{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T03:09:59Z","timestamp":1775012999524,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030361495","type":"print"},{"value":"9783030361501","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T00:00:00Z","timestamp":1574208000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-36150-1_18","type":"book-chapter","created":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T09:03:59Z","timestamp":1574154239000},"page":"213-224","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Effects of a Social Force Model Reward in Robot Navigation Based on Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"\u00d3scar","family":"Gil","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Sanfeliu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,20]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 961\u2013971, June 2016","DOI":"10.1109\/CVPR.2016.110"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Van\u00a0den Berg, J., Lin, M., Manocha, D.: Reciprocal velocity obstacles for real-time multi-agent navigation. In: 2008 IEEE International Conference on Robotics and Automation, pp. 1928\u20131935. IEEE (2008)","DOI":"10.1109\/ROBOT.2008.4543489"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C., Liu, Y., Kreiss, S., Alahi, A.: Crowd-robot interaction: crowd-aware robot navigation with attention-based deep reinforcement learning. In: 2019 International Conference on Robotics and Automation, pp. 6015\u20136022, May 2019","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y.F., Everett, M., Liu, M., How, J.P.: Socially aware motion planning with deep reinforcement learning. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1343\u20131350. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202312"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.F., Liu, M., Everett, M., How, J.P.: Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 285\u2013292 (2017)","DOI":"10.1109\/ICRA.2017.7989037"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Everett, M., Chen, Y.F., How, J.P.: 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 (2018)","DOI":"10.1109\/IROS.2018.8593871"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Ferrer, G., Sanfeliu, A.: Proactive kinodynamic planning using the extended social force model and human motion prediction in urban environments. In: 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1730\u20131735. IEEE (2014)","DOI":"10.1109\/IROS.2014.6942788"},{"issue":"4","key":"18_CR8","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1007\/s10514-016-9584-y","volume":"41","author":"G Ferrer","year":"2017","unstructured":"Ferrer, G., Zulueta, A.G., Cotarelo, F.H., Sanfeliu, A.: Robot social-aware navigation framework to accompany people walking side-by-side. Auton. Robots 41(4), 775\u2013793 (2017)","journal-title":"Auton. Robots"},{"key":"18_CR9","unstructured":"Francis, A., Faust, A., Chiang, H.L., Hsu, J., Kew, J.C., Fiser, M., Lee, T.E.: Long-range indoor navigation with PRM-RL. CoRR abs\/1902.09458 (2019)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Grzes, M., Kudenko, D.: Reward shaping and mixed resolution function approximation. In: Developments in Intelligent Agent Technologies and Multi-Agent Systems: Concepts and Applications, pp. 95\u2013115. IGI Global (2011)","DOI":"10.4018\/978-1-60960-171-3.ch007"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., Alahi, A.: Social GAN: socially acceptable trajectories with generative adversarial networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2255\u20132264, June 2018","DOI":"10.1109\/CVPR.2018.00240"},{"key":"18_CR12","unstructured":"Haddad, S., Wu, M., Wei, H., Lam, S.K.: Situation-aware pedestrian trajectory prediction with spatio-temporal attention model. CoRR abs\/1902.05437 (2019)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Hasan, I., Setti, F., Tsesmelis, T., Del Bue, A., Galasso, F., Cristani, M.: MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6067\u20136076 (2018)","DOI":"10.1109\/CVPR.2018.00635"},{"issue":"5","key":"18_CR14","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","volume":"51","author":"D Helbing","year":"1995","unstructured":"Helbing, D., Molnar, P.: Social force model for pedestrian dynamics. Phys. Rev. E 51(5), 4282 (1995)","journal-title":"Phys. Rev. E"},{"issue":"4","key":"18_CR15","doi-asserted-by":"publisher","first-page":"3184","DOI":"10.1109\/LRA.2019.2925731","volume":"4","author":"Noriaki Hirose","year":"2019","unstructured":"Hirose, N., Xia, F., Martin-Martin, R., Sadeghian, A., Savarese, S.: Deep visual MPC-policy learning for navigation. arXiv preprint \narXiv:1903.02749\n\n (2019)","journal-title":"IEEE Robotics and Automation Letters"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xu, A., Chen, Z.: Map-based deep imitation learning for obstacle avoidance. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8644\u20138649. IEEE (2018)","DOI":"10.1109\/IROS.2018.8593683"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Long, P., Fanl, T., Liao, X., Liu, W., Zhang, H., Pan, J.: Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. In: 2018 IEEE International Conference on Robotics and Automation, pp. 6252\u20136259 (2018)","DOI":"10.1109\/ICRA.2018.8461113"},{"issue":"2","key":"18_CR18","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1109\/LRA.2017.2651371","volume":"2","author":"P Long","year":"2017","unstructured":"Long, P., Liu, W., Pan, J.: Deep-learned collision avoidance policy for distributed multiagent navigation. IEEE Robot. Autom. Lett. 2(2), 656\u2013663 (2017)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"18_CR19","unstructured":"Ng, A.Y., Harada, D., Russell, S.J.: Policy invariance under reward transformations: theory and application to reward shaping. In: Proceedings of the Sixteenth International Conference on Machine Learning, ICML 1999, pp. 278\u2013287. Morgan Kaufmann Publishers Inc. (1999)"},{"key":"18_CR20","unstructured":"Repiso, E., Garrell, A., Sanfeliu, A.: Adaptive side-by-side social robot navigation to approach and interact with people. Int. J. Soc. Rob. 11, 1\u201322 (2019)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Sadeghian, A., Kosaraju, V., Sadeghian, A., Hirose, N., Rezatofighi, H., Savarese, S.: SoPhie: an attentive GAN for predicting paths compliant to social and physical constraints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1349\u20131358 (2019)","DOI":"10.1109\/CVPR.2019.00144"},{"key":"18_CR22","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press (2018)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Tail, L., Zhang, J., Liu, M., Burgard, W.: Socially compliant navigation through raw depth inputs with generative adversarial imitation learning. In: 2018 IEEE International Conference on Robotics and Automation, pp. 1111\u20131117 (2018)","DOI":"10.1109\/ICRA.2018.8460968"},{"issue":"3","key":"18_CR24","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"issue":"3","key":"18_CR25","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1177\/0278364914557874","volume":"34","author":"P Trautman","year":"2015","unstructured":"Trautman, P., Ma, J., Murray, R.M., Krause, A.: Robot navigation in dense human crowds: statistical models and experimental studies of human-robot cooperation. Int. J. Robot. Res. 34(3), 335\u2013356 (2015)","journal-title":"Int. J. Robot. Res."},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Van Den\u00a0Berg, J., Guy, S.J., Lin, M., Manocha, D.: Reciprocal n-body collision avoidance. In: Robotics Research, pp. 3\u201319. Springer (2011)","DOI":"10.1007\/978-3-642-19457-3_1"},{"key":"18_CR27","volume-title":"Temporal-Difference Learning and Applications in Finance","author":"B Roy Van","year":"2001","unstructured":"Van Roy, B.: Temporal-Difference Learning and Applications in Finance. MIT Press, Cambridge (2001)"},{"key":"18_CR28","unstructured":"Zou, H., Ren, T., Yan, D., Su, H., Zhu, J.: Reward shaping via meta-learning. CoRR abs\/1901.09330 (2019)"}],"container-title":["Advances in Intelligent Systems and Computing","Robot 2019: Fourth Iberian Robotics Conference"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36150-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,23]],"date-time":"2020-01-23T01:20:51Z","timestamp":1579742451000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36150-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,20]]},"ISBN":["9783030361495","9783030361501"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36150-1_18","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"value":"2194-5357","type":"print"},{"value":"2194-5365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,20]]},"assertion":[{"value":"20 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ROBOT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iberian Robotics conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"robot2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}