{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T02:38:10Z","timestamp":1784169490334,"version":"3.55.0"},"reference-count":117,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,3,20]],"date-time":"2022-03-20T00:00:00Z","timestamp":1647734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,20]],"date-time":"2022-03-20T00:00:00Z","timestamp":1647734400000},"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":["Auton Robot"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s10514-022-10039-8","type":"journal-article","created":{"date-parts":[[2022,3,20]],"date-time":"2022-03-20T11:02:19Z","timestamp":1647774139000},"page":"569-597","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":223,"title":["Motion planning and control for mobile robot navigation using machine learning: a survey"],"prefix":"10.1007","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5151-2186","authenticated-orcid":false,"given":"Xuesu","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Garrett","family":"Warnell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,3,20]]},"reference":[{"key":"10039_CR1","unstructured":"Becker-Ehmck, P., Karl, M., Peters, J., & van\u00a0der Smagt, P. (2020). Learning to fly via deep model-based reinforcement learning. arXiv preprint arXiv:2003.08876"},{"key":"10039_CR2","doi-asserted-by":"crossref","unstructured":"Bhardwaj, M., Boots, B., & Mukadam, M. (2020). Differentiable Gaussian process motion planning. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 10598\u201310604). IEEE.","DOI":"10.1109\/ICRA40945.2020.9197260"},{"key":"10039_CR3","unstructured":"Bojarski, M., Del\u00a0Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et\u00a0al. (2016). End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316"},{"key":"10039_CR4","unstructured":"Bruce, J., S\u00fcnderhauf, N., Mirowski, P., Hadsell, R., & Milford, M. (2017). One-shot reinforcement learning for robot navigation with interactive replay. arXiv preprint arXiv:1711.10137"},{"key":"10039_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., Liu, Y., Kreiss, S., & Alahi, A. (2019). Crowd\u2013robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning. In 2019 international conference on robotics and automation (ICRA) (pp. 6015\u20136022). IEEE.","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"10039_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y. F., Everett, M., Liu, M., & How, J. P. (2017). Socially aware motion planning with deep reinforcement learning. In 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 1343\u20131350). IEEE.","DOI":"10.1109\/IROS.2017.8202312"},{"key":"10039_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y. F., Liu, M., Everett, M., & How, J. P. (2017). Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In 2017 IEEE international conference on robotics and automation (ICRA) (pp. 285\u2013292). IEEE","DOI":"10.1109\/ICRA.2017.7989037"},{"issue":"2","key":"10039_CR8","doi-asserted-by":"publisher","first-page":"2007","DOI":"10.1109\/LRA.2019.2899918","volume":"4","author":"HTL Chiang","year":"2019","unstructured":"Chiang, H. T. L., Faust, A., Fiser, M., & Francis, A. (2019). Learning navigation behaviors end-to-end with autorl. IEEE Robotics and Automation Letters, 4(2), 2007\u20132014.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10039_CR9","unstructured":"Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555"},{"key":"10039_CR10","doi-asserted-by":"crossref","unstructured":"Codevilla, F., Miiller, M., L\u00f3pez, A., Koltun, V., & Dosovitskiy, A. (2018). End-to-end driving via conditional imitation learning. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 1\u20139). IEEE.","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"10039_CR11","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1613\/jair.2994","volume":"39","author":"K Daniel","year":"2010","unstructured":"Daniel, K., Nash, A., Koenig, S., & Felner, A. (2010). Theta*: Any-angle path planning on grids. Journal of Artificial Intelligence Research, 39, 533\u2013579.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10039_CR12","unstructured":"Dennis, M., Jaques, N., Vinitsky, E., Bayen, A., Russell, S., Critch, A., & Levine, S. (2020). Emergent complexity and zero-shot transfer via unsupervised environment design. In Advances in neural information processing systems (Vol.\u00a033, pp. 13049\u201313061). Curran Associates, Inc."},{"issue":"1","key":"10039_CR13","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/BF01386390","volume":"1","author":"EW Dijkstra","year":"1959","unstructured":"Dijkstra, E. W. (1959). A note on two problems in connexion with graphs. Numerische Mathematik, 1(1), 269\u2013271.","journal-title":"Numerische Mathematik"},{"key":"10039_CR14","doi-asserted-by":"crossref","unstructured":"Ding, W., Li, S., Qian, H., & Chen, Y. (2018). Hierarchical reinforcement learning framework towards multi-agent navigation. In 2018 IEEE international conference on robotics and biomimetics (ROBIO) (pp. 237\u2013242). IEEE.","DOI":"10.1109\/ROBIO.2018.8664803"},{"issue":"2","key":"10039_CR15","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/MRA.2006.1638022","volume":"13","author":"H Durrant-Whyte","year":"2006","unstructured":"Durrant-Whyte, H., & Bailey, T. (2006). Simultaneous localization and mapping: Part I. IEEE Robotics & Automation Magazine, 13(2), 99\u2013110.","journal-title":"IEEE Robotics & Automation Magazine"},{"issue":"6","key":"10039_CR16","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/2.30720","volume":"22","author":"A Elfes","year":"1989","unstructured":"Elfes, A. (1989). Using occupancy grids for mobile robot perception and navigation. Computer, 22(6), 46\u201357.","journal-title":"Computer"},{"key":"10039_CR17","doi-asserted-by":"crossref","unstructured":"Everett, M., Chen, Y. F., & How, J. P. (2018). Motion planning among dynamic, decision-making agents with deep reinforcement learning. In 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 3052\u20133059). IEEE.","DOI":"10.1109\/IROS.2018.8593871"},{"key":"10039_CR18","doi-asserted-by":"crossref","unstructured":"Faust, A., Oslund, K., Ramirez, O., Francis, A., Tapia, L., Fiser, M., & Davidson, J. (2018). Prm-rl: Long-range robotic navigation tasks by combining reinforcement learning and sampling-based planning. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 5113\u20135120). IEEE.","DOI":"10.1109\/ICRA.2018.8461096"},{"issue":"1","key":"10039_CR19","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/100.580977","volume":"4","author":"D Fox","year":"1997","unstructured":"Fox, D., Burgard, W., & Thrun, S. (1997). The dynamic window approach to collision avoidance. IEEE Robotics & Automation Magazine, 4(1), 23\u201333.","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"10039_CR20","unstructured":"Gao, W., Hsu, D., Lee, W. S., Shen, S., & Subramanian, K. (2017). Intention-net: Integrating planning and deep learning for goal-directed autonomous navigation. In Conference on robot learning (pp. 185\u2013194). PMLR."},{"issue":"2","key":"10039_CR21","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/LRA.2015.2509024","volume":"1","author":"A Giusti","year":"2015","unstructured":"Giusti, A., Guzzi, J., Cire\u015fan, D. C., He, F. L., Rodr\u00edguez, J. P., Fontana, F., et al. (2015). A machine learning approach to visual perception of forest trails for mobile robots. IEEE Robotics and Automation Letters, 1(2), 661\u2013667.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"8","key":"10039_CR22","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1007\/s10514-018-9719-4","volume":"42","author":"J Godoy","year":"2018","unstructured":"Godoy, J., Chen, T., Guy, S. J., Karamouzas, I., & Gini, M. (2018). ALAN: Adaptive learning for multi-agent navigation. Autonomous Robots, 42(8), 1543\u20131562.","journal-title":"Autonomous Robots"},{"key":"10039_CR23","doi-asserted-by":"crossref","unstructured":"Gupta, S., Davidson, J., Levine, S., Sukthankar, R., & Malik, J. (2017) Cognitive mapping and planning for visual navigation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2616\u20132625).","DOI":"10.1109\/CVPR.2017.769"},{"key":"10039_CR24","unstructured":"Gupta, S., Fouhey, D., Levine, S., & Malik, J. (2017). Unifying map and landmark based representations for visual navigation. arXiv preprint arXiv:1712.08125"},{"issue":"2","key":"10039_CR25","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/tssc.1968.300136","volume":"4","author":"P Hart","year":"1968","unstructured":"Hart, P., Nilsson, N., & Raphael, B. (1968). A formal basis for the heuristic determination of minimum cost paths. IEEE Transactions on Systems Science and Cybernetics, 4(2), 100\u2013107. https:\/\/doi.org\/10.1109\/tssc.1968.300136.","journal-title":"IEEE Transactions on Systems Science and Cybernetics"},{"key":"10039_CR26","doi-asserted-by":"crossref","unstructured":"Henry, P., Vollmer, C., Ferris, B., & Fox, D. (2010). Learning to navigate through crowded environments. In 2010 IEEE international conference on robotics and automation (pp. 981\u2013986). IEEE.","DOI":"10.1109\/ROBOT.2010.5509772"},{"issue":"8","key":"10039_CR27","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"issue":"4","key":"10039_CR28","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1109\/TRO.2010.2049527","volume":"26","author":"L Jaillet","year":"2010","unstructured":"Jaillet, L., Cort\u00e9s, J., & Sim\u00e9on, T. (2010). Sampling-based path planning on configuration-space costmaps. IEEE Transactions on Robotics, 26(4), 635\u2013646.","journal-title":"IEEE Transactions on Robotics"},{"key":"10039_CR29","doi-asserted-by":"crossref","unstructured":"Jiang, P., Osteen, P., Wigness, M., & Saripalli, S. (2021). Rellis-3d dataset: Data, benchmarks and analysis. In 2021 IEEE international conference on robotics and automation (ICRA) (pp. 1110\u20131116). IEEE.","DOI":"10.1109\/ICRA48506.2021.9561251"},{"key":"10039_CR30","doi-asserted-by":"crossref","unstructured":"Jin, J., Nguyen, N. M., Sakib, N., Graves, D., Yao, H., & Jagersand, M. (2020). Mapless navigation among dynamics with social-safety-awareness: A reinforcement learning approach from 2d laser scans. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 6979\u20136985). IEEE.","DOI":"10.1109\/ICRA40945.2020.9197148"},{"key":"10039_CR31","doi-asserted-by":"crossref","unstructured":"Johnson, C., & Kuipers, B. (2018). Socially-aware navigation using topological maps and social norm learning. In Proceedings of the 2018 AAAI\/ACM conference on AI, ethics, and society (pp. 151\u2013157).","DOI":"10.1145\/3278721.3278772"},{"issue":"2","key":"10039_CR32","doi-asserted-by":"publisher","first-page":"1312","DOI":"10.1109\/LRA.2021.3057023","volume":"6","author":"G Kahn","year":"2021","unstructured":"Kahn, G., Abbeel, P., & Levine, S. (2021). Badgr: An autonomous self-supervised learning-based navigation system. IEEE Robotics and Automation Letters, 6(2), 1312\u20131319.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10039_CR33","unstructured":"Kahn, G., Villaflor, A., Abbeel, P., & Levine, S. (2018) Composable action-conditioned predictors: Flexible off-policy learning for robot navigation. In Conference on robot learning (pp. 806\u2013816). PMLR."},{"key":"10039_CR34","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 2018 IEEE international conference on robotics and automation (ICRA) (pp. 1\u20138). IEEE.","DOI":"10.1109\/ICRA.2018.8460655"},{"issue":"7","key":"10039_CR35","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1177\/0278364911406761","volume":"30","author":"S Karaman","year":"2011","unstructured":"Karaman, S., & Frazzoli, E. (2011). Sampling-based algorithms for optimal motion planning. The International Journal of Robotics Research, 30(7), 846\u2013894.","journal-title":"The International Journal of Robotics Research"},{"issue":"4","key":"10039_CR36","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/70.508439","volume":"12","author":"LE Kavraki","year":"1996","unstructured":"Kavraki, L. E., Svestka, P., Latombe, J. C., & Overmars, M. H. (1996). Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation, 12(4), 566\u2013580.","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"10039_CR37","unstructured":"Khan, A., Zhang, C., Atanasov, N., Karydis, K., Kumar, V., & Lee, D. D. (2018). Memory augmented control networks. In International conference on learning representations (ICLR)."},{"issue":"1","key":"10039_CR38","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s12369-015-0310-2","volume":"8","author":"B Kim","year":"2016","unstructured":"Kim, B., & Pineau, J. (2016). Socially adaptive path planning in human environments using inverse reinforcement learning. International Journal of Social Robotics, 8(1), 51\u201366.","journal-title":"International Journal of Social Robotics"},{"key":"10039_CR39","unstructured":"Koenig, S., & Likhachev, M. (2002). D$$\\hat{\\,}{}^{*}$$ lite. In AAAI\/IAAI (Vol. 15)."},{"issue":"11","key":"10039_CR40","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1177\/0278364915619772","volume":"35","author":"H Kretzschmar","year":"2016","unstructured":"Kretzschmar, H., Spies, M., Sprunk, C., & Burgard, W. (2016). Socially compliant mobile robot navigation via inverse reinforcement learning. The International Journal of Robotics Research, 35(11), 1289\u20131307.","journal-title":"The International Journal of Robotics Research"},{"key":"10039_CR41","first-page":"30","volume":"22","author":"O Kroemer","year":"2021","unstructured":"Kroemer, O., Niekum, S., & Konidaris, G. (2021). A review of robot learning for manipulation: Challenges, representations, and algorithms. Journal of Machine Learning Research, 22, 30\u20131.","journal-title":"Journal of Machine Learning Research"},{"key":"10039_CR42","unstructured":"LaValle, S. M. (1998). Rapidly-exploring random trees: A new tool for path planning."},{"key":"10039_CR43","doi-asserted-by":"crossref","unstructured":"LaValle, S. M. (2006). Planning algorithms. Cambridge University Press.","DOI":"10.1017\/CBO9780511546877"},{"key":"10039_CR44","unstructured":"LeCunn, Y., Muller, U., Ben, J., Cosatto, E., & Flepp, B. (2006). Off-road obstacle avoidance through end-to-end learning. In Advances in neural information processing systems (pp. 739\u2013746)."},{"issue":"1","key":"10039_CR45","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1049\/trit.2018.0008","volume":"3","author":"M Li","year":"2018","unstructured":"Li, M., Jiang, R., Ge, S. S., & Lee, T. H. (2018). Role playing learning for socially concomitant mobile robot navigation. CAAI Transactions on Intelligence Technology, 3(1), 49\u201358.","journal-title":"CAAI Transactions on Intelligence Technology"},{"key":"10039_CR46","doi-asserted-by":"crossref","unstructured":"Liang, J., Patel, U., Sathyamoorthy, A. J., & Manocha, D. (2020). Crowd-steer: Realtime smooth and collision-free robot navigation in densely crowded scenarios trained using high-fidelity simulation. In IJCAI (pp. 4221\u20134228).","DOI":"10.24963\/ijcai.2020\/583"},{"key":"10039_CR47","unstructured":"Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"key":"10039_CR48","doi-asserted-by":"crossref","unstructured":"Lin, J., Wang, L., Gao, F., Shen, S., & Zhang, F. (2019). Flying through a narrow gap using neural network: An end-to-end planning and control approach. In 2019 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 3526\u20133533). IEEE.","DOI":"10.1109\/IROS40897.2019.8967944"},{"issue":"2","key":"10039_CR49","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1109\/LRA.2021.3056373","volume":"6","author":"B Liu","year":"2021","unstructured":"Liu, B., Xiao, X., & Stone, P. (2021). A lifelong learning approach to mobile robot navigation. IEEE Robotics and Automation Letters, 6(2), 1090\u20131096.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10039_CR50","doi-asserted-by":"crossref","unstructured":"Long, P., Fanl, T., Liao, X., Liu, W., Zhang, H., & Pan, J. (2018). Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 6252\u20136259). IEEE.","DOI":"10.1109\/ICRA.2018.8461113"},{"key":"10039_CR51","unstructured":"Lopez-Paz, D., & Ranzato, M. (2017). Gradient episodic memory for continual learning. In Advances in neural information processing systems (pp. 6467\u20136476)."},{"issue":"2","key":"10039_CR52","doi-asserted-by":"publisher","first-page":"1088","DOI":"10.1109\/LRA.2018.2795643","volume":"3","author":"A Loquercio","year":"2018","unstructured":"Loquercio, A., Maqueda, A. I., Del-Blanco, C. R., & Scaramuzza, D. (2018). Dronet: Learning to fly by driving. IEEE Robotics and Automation Letters, 3(2), 1088\u20131095.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10039_CR53","doi-asserted-by":"crossref","unstructured":"Lu, D. V., Hershberger, D., & Smart, W. D. (2014). Layered costmaps for context-sensitive navigation. In 2014 IEEE\/RSJ international conference on intelligent robots and systems (pp. 709\u2013715). IEEE.","DOI":"10.1109\/IROS.2014.6942636"},{"key":"10039_CR54","doi-asserted-by":"crossref","unstructured":"Luber, M., Spinello, L., Silva, J., & Arras, K. O. (2012). Socially-aware robot navigation: A learning approach. In 2012 IEEE\/RSJ international conference on intelligent robots and systems (pp. 902\u2013907). IEEE.","DOI":"10.1109\/IROS.2012.6385716"},{"key":"10039_CR55","doi-asserted-by":"crossref","unstructured":"Martins, G. S., Rocha, R. P., Pais, F. J., & Menezes, P. (2019). Clusternav: Learning-based robust navigation operating in cluttered environments. In 2019 international conference on robotics and automation (ICRA) (pp. 9624\u20139630). IEEE.","DOI":"10.1109\/ICRA.2019.8794262"},{"key":"10039_CR56","unstructured":"Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., & Kavukcuoglu, K. (2016). Asynchronous methods for deep reinforcement learning. In International conference on machine learning (pp. 1928\u20131937)."},{"key":"10039_CR57","doi-asserted-by":"crossref","unstructured":"Nist\u00e9r, D., Naroditsky, O., & Bergen, J. (2004). Visual odometry. In Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition, 2004. CVPR 2004 (Vol. 1, p. I). IEEE.","DOI":"10.1109\/CVPR.2004.1315094"},{"key":"10039_CR58","doi-asserted-by":"crossref","unstructured":"Okal, B., & Arras, K. O. (2016). Learning socially normative robot navigation behaviors with Bayesian inverse reinforcement learning. In 2016 IEEE international conference on robotics and automation (ICRA) (pp. 2889\u20132895). IEEE.","DOI":"10.1109\/ICRA.2016.7487452"},{"key":"10039_CR59","unstructured":"OSRF. (2018). Ros wiki move_base. http:\/\/wiki.ros.org\/move_base"},{"key":"10039_CR60","unstructured":"Palmieri, L., & Arras, K. O. (2014). Efficient and smooth RRT motion planning using a novel extend function for wheeled mobile robots. In IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 205\u2013211)."},{"issue":"2\u20133","key":"10039_CR61","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1177\/0278364919880273","volume":"39","author":"Y Pan","year":"2020","unstructured":"Pan, Y., Cheng, C. A., Saigol, K., Lee, K., Yan, X., Theodorou, E. A., & Boots, B. (2020). Imitation learning for agile autonomous driving. The International Journal of Robotics Research, 39(2\u20133), 286\u2013302.","journal-title":"The International Journal of Robotics Research"},{"key":"10039_CR62","unstructured":"Park, J. J. (2016). Graceful navigation for mobile robots in dynamic and uncertain environments. Ph.D. thesis."},{"key":"10039_CR63","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Higueras, N., Caballero, F., & Merino, L. (2018). Learning human-aware path planning with fully convolutional networks. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICRA.2018.8460851"},{"issue":"2","key":"10039_CR64","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/s12369-017-0448-1","volume":"10","author":"N P\u00e9rez-Higueras","year":"2018","unstructured":"P\u00e9rez-Higueras, N., Caballero, F., & Merino, L. (2018). Teaching robot navigation behaviors to optimal RRT planners. International Journal of Social Robotics, 10(2), 235\u2013249.","journal-title":"International Journal of Social Robotics"},{"key":"10039_CR65","doi-asserted-by":"crossref","unstructured":"Pfeiffer, M., Schaeuble, M., Nieto, J., Siegwart, R., & Cadena, C. (2017). From perception to decision: A data-driven approach to end-to-end motion planning for autonomous ground robots. In 2017 IEEE international conference on robotics and automation (ICRA) (pp. 1527\u20131533). IEEE.","DOI":"10.1109\/ICRA.2017.7989182"},{"key":"10039_CR66","doi-asserted-by":"crossref","unstructured":"Pfeiffer, M., Schwesinger, U., Sommer, H., Galceran, E., & Siegwart, R. (2016). Predicting actions to act predictably: Cooperative partial motion planning with maximum entropy models. In 2016 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 2096\u20132101). IEEE.","DOI":"10.1109\/IROS.2016.7759329"},{"issue":"4","key":"10039_CR67","doi-asserted-by":"publisher","first-page":"4423","DOI":"10.1109\/LRA.2018.2869644","volume":"3","author":"M Pfeiffer","year":"2018","unstructured":"Pfeiffer, M., Shukla, S., Turchetta, M., Cadena, C., Krause, A., Siegwart, R., & Nieto, J. (2018). Reinforced imitation: Sample efficient deep reinforcement learning for mapless navigation by leveraging prior demonstrations. IEEE Robotics and Automation Letters, 3(4), 4423\u20134430.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10039_CR68","doi-asserted-by":"crossref","unstructured":"Pokle, A., Mart\u00edn-Mart\u00edn, R., Goebel, P., Chow, V., Ewald, H. M., Yang, J., Wang, Z., Sadeghian, A., Sadigh, D., Savarese, S.,et\u00a0al. (2019). Deep local trajectory replanning and control for robot navigation. In 2019 international conference on robotics and automation (ICRA) (pp. 5815\u20135822). IEEE.","DOI":"10.1109\/ICRA.2019.8794062"},{"key":"10039_CR69","unstructured":"Pomerleau, D. A. (1989). Alvinn: An autonomous land vehicle in a neural network. In Advances in neural information processing systems (pp. 305\u2013313)."},{"key":"10039_CR70","doi-asserted-by":"crossref","unstructured":"Quinlan, S., & Khatib, O. (1993). Elastic bands: Connecting path planning and control. In [1993] Proceedings IEEE international conference on robotics and automation (pp. 802\u2013807). IEEE.","DOI":"10.1109\/ROBOT.1993.291936"},{"key":"10039_CR71","unstructured":"Ramachandran, D., & Amir, E. (2007). Bayesian inverse reinforcement learning. In IJCAI (Vol. 7, pp. 2586\u20132591)."},{"key":"10039_CR72","doi-asserted-by":"crossref","unstructured":"Richter, C., & Roy, N. (2017). Safe visual navigation via deep learning and novelty detection. In Robotics: Science and systems (RSS).","DOI":"10.15607\/RSS.2017.XIII.064"},{"key":"10039_CR73","unstructured":"Ross, S., Gordon, G., & Bagnell, D. (2011). A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 627\u2013635)."},{"key":"10039_CR74","doi-asserted-by":"crossref","unstructured":"Ross, S., Melik-Barkhudarov, N., Shankar, K. S., Wendel, A., Dey, D., Bagnell, J. A., & Hebert, M. (2013). Learning monocular reactive UAV control in cluttered natural environments. In 2013 IEEE international conference on robotics and automation (pp. 1765\u20131772). IEEE.","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"10039_CR75","unstructured":"Russell, S. J., & Norvig, P. (2016). Artificial intelligence: A modern approach. Pearson Education Limited."},{"key":"10039_CR76","doi-asserted-by":"crossref","unstructured":"Sadeghi, F., & Levine, S. (2017). CAD2RL: Real single-image flight without a single real image. In Robotics: Science and systems (RSS).","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"10039_CR77","doi-asserted-by":"crossref","unstructured":"Sepulveda, G., Niebles, J. C., & Soto, A. (2018). A deep learning based behavioral approach to indoor autonomous navigation. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 4646\u20134653). IEEE.","DOI":"10.1109\/ICRA.2018.8460646"},{"key":"10039_CR78","unstructured":"Sergeant, J., S\u00fcnderhauf, N., Milford, M., & Upcroft, B. (2015). Multimodal deep autoencoders for control of a mobile robot. In Proceedings of Australasian conference for robotics and automation (ACRA)."},{"key":"10039_CR79","doi-asserted-by":"crossref","unstructured":"Shiarlis, K., Messias, J., & Whiteson, S. (2017). Rapidly exploring learning trees. In 2017 IEEE international conference on robotics and automation (ICRA) (pp. 1541\u20131548). IEEE.","DOI":"10.1109\/ICRA.2017.7989184"},{"key":"10039_CR80","doi-asserted-by":"crossref","unstructured":"Siva, S., Wigness, M., Rogers, J., & Zhang, H. (2019). Robot adaptation to unstructured terrains by joint representation and apprenticeship learning. In Robotics: Science and systems (RSS).","DOI":"10.15607\/RSS.2019.XV.030"},{"key":"10039_CR81","doi-asserted-by":"crossref","unstructured":"Sood, R., Vats, S., & Likhachev, M. (2020). Learning to use adaptive motion primitives in search-based planning for navigation. In 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 6923\u20136929). IEEE.","DOI":"10.1109\/IROS45743.2020.9341055"},{"key":"10039_CR82","unstructured":"Stein, G. J., Bradley, C., & Roy, N. (2018). Learning over subgoals for efficient navigation of structured, unknown environments. In Conference on robot learning (pp. 213\u2013222)."},{"key":"10039_CR83","doi-asserted-by":"crossref","unstructured":"Stratonovich, R. L. (1965). Conditional Markov processes. In Non-linear transformations of stochastic processes (pp. 427\u2013453). Elsevier.","DOI":"10.1016\/B978-1-4832-3230-0.50041-9"},{"key":"10039_CR84","doi-asserted-by":"crossref","unstructured":"Tai, L., Li, S., & Liu, M. (2016). A deep-network solution towards model-less obstacle avoidance. In 2016 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 2759\u20132764). IEEE.","DOI":"10.1109\/IROS.2016.7759428"},{"key":"10039_CR85","unstructured":"Tai, L., & Liu, M. (2016). Deep-learning in mobile robotics-from perception to control systems: A survey on why and why not. arXiv preprint arXiv:1612.07139"},{"key":"10039_CR86","doi-asserted-by":"crossref","unstructured":"Tai, L., Paolo, G., & Liu, M. (2017). Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation. In 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 31\u201336). IEEE.","DOI":"10.1109\/IROS.2017.8202134"},{"key":"10039_CR87","unstructured":"Tai, L., Zhang, J., Liu, M., Boedecker, J., & Burgard, W. (2016). A survey of deep network solutions for learning control in robotics: From reinforcement to imitation. arXiv preprint arXiv:1612.07139"},{"key":"10039_CR88","doi-asserted-by":"crossref","unstructured":"Tai, L., Zhang, J., Liu, M., & Burgard, W. (2018). Socially compliant navigation through raw depth inputs with generative adversarial imitation learning. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 1111\u20131117). IEEE.","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"10039_CR89","doi-asserted-by":"crossref","unstructured":"Tamar, A., Wu, Y., Thomas, G., Levine, S., & Abbeel, P. (2016). Value iteration networks. In Advances in neural information processing systems (pp. 2154\u20132162).","DOI":"10.24963\/ijcai.2017\/700"},{"issue":"9","key":"10039_CR90","doi-asserted-by":"publisher","first-page":"935","DOI":"10.3390\/electronics8090935","volume":"8","author":"D Teso-Fz-Beto\u00f1o","year":"2019","unstructured":"Teso-Fz-Beto\u00f1o, D., Zulueta, E., Fernandez-Gamiz, U., Saenz-Aguirre, A., & Martinez, R. (2019). Predictive dynamic window approach development with artificial neural fuzzy inference improvement. Electronics, 8(9), 935.","journal-title":"Electronics"},{"issue":"4","key":"10039_CR91","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/0921-8890(95)00022-8","volume":"15","author":"S Thrun","year":"1995","unstructured":"Thrun, S. (1995). An approach to learning mobile robot navigation. Robotics and Autonomous Systems, 15(4), 301\u2013319.","journal-title":"Robotics and Autonomous Systems"},{"issue":"1153","key":"10039_CR92","first-page":"405","volume":"203","author":"S Ullman","year":"1979","unstructured":"Ullman, S. (1979). The interpretation of structure from motion. Proceedings of the Royal Society of London. Series B. Biological Sciences, 203(1153), 405\u2013426.","journal-title":"Proceedings of the Royal Society of London. Series B. Biological Sciences"},{"key":"10039_CR93","doi-asserted-by":"crossref","unstructured":"Van Den\u00a0Berg, J., Guy, S. J., Lin, M., & Manocha, D. (2011). Reciprocal n-body collision avoidance. In Robotics research (pp. 3\u201319). Springer.","DOI":"10.1007\/978-3-642-19457-3_1"},{"issue":"4","key":"10039_CR94","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1109\/TG.2018.2849942","volume":"10","author":"Y Wang","year":"2018","unstructured":"Wang, Y., He, H., & Sun, C. (2018). Learning to navigate through complex dynamic environment with modular deep reinforcement learning. IEEE Transactions on Games, 10(4), 400\u2013412.","journal-title":"IEEE Transactions on Games"},{"key":"10039_CR95","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xiao, X., Liu, B., Warnell, G., & Stone, P. (2021). Appli: Adaptive planner parameter learning from interventions. In 2021 IEEE international conference on robotics and automation (ICRA) (pp. 6079\u20136085). IEEE.","DOI":"10.1109\/ICRA48506.2021.9561311"},{"key":"10039_CR96","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xiao, X., Nettekoven, A. J., Umasankar, K., Singh, A., Bommakanti, S., Topcu, U., & Stone, P. (2021). From agile ground to aerial navigation: Learning from learned hallucination. In 2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE.","DOI":"10.1109\/IROS51168.2021.9636402"},{"issue":"4","key":"10039_CR97","doi-asserted-by":"publisher","first-page":"7744","DOI":"10.1109\/LRA.2021.3100940","volume":"6","author":"Z Wang","year":"2021","unstructured":"Wang, Z., Xiao, X., Warnell, G., & Stone, P. (2021). Apple: Adaptive planner parameter learning from evaluative feedback. IEEE Robotics and Automation Letters, 6(4), 7744\u20137749.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"3\u20134","key":"10039_CR98","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C. J., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3\u20134), 279\u2013292.","journal-title":"Machine Learning"},{"key":"10039_CR99","doi-asserted-by":"crossref","unstructured":"Wigness, M., Rogers, J. G., & Navarro-Serment, L. E. (2018). Robot navigation from human demonstration: Learning control behaviors. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 1150\u20131157). IEEE.","DOI":"10.1109\/ICRA.2018.8462900"},{"key":"10039_CR100","doi-asserted-by":"crossref","unstructured":"Xiao, X., Biswas, J., & Stone, P. (2021a). Learning inverse kinodynamics for accurate high-speed off-road navigation on unstructured terrain. IEEE Robotics and Automation Letters, 6(3), 6054\u20136060.","DOI":"10.1109\/LRA.2021.3090023"},{"key":"10039_CR101","doi-asserted-by":"crossref","unstructured":"Xiao, X., Liu, B., & Stone, P. (2021b). Agile robot navigation through hallucinated learning and sober deployment. In 2021 IEEE international conference on robotics and automation (ICRA) (pp. 7316\u20137322). IEEE.","DOI":"10.1109\/ICRA48506.2021.9562117"},{"issue":"3","key":"10039_CR102","doi-asserted-by":"publisher","first-page":"4541","DOI":"10.1109\/LRA.2020.3002217","volume":"5","author":"X Xiao","year":"2020","unstructured":"Xiao, X., Liu, B., Warnell, G., Fink, J., & Stone, P. (2020). Appld: Adaptive planner parameter learning from demonstration. IEEE Robotics and Automation Letters, 5(3), 4541\u20134547.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"2","key":"10039_CR103","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1109\/LRA.2021.3058927","volume":"6","author":"X Xiao","year":"2021","unstructured":"Xiao, X., Liu, B., Warnell, G., & Stone, P. (2021c). Toward agile maneuvers in highly constrained spaces: Learning from hallucination. IEEE Robotics and Automation Letters, 6(2), 1503\u20131510.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10039_CR104","doi-asserted-by":"crossref","unstructured":"Xiao, X., Wang, Z., Xu, Z., Liu, B., Warnell, G., Dhamankar, G., Nair, A., & Stone, P. (2021d). Appl: Adaptive planner parameter learning. arXiv preprint arXiv:2105.07620","DOI":"10.1016\/j.robot.2022.104132"},{"key":"10039_CR105","doi-asserted-by":"crossref","unstructured":"Xie, L., Wang, S., Rosa, S., Markham, A., & Trigoni, N. (2018). Learning with training wheels: Speeding up training with a simple controller for deep reinforcement learning. In 2018 IEEE international conference on robotics and automation (ICRA) (pp. 6276\u20136283). IEEE.","DOI":"10.1109\/ICRA.2018.8461203"},{"key":"10039_CR106","doi-asserted-by":"crossref","unstructured":"Xu, Z., Dhamankar, G., Nair, A., Xiao, X., Warnell, G., Liu, B., Wang, Z., & Stone, P. (2021). Applr: Adaptive planner parameter learning from reinforcement. In 2021 IEEE international conference on robotics and automation (ICRA) (pp. 6086\u20136092). IEEE.","DOI":"10.1109\/ICRA48506.2021.9561647"},{"key":"10039_CR107","unstructured":"Yao, X., Zhang, J., & Oh, J. (2019). Following social groups: Socially compliant autonomous navigation in dense crowds. arXiv preprint arXiv:1911.12063"},{"issue":"18","key":"10039_CR108","doi-asserted-by":"publisher","first-page":"3837","DOI":"10.3390\/s19183837","volume":"19","author":"J Zeng","year":"2019","unstructured":"Zeng, J., Ju, R., Qin, L., Hu, Y., Yin, Q., & Hu, C. (2019). Navigation in unknown dynamic environments based on deep reinforcement learning. Sensors, 19(18), 3837.","journal-title":"Sensors"},{"key":"10039_CR109","doi-asserted-by":"crossref","unstructured":"Zhang, J., Springenberg, J. T., Boedecker, J., & Burgard, W. (2017). Deep reinforcement learning with successor features for navigation across similar environments. In 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 2371\u20132378). IEEE.","DOI":"10.1109\/IROS.2017.8206049"},{"key":"10039_CR110","unstructured":"Zhang, J., Tai, L., Boedecker, J., Burgard, W., & Liu, M. (2017). Neural slam: Learning to explore with external memory. arXiv preprint arXiv:1706.09520"},{"key":"10039_CR111","doi-asserted-by":"crossref","unstructured":"Zhang, T., Kahn, G., Levine, S., & Abbeel, P. (2016). Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search. In 2016 IEEE international conference on robotics and automation (ICRA) (pp. 528\u2013535). IEEE.","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"10039_CR112","doi-asserted-by":"publisher","first-page":"106436","DOI":"10.1016\/j.oceaneng.2019.106436","volume":"191","author":"L Zhao","year":"2019","unstructured":"Zhao, L., & Roh, M. I. (2019). Colregs-compliant multiship collision avoidance based on deep reinforcement learning. Ocean Engineering, 191, 106436.","journal-title":"Ocean Engineering"},{"key":"10039_CR113","unstructured":"Zhelo, O., Zhang, J., Tai, L., Liu, M., & Burgard, W. (2018). Curiosity-driven exploration for mapless navigation with deep reinforcement learning. arXiv preprint arXiv:1804.00456"},{"issue":"1","key":"10039_CR114","doi-asserted-by":"publisher","first-page":"176","DOI":"10.3390\/s19010176","volume":"19","author":"X Zhou","year":"2019","unstructured":"Zhou, X., Gao, Y., & Guan, L. (2019). Towards goal-directed navigation through combining learning based global and local planners. Sensors, 19(1), 176.","journal-title":"Sensors"},{"key":"10039_CR115","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017). Target-driven visual navigation in indoor scenes using deep reinforcement learning. In 2017 IEEE international conference on robotics and automation (ICRA) (pp. 3357\u20133364). IEEE.","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"10039_CR116","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Schwab, D., & Veloso, M. (2019). Learning primitive skills for mobile robots. In 2019 international conference on robotics and automation (ICRA) (pp. 7597\u20137603). IEEE.","DOI":"10.1109\/ICRA.2019.8793688"},{"key":"10039_CR117","unstructured":"Ziebart, B. D., Maas, A. L., Bagnell, J. A., & Dey, A. K. (2008). Maximum entropy inverse reinforcement learning. In AAAI (Vol. 8, pp. 1433\u20131438)."}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-022-10039-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-022-10039-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-022-10039-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T18:28:56Z","timestamp":1655836136000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-022-10039-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,20]]},"references-count":117,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["10039"],"URL":"https:\/\/doi.org\/10.1007\/s10514-022-10039-8","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,20]]},"assertion":[{"value":"24 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}