{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:01:40Z","timestamp":1742994100999,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642015120"},{"type":"electronic","value":"9783642015137"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-01513-7_30","type":"book-chapter","created":{"date-parts":[[2009,5,20]],"date-time":"2009-05-20T07:35:42Z","timestamp":1242804942000},"page":"278-288","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning Control of a Real Mobile Robot Using Approximate Policy Iteration"],"prefix":"10.1007","author":[{"given":"Pengcheng","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Chunming","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qiping","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"30_CR1","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/70.481750","volume":"12","author":"G. Campion","year":"1996","unstructured":"Campion, G.: Structural Properties and Classification of Dynamic Models of Wheeled Mobile Robots. IEEE Trans. on Robotics and Automation\u00a012, 47\u201362 (1996)","journal-title":"IEEE Trans. on Robotics and Automation"},{"key":"30_CR2","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1177\/027836498900800502","volume":"8","author":"J.C. Alexander","year":"1989","unstructured":"Alexander, J.C., Brooks, J.H.: On the Kinematics of Wheeled Mobile Robots. Int. J. of Robotics Research\u00a08, 15\u201327 (1989)","journal-title":"Int. J. of Robotics Research"},{"key":"30_CR3","unstructured":"Chiacchio, P.: Exploiting Redundancy in Minimum-time Path Following Robot Control. In: American Control Conference (1982)"},{"key":"30_CR4","first-page":"2670","volume-title":"32nd Conference on Decision and Control","author":"N. Sarkar","year":"1993","unstructured":"Sarkar, N., Gen, V.: Dynamic Path Following: A New Control Algorithm for Mobile Robots. In: 32nd Conference on Decision and Control, pp. 2670\u20132675. IEEE Press, New York (1993)"},{"key":"30_CR5","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1109\/TRO.2004.837240","volume":"21","author":"P. Coelho","year":"2005","unstructured":"Coelho, P., Numes, U.: Path Following Control of Mobile Robots in Presence of Uncertainties. IEEE Transaction on Robotics\u00a021, 252\u2013261 (2005)","journal-title":"IEEE Transaction on Robotics"},{"key":"30_CR6","first-page":"106","volume-title":"IEEE International Conference on Robotics and Automation","author":"R. Brooks","year":"1987","unstructured":"Brooks, R.: A Hardware Retargetable Distributed Layered Architecture for Mobile Robot Control. In: IEEE International Conference on Robotics and Automation, pp. 106\u2013110. IEEE Press, New York (1987)"},{"key":"30_CR7","first-page":"611","volume":"16","author":"C.L. Chen","year":"2005","unstructured":"Chen, C.L., Chen, C.H.: Reinforcement Learning for Mobile Robot from Reaction to Deliberation. Journal of Systems Engineering and Electronic\u00a016, 611\u2013617 (2005)","journal-title":"Journal of Systems Engineering and Electronic"},{"key":"30_CR8","volume-title":"Reinforcement Learning, an Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning, an Introduction. MIT Press, Cambridge (1998)"},{"key":"30_CR9","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement Learning: A Survey. J. Artif. Intell. Res.\u00a04, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"30_CR10","first-page":"3404","volume-title":"IEEE International Conference on Robotics and Automation","author":"W.D. Smart","year":"2002","unstructured":"Smart, W.D., Kaelbing, L.P.: Effective Reinforcement Learning for Mobile Robots. In: IEEE International Conference on Robotics and Automation, pp. 3404\u20133410. IEEE Press, New York (2002)"},{"key":"30_CR11","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1109\/TNN.2007.899161","volume":"18","author":"X. Xu","year":"2007","unstructured":"Xu, X., Hu, D.W., Lu, X.C.: Kernel-Based Least Squares Policy Iteration for Reinforcement Learning. IEEE Transaction on Neural Networks\u00a018, 973\u2013992 (2007)","journal-title":"IEEE Transaction on Neural Networks"},{"key":"30_CR12","first-page":"672","volume":"33","author":"C. Canudas","year":"1992","unstructured":"Canudas, C., Sordalen, O.J.: Exponential Stabilization of Mobile Robots with Nonholonomic Constraints. IEEE Transactions on Automatic Control\u00a033, 672\u2013677 (1992)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"30_CR13","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1023\/A:1017936530646","volume":"49","author":"J. Boyan","year":"2002","unstructured":"Boyan, J.: Technical Update: Least-squares Temporal Difference Learning. Mach. Learn.\u00a049, 233\u2013246 (2002)","journal-title":"Mach. Learn."},{"key":"30_CR14","first-page":"1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares Policy Iteration. J. Mach. Learn. Res.\u00a04, 1107\u20131149 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"30_CR15","doi-asserted-by":"publisher","first-page":"2275","DOI":"10.1109\/TSP.2004.830985","volume":"52","author":"Y. Engel","year":"2004","unstructured":"Engel, Y., Mannor, S., Meir, R.: The Kernel Recursive Least-squares Algorithm. IEEE Trans. Signal Process.\u00a052, 2275\u20132285 (2004)","journal-title":"IEEE Trans. Signal Process."},{"key":"30_CR16","volume-title":"Neuro-Dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"30_CR17","first-page":"1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares Policy Iteration. J. Mach. Learn. Res.\u00a04, 1107\u20131149 (2003)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2009"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-01513-7_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,8]],"date-time":"2019-03-08T01:08:26Z","timestamp":1552007306000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-01513-7_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642015120","9783642015137"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-01513-7_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}