{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:53:17Z","timestamp":1743090797573,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030845285"},{"type":"electronic","value":"9783030845292"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-84529-2_50","type":"book-chapter","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T15:01:42Z","timestamp":1628521302000},"page":"592-604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Research on Path Planning Algorithm for Mobile Robot Based on Improved Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Junwei","family":"Liu","sequence":"first","affiliation":[]},{"given":"Aihua","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,9]]},"reference":[{"key":"50_CR1","doi-asserted-by":"crossref","unstructured":"Marin-Plaza, P., Hussein, A., Martin, D., et al.: Global and local path planning study in a ROS-based research platform for autonomous vehicles. J. Adv. Transp. 2018(PT.1), 1\u201310 (2018)","DOI":"10.1155\/2018\/6392697"},{"key":"50_CR2","doi-asserted-by":"crossref","unstructured":"Li, G., Yamashita, A., Asama, H., et al.: An efficient improved artificial potential field based regression search method for robot path planning. In: International Conference on Mechatronics & Automation. IEEE (2012)","DOI":"10.1109\/ICMA.2012.6283526"},{"issue":"2","key":"50_CR3","first-page":"51","volume":"45","author":"L Chang","year":"2020","unstructured":"Chang, L., Shan, L., Jiang, C., et al.: Reinforcement based mobile robot path planning with improved dynamic window approach in unknown environment. Auton. Robot. 45(2), 51\u201376 (2020)","journal-title":"Auton. Robot."},{"key":"50_CR4","unstructured":"Liu, G., Lao, S.Y., Tan, D.F., et al.: Fast graphic converse method for path planning of anti-ship missile. J. Ballist. (2011)"},{"key":"50_CR5","doi-asserted-by":"crossref","unstructured":"Tang, X.R., Zhu, Y., Jiang, X.X.: Improved A-star algorithm for robot path planning in static environment. J. Phys. Conf. Ser. 1792(1), 012067 (2021). 8p.","DOI":"10.1088\/1742-6596\/1792\/1\/012067"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Shen, Z., Hao, Y., Li, K.: Application research of an Adaptive Genetic Algorithms based on information entropy in path planning. Int. J. Inf. 13(6) (2010)","DOI":"10.1109\/ICINFA.2010.5512030"},{"issue":"2","key":"50_CR7","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.3233\/JIFS-189344","volume":"40","author":"G Wang","year":"2021","unstructured":"Wang, G., Zhou, J.: Dynamic robot path planning system using neural network. J. Intell. Fuzzy Syst. 40(2), 3055\u20133063 (2021)","journal-title":"J. Intell. Fuzzy Syst."},{"key":"50_CR8","unstructured":"Zhang, C., You, X.: Improved quantum ant colony algorithm of path planning for mobile robot based on grid model. Electron. Sci. Technol. (2016)"},{"key":"50_CR9","unstructured":"Gaskett, C., Fletcher, L., Zelinsky, A.: Reinforcement learning for a vision based mobile robot. IEEE (2018)"},{"key":"50_CR10","doi-asserted-by":"crossref","unstructured":"Kamalapurkar, R., Walters, P., Rosenfeld, J., et al.: Model-Based Reinforcement Learning for Approximate Optimal Control (2018)","DOI":"10.1007\/978-3-319-78384-0"},{"issue":"2","key":"50_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-017-0468-y","volume":"86","author":"AS Polydoros","year":"2017","unstructured":"Polydoros, A.S., Nalpantidis, L.: Survey of model-based reinforcement learning: applications on robotics. J. Intell. Rob. Syst. 86(2), 1\u201321 (2017)","journal-title":"J. Intell. Rob. Syst."},{"issue":"012","key":"50_CR12","first-page":"351","volume":"30","author":"L Tong","year":"2013","unstructured":"Tong, L., Wang, J.: Application of reinforcement learning in robot path planning. Comput. Simul. 30(012), 351\u2013355 (2013)","journal-title":"Comput. Simul."},{"key":"50_CR13","unstructured":"Huang, C., Sheng, Z., Jie, X., et al.: Markov Decision Process (2018)"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Surya, S., Rakesh, N.: Traffic Congestion Prediction and Intelligent Signaling Based on Markov Decision Process and Reinforcement Learning (2018)","DOI":"10.1007\/978-981-10-5146-3_30"},{"key":"50_CR15","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-662-47487-7_24","volume-title":"Advanced Multimedia and Ubiquitous Engineering","author":"P Chu","year":"2015","unstructured":"Chu, P., Vu, H., Yeo, D., Lee, B., Um, K., Cho, K.: Robot reinforcement learning for automatically avoiding a dynamic obstacle in a virtual environment. In: Park, J.J.H., Chao, H.-C., Arabnia, H., Yen, N.Y. (eds.) Advanced Multimedia and Ubiquitous Engineering. LNEE, vol. 352, pp. 157\u2013164. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-47487-7_24"},{"key":"50_CR16","doi-asserted-by":"crossref","unstructured":"Chen, L.P., Mohri, M., Rostamizadeh, A., Talwalkar, A.: Foundations of machine learning, second edition. Statistical Papers 60 (2019)","DOI":"10.1007\/s00362-019-01124-9"},{"key":"50_CR17","doi-asserted-by":"crossref","unstructured":"Watkins, C., Dayan, P.: Q-learning. Machine Learning (1992)","DOI":"10.1007\/BF00992698"},{"issue":"05","key":"50_CR18","first-page":"888","volume":"15","author":"R Yang","year":"2020","unstructured":"Yang, R., Yan, J.P., Li, X.: Research on sparse reward algorithm for reinforcement learning: theory and experiment . J. Intell. Syst. 15(05), 888\u2013899 (2020)","journal-title":"J. Intell. Syst."},{"key":"50_CR19","unstructured":"Riedmiller, M., Hafner, R., Lampe, T., et al.: Learning by Playing-Solving Sparse Reward Tasks from Scratch (2018)"},{"key":"50_CR20","unstructured":"Gullapalli, V., Barto, A.G.: Shaping as a Method for Accelerating Reinforcement Learning. IEEE (2002)"},{"key":"50_CR21","volume-title":"Reward Shaping","author":"E Wiewiora","year":"2011","unstructured":"Wiewiora, E.: Reward Shaping. Springer, Heidelberg (2011)"},{"key":"50_CR22","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, vol. 99, pp. 278\u2013287 (1999)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Computing Theories and Application"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-84529-2_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:09:28Z","timestamp":1710256168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-84529-2_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030845285","9783030845292"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-84529-2_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"9 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2021a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2021\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}