforcement learning fusing vision and pure pursuit for self-driving. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 3298\u20133304). IEEE.","DOI":"10.1109\/ICRA40945.2020.9197027"},{"key":"10160_CR37","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1007\/s13042-017-0660-1","volume":"10","author":"M Raj","year":"2019","unstructured":"Raj, M., Semwal, V. B., & Nandi, G. C. (2019). Multiobjective optimized bipedal locomotion. International Journal of Machine Learning and Cybernetics, 10, 1997\u20132013.","journal-title":"International Journal of Machine Learning and Cybernetics"},{"issue":"6","key":"10160_CR38","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1016\/j.dt.2018.03.008","volume":"14","author":"AK Rath","year":"2018","unstructured":"Rath, A. K., Parhi, D. R., Das, H. C., Muni, M. K., & Kumar, P. B. (2018). Analysis and use of fuzzy intelligent technique for navigation of humanoid robot in obstacle prone zone. Defence Technology, 14(6), 677\u2013682.","journal-title":"Defence Technology"},{"issue":"02","key":"10160_CR39","doi-asserted-by":"publisher","first-page":"2050013","DOI":"10.1142\/S0219843620500139","volume":"17","author":"P Regier","year":"2020","unstructured":"Regier, P., Milioto, A., Stachniss, C., & Bennewitz, M. (2020). Classifying obstacles and exploiting class information for humanoid navigation through cluttered environments. International Journal of Humanoid Robotics, 17(02), 2050013.","journal-title":"International Journal of Humanoid Robotics"},{"key":"10160_CR40","unstructured":"R\u00f6fer, T., Laue, T., Kuball, J., L\u00fcbken, A., Maa\u00df, F., M\u00fcller, J., Post, L., Richter-Klug, J., Schulz, P., & Stolpmann, A. (2016). B-human: Team Report and Code Release 2016. Deutschen Forschungszentrums f\u00fcr K\u00fcnstliche Intelligenz (DFKI) GmbH."},{"key":"10160_CR41","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347."},{"key":"10160_CR42","doi-asserted-by":"crossref","unstructured":"Sherikov, A., Dimitrov, D., & Wieber, P.-B. (2014). Whole body motion controller with long-term balance constraints. In 2014 IEEE-RAS international conference on humanoid robots (pp. 444\u2013450). IEEE.","DOI":"10.1109\/HUMANOIDS.2014.7041399"},{"issue":"12","key":"10160_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. (2012). A literature review on the optimization of legged robots. Journal of Vibration and Control, 18(12), 1753\u20131767.","journal-title":"Journal of Vibration and Control"},{"key":"10160_CR44","unstructured":"Sugihara*, T. (2002). Realtime humanoid motion generation through zmp manipulation based on inverted pendulum control. In Porc. of proc. IEEE int. conf. on robotics and automation."},{"key":"10160_CR45","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017). Domain randomization for transferring deep neural networks from simulation to the real world. In IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 23\u201330). IEEE.","DOI":"10.1109\/IROS.2017.8202133"},{"issue":"01","key":"10160_CR46","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1142\/S0219843604000083","volume":"1","author":"M Vukobratovi\u0107","year":"2004","unstructured":"Vukobratovi\u0107, M., & Borovac, B. (2004). Zero-moment point-thirty five years of its life. International Journal of Humanoid Robotics, 1(01), 157\u2013173.","journal-title":"International Journal of Humanoid Robotics"},{"key":"10160_CR47","doi-asserted-by":"crossref","unstructured":"Wiering, M., & Otterlo, M. V. (2012). Reinforcement learning: State of the art. Springer.","DOI":"10.1007\/978-3-642-27645-3"},{"key":"10160_CR48","doi-asserted-by":"crossref","unstructured":"Yamamoto, T., & Sugihara, T. (2021). Responsive navigation of a biped robot that takes into account terrain, foot-reachability and capturability. Advanced Robotics, 35(8), 516\u2013530.","DOI":"10.1080\/01691864.2021.1896382"},{"issue":"2","key":"10160_CR49","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/LRA.2020.2972879","volume":"5","author":"C Yang","year":"2020","unstructured":"Yang, C., Yuan, K., Heng, S., Komura, T., & Li, Z. (2020). Learning natural locomotion behaviors for humanoid robots using human bias. IEEE Robotics and Automation Letters, 5(2), 2610\u20132617.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"1","key":"10160_CR50","doi-asserted-by":"publisher","first-page":"35","DOI":"10.5772\/62245","volume":"13","author":"J Yi","year":"2016","unstructured":"Yi, J., Zhu, Q., Xiong, R., & Wu, J. (2016). Walking algorithm of humanoid robot on uneven terrain with terrain estimation. International Journal of Advanced Robotic Systems, 13(1), 35.","journal-title":"International Journal of Advanced Robotic Systems"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-024-10160-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-024-10160-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-024-10160-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T10:08:28Z","timestamp":1719482908000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-024-10160-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,17]]},"references-count":50,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10160"],"URL":"https:\/\/doi.org\/10.1007\/s10514-024-10160-w","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"type":"print","value":"0929-5593"},{"type":"electronic","value":"1573-7527"}],"subject":[],"published":{"date-parts":[[2024,4,17]]},"assertion":[{"value":"7 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors have no conflicts of interest. On behalf of all authors, the corresponding author states that there is no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The ethics committee approval from the authors\u2019 institution informed consent has been obtained for this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"5"}}