{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T18:44:54Z","timestamp":1648838694711},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T00:00:00Z","timestamp":1470268800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2017,4]]},"DOI":"10.1007\/s10514-016-9604-y","type":"journal-article","created":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T07:16:05Z","timestamp":1470294965000},"page":"1013-1026","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A confidence-based roadmap using Gaussian process regression"],"prefix":"10.1007","volume":"41","author":[{"given":"Yuya","family":"Okadome","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutaka","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,8,4]]},"reference":[{"key":"9604_CR1","unstructured":"Asmuth, J., & Littman, M.\u00a0L. (2011). Learning is planning: Near Bayes-optimal reinforcement learning via Monte-Carlo tree search. In Uncertainty in Artificial Intelligence."},{"issue":"7","key":"9604_CR2","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1177\/0278364911406562","volume":"30","author":"JVD Berg","year":"2011","unstructured":"Berg, J. V. D., et al. (2011). LQG-MP: Optimized path planning for robots with motion uncertainty and imperfect state information. The International Journal of Robotics Research, 30(7), 895\u2013913.","journal-title":"The International Journal of Robotics Research"},{"key":"9604_CR3","unstructured":"Bishop, C.\u00a0M. (2006). Pattern recognition and machine learning (1st ed.). Springer. corr. 2nd printing edn."},{"key":"9604_CR4","doi-asserted-by":"crossref","unstructured":"Bry, A., & Roy, N. (2011). Rapidly-exploring Random Belief Trees for motion planning under uncertainty. In 2011 IEEE international conference on robotics and automation (ICRA) (pp. 723\u2013730).","DOI":"10.1109\/ICRA.2011.5980508"},{"key":"9604_CR5","volume-title":"Principles of robot motion: Theory, algorithms, and implementations","author":"H\u00a0M Choset","year":"2005","unstructured":"Choset, H\u00a0. M. (2005). Principles of robot motion: Theory, algorithms, and implementations. Cambridge: MIT Press."},{"key":"9604_CR6","unstructured":"Chrisman, L. (1992). Reinforcement learning with perceptual aliasing: The perceptual distinctions approach. In AAAI (pp. 183\u2013188)."},{"issue":"9\u201310","key":"9604_CR7","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1177\/0278364913481250","volume":"32","author":"S Dalibard","year":"2013","unstructured":"Dalibard, S., et al. (2013). Dynamic walking and whole-body motion planning for humanoid robots: An integrated approach. The International Journal of Robotics Research, 32(9\u201310), 1089\u20131103.","journal-title":"The International Journal of Robotics Research"},{"issue":"3","key":"9604_CR8","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1145\/3828.3830","volume":"32","author":"R Dechter","year":"1985","unstructured":"Dechter, R., & Pearl, J. (1985). Generalized best-first search strategies and the optimality of A*. Journal of the ACM (JACM), 32(3), 505\u2013536.","journal-title":"Journal of the ACM (JACM)"},{"key":"9604_CR9","unstructured":"Deisenroth, M.\u00a0P., & Rasmussen, C.\u00a0E. (2011). PILCO: A model-based and data-efficient approach to policy search. In In Proceedings of the International Conference on Machine Learning."},{"issue":"1","key":"9604_CR10","doi-asserted-by":"crossref","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"},{"issue":"1","key":"9604_CR11","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1162\/089976600300015961","volume":"12","author":"K Doya","year":"2000","unstructured":"Doya, K. (2000). Reinforcement learning in continuous time and space. Neural Computation, 12(1), 219\u2013245.","journal-title":"Neural Computation"},{"key":"9604_CR12","first-page":"857","volume":"10","author":"L Foster","year":"2009","unstructured":"Foster, L., et al. (2009). Stable and efficient Gaussian Process calculations. Journal of Machine Learning Research, 10, 857\u2013882.","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"9604_CR13","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TSMCB.2011.2170565","volume":"42","author":"I Grondman","year":"2012","unstructured":"Grondman, I., et al. (2012). Efficient model learning methods for actor critic control. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 42(3), 591\u2013602.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)"},{"key":"9604_CR14","doi-asserted-by":"crossref","unstructured":"Hinton, G.\u00a0E. (2002). Training products of experts by minimizing contrastive divergence. Neural computation, 14, 1771\u20131800.","DOI":"10.1162\/089976602760128018"},{"key":"9604_CR15","doi-asserted-by":"crossref","unstructured":"Ijspeert, A.\u00a0J. (2008). Central pattern generators for locomotion control in animals and robots: A review. Neural Networks 21(4), 642\u2013653. Robotics and Neuroscience.","DOI":"10.1016\/j.neunet.2008.03.014"},{"key":"9604_CR16","doi-asserted-by":"crossref","unstructured":"Indyk, P., & Motwani, R. (1998). Approximate nearest neighbors: towards removing the curse of dimensionality. In Proceedings of the thirtieth annual ACM symposium on theory of computing, STOC \u201998 (pp. 604\u2013613). New York, ACM.","DOI":"10.1145\/276698.276876"},{"issue":"4","key":"9604_CR17","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1109\/70.508439","volume":"12","author":"LE Kavraki","year":"1996","unstructured":"Kavraki, L. E., et al. (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":"9604_CR18","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s10514-009-9119-x","volume":"27","author":"J Ko","year":"2009","unstructured":"Ko, J., & Fox, D. (2009). GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation models. Autonomous Robots, 27, 75\u201390.","journal-title":"Autonomous Robots"},{"issue":"5","key":"9604_CR19","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1109\/TCST.2008.2012116","volume":"17","author":"Y Kuwata","year":"2009","unstructured":"Kuwata, Y., et al. (2009). Real-time motion planning with applications to autonomous urban driving. IEEE Transactions on Control Systems Technology, 17(5), 1105\u20131118.","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"9604_CR20","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511546877","volume-title":"Planning algorithms","author":"S\u00a0M LaValle","year":"2006","unstructured":"LaValle, S\u00a0. M. (2006). Planning algorithms. Cambridge: Cambridge University Press."},{"issue":"5","key":"9604_CR21","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1177\/02783640122067453","volume":"20","author":"SM LaValle","year":"2001","unstructured":"LaValle, S. M., & Kuffner, J. J. (2001). Randomized kinodynamic planning. The International Journal of Robotics Research, 20(5), 378\u2013400.","journal-title":"The International Journal of Robotics Research"},{"key":"9604_CR22","unstructured":"Lawrence, N. D. (2004). Gaussian process latent variable models for visualisation of high dimensional data. Advances in neural information systems, 16, 329\u2013336."},{"key":"9604_CR23","doi-asserted-by":"crossref","unstructured":"Marco, A., et\u00a0al. (2016). Automatic LQR tuning based on Gaussian process global optimization. In 2016 IEEE international conference on robotics and automation (ICRA), (pp. 270\u2013277).","DOI":"10.1109\/ICRA.2016.7487144"},{"key":"9604_CR24","doi-asserted-by":"crossref","unstructured":"Mukadam, M., et\u00a0al. (2016). Gaussian process motion planning. In 2016 IEEE international conference on robotics and automation (ICRA) (pp. 9\u201315).","DOI":"10.1109\/ICRA.2016.7487091"},{"key":"9604_CR25","doi-asserted-by":"crossref","unstructured":"Okadome, Y., et\u00a0al. (2013). Fast approximation method for Gaussian process regression using hash function for non-uniformly distributed data. In Artificial neural networks and machine learning (pp. 17\u201325).","DOI":"10.1007\/978-3-642-40728-4_3"},{"key":"9604_CR26","doi-asserted-by":"crossref","unstructured":"Okadome, Y., et\u00a0al. (2014). Confidence-based roadmap using Gaussian process regression for a robot control. In 2014 IEEE\/RSJ international conference on intelligent robots and systems (IROS 2014) (pp. 661\u2013666).","DOI":"10.1109\/IROS.2014.6942629"},{"issue":"4","key":"9604_CR27","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1016\/j.neunet.2008.02.003","volume":"21","author":"J Peters","year":"2008","unstructured":"Peters, J., & Schaal, S. (2008). Reinforcement learning of motor skills with policy gradients. Neural Networks, 21(4), 682\u2013697.","journal-title":"Neural Networks"},{"issue":"11\u201312","key":"9604_CR28","doi-asserted-by":"crossref","first-page":"1448","DOI":"10.1177\/0278364909341659","volume":"28","author":"S Prentice","year":"2009","unstructured":"Prentice, S., & Roy, N. (2009). The belief roadmap: Efficient planning in belief space by factoring the covariance. The International Journal of Robotics Research, 28(11\u201312), 1448\u20131465.","journal-title":"The International Journal of Robotics Research"},{"key":"9604_CR29","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3206.001.0001","volume-title":"Gaussian processes for machine learning","author":"C\u00a0E Rasmussen","year":"2005","unstructured":"Rasmussen, C\u00a0. E., & Williams, C\u00a0. K\u00a0. I. (2005). Gaussian processes for machine learning. Cambridge: the mit press."},{"key":"9604_CR30","first-page":"1729","volume":"12","author":"S Ross","year":"2011","unstructured":"Ross, S., et al. (2011). A Bayesian approach for learning and planning in partially observable Markov decision processes. The Journal of Machine Learning Research, 12, 1729\u20131770.","journal-title":"The Journal of Machine Learning Research"},{"key":"9604_CR31","doi-asserted-by":"crossref","unstructured":"Spaan, M.\u00a0T.\u00a0J., & Vlassis, N. (2004). \u2018A point-based POMDP algorithm for robot planning\u2019. In IEEE international conference on robotics and automation (Vol. 3, pp. 2399\u20132404). IEEE.","DOI":"10.1109\/ROBOT.2004.1307420"},{"key":"9604_CR32","unstructured":"Sutton, R. S., et al. (2000). Policy gradient method for reinforcement learning with function approximation. In Advances in neural information processing systems (Vol. 12, pp. 1057\u20131063)."},{"key":"9604_CR33","doi-asserted-by":"crossref","unstructured":"Theodorou, E., et\u00a0al. (2010). \u2018Reinforcement learning of motor skills in high dimensions: A path integral approach\u2019. In 2010 IEEE international conference on robotics and automation (ICRA), (pp. 2397 \u20132403).","DOI":"10.1109\/ROBOT.2010.5509336"},{"key":"9604_CR34","unstructured":"Thrun, S. B. (1992). Efficient exploration in reinforcement learning. Tech. rep., Pittsburgh."},{"key":"9604_CR35","doi-asserted-by":"crossref","unstructured":"Todorov, E., & Li, W. (2005). A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic In Proceedings of the 2005, American control conference (Vol. 1, pp. 300\u2013306).","DOI":"10.1109\/ACC.2005.1469949"},{"issue":"2","key":"9604_CR36","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1109\/TPAMI.2007.1167","volume":"30","author":"JM Wang","year":"2008","unstructured":"Wang, J. M., et al. (2008). Gaussian process dynamical models for human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), 283\u2013298.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-016-9604-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10514-016-9604-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-016-9604-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-016-9604-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,12]],"date-time":"2019-09-12T00:37:05Z","timestamp":1568248625000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10514-016-9604-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,4]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,4]]}},"alternative-id":["9604"],"URL":"https:\/\/doi.org\/10.1007\/s10514-016-9604-y","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,8,4]]}}}