{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T02:40:05Z","timestamp":1743907205108,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031880162","type":"print"},{"value":"9783031880179","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-88017-9_7","type":"book-chapter","created":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T02:15:43Z","timestamp":1743905743000},"page":"87-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Inferring Pedestrian Decision-Making Through Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6618-1331","authenticated-orcid":false,"given":"Xiangmin","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3363-8620","authenticated-orcid":false,"given":"Liu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6332-7858","authenticated-orcid":false,"given":"Arnab","family":"Majumdar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6762-8746","authenticated-orcid":false,"given":"Washington","family":"Ochieng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,6]]},"reference":[{"key":"7_CR1","volume-title":"Multi-Agent Reinforcement Learning: Foundations and Modern Approaches","author":"SV Albrecht","year":"2024","unstructured":"Albrecht, S.V., Christianos, F., Sch\u00e4fer, L.: Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. The MIT Press, Cambridge, Massachusetts (2024)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Allievi, W.B.K., Banzhaf, H., Stone, F.S.: Reward (mis)design for autonomous driving. Artif. Intell. 316 (2023)","DOI":"10.1016\/j.artint.2022.103829"},{"key":"7_CR3","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.trf.2020.02.007","volume":"70","author":"R Alsaleh","year":"2020","unstructured":"Alsaleh, R., Sayed, T.: Modeling pedestrian-cyclist interactions in shared space using inverse reinforcement learning. Transport. Res. F: Traffic Psychol. Behav. 70, 37\u201357 (2020)","journal-title":"Transport. Res. F: Traffic Psychol. Behav."},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. Trans. Syst. Man Cybern. SMC-13(5), 834\u2013846 (1983)","DOI":"10.1109\/TSMC.1983.6313077"},{"issue":"5","key":"7_CR5","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1080\/01441647.2021.2000064","volume":"42","author":"N Basu","year":"2022","unstructured":"Basu, N., Haque, M.M., King, M., Kamruzzaman, M., Oviedo-Trespalacios, O.: A systematic review of the factors associated with pedestrian route choice. Transp. Rev. 42(5), 594\u2013672 (2022)","journal-title":"Transp. Rev."},{"key":"7_CR6","doi-asserted-by":"crossref","first-page":"4929","DOI":"10.1007\/s10668-019-00381-w","volume":"22","author":"GR Bivina","year":"2020","unstructured":"Bivina, G.R., Parida, M.: Prioritizing pedestrian needs using a multi-criteria decision approach for a sustainable built environment in the Indian context. Environ. Dev. Sustain. 22, 4929\u20134950 (2020)","journal-title":"Environ. Dev. Sustain."},{"issue":"4","key":"7_CR7","doi-asserted-by":"crossref","first-page":"3774","DOI":"10.1109\/LRA.2019.2929996","volume":"4","author":"G Chalvatzaki","year":"2019","unstructured":"Chalvatzaki, G., Papageorgiou, X.S., Maragos, P., Tzafestas, C.S.: Learn to adapt to human walking: a model-based reinforcement learning approach for a robotic assistant rollator. Robot. Autom. Lett. 4(4), 3774\u20133781 (2019)","journal-title":"Robot. Autom. Lett."},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Eschmann, J.: Reward function design in reinforcement learning. In: Belousov, B., Abdulsamad, H., Klink, P., Parisi, S., Peters, J. (eds.) Reinforcement Learning Algorithms: Analysis and Applications, pp. 25\u201333. Springer (2021)","DOI":"10.1007\/978-3-030-41188-6_3"},{"key":"7_CR9","doi-asserted-by":"crossref","first-page":"10357","DOI":"10.1109\/ACCESS.2021.3050338","volume":"9","author":"M Everett","year":"2021","unstructured":"Everett, M., Chen, Y.F., How, J.P.: Collision avoidance in pedestrian-rich environments with deep reinforcement learning. IEEE Access 9, 10357\u201310377 (2021)","journal-title":"IEEE Access"},{"issue":"1","key":"7_CR10","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1177\/0739456X15591585","volume":"36","author":"R Ewing","year":"2015","unstructured":"Ewing, R., Hajrasouliha, A., Neckerman, K.M., Purciel-Hill, M., Greene, W.: Streetscape features related to pedestrian activity. J. Plan. Educ. Res. 36(1), 5\u201315 (2015)","journal-title":"J. Plan. Educ. Res."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Fahad, M., Chen, Z., Guo, Y.: Learning how pedestrians navigate: a deep inverse reinforcement learning approach. In: Proceedings of a Conference in Madrid (2018)","DOI":"10.1109\/IROS.2018.8593438"},{"key":"7_CR12","unstructured":"Finn, C., Christiano, P., Abbeel, P., Sutskever, I.: A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models. arXiv preprint https:\/\/arxiv.org\/abs\/1611.03852 (2016)"},{"key":"7_CR13","unstructured":"Fu, J., Luo, K., Levine, S.: Learning robust rewards with adversarial inverse reinforcement learning. In: Proceedings of a Conference in Vancouver (2018)"},{"issue":"8","key":"7_CR14","doi-asserted-by":"crossref","first-page":"4815","DOI":"10.1109\/LRA.2023.3289770","volume":"8","author":"D Gonon","year":"2023","unstructured":"Gonon, D., Billard, A.: Inverse reinforcement learning of pedestrian-robot coordination. Robot. Autom. Lett. 8(8), 4815\u20134822 (2023)","journal-title":"Robot. Autom. Lett."},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Haghani, M., Sarvi, M.: Pedestrian crowd tactical-level decision making during emergency evacuations. J. Adv. Transp. (2016)","DOI":"10.1002\/atr.1434"},{"key":"7_CR16","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.trb.2016.10.019","volume":"95","author":"M Haghani","year":"2017","unstructured":"Haghani, M., Sarvi, M.: Stated and revealed exit choices of pedestrian crowd evacuees. Transp. Res. Part B: Methodol. 95, 238\u2013259 (2017)","journal-title":"Transp. Res. Part B: Methodol."},{"key":"7_CR17","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.ssci.2018.12.026","volume":"114","author":"M Haghani","year":"2019","unstructured":"Haghani, M., Sarvi, M.: Imitative (herd) behaviour in direction decision-making hinders efficiency of crowd evacuation processes. Saf. Sci. 114, 49\u201360 (2019)","journal-title":"Saf. Sci."},{"issue":"5","key":"7_CR18","doi-asserted-by":"crossref","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\u20134286 (1995)","journal-title":"Phys. Rev. E"},{"key":"7_CR19","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Proceedings of a Conference in Montreal (2016)"},{"key":"7_CR20","unstructured":"Hugging Face: PPO Agent playing seals\/CartPole-v0. https:\/\/huggingface.co\/HumanCompatibleAI\/ppo-seals-CartPole-v0. Accessed 1 Feb 2024"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Kim, J., Tak, S., Bierlaire, M., Yeo, H.: Trajectory data analysis on the spatial and temporal influence of pedestrian flow on path planning decision. Sustainability 12(24) (2020)","DOI":"10.3390\/su122410419"},{"key":"7_CR22","unstructured":"Kokhlikyan, N., et al.: Captum: a unified and generic model interpretability library for pytorch. arXiv preprint https:\/\/arxiv.org\/abs\/2009.07896 (2020)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yan, Q., Alahi, A.: Social NCE: contrastive learning of socially-aware motion representations (2021), preprint or unpublished","DOI":"10.1109\/ICCV48922.2021.01484"},{"key":"7_CR24","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.firesaf.2015.07.001","volume":"78","author":"R Lovreglio","year":"2015","unstructured":"Lovreglio, R., Ronchi, E., Nilsson, D.: A model of the decision-making process during pre-evacuation. Fire Saf. 78, 168\u2013179 (2015)","journal-title":"Fire Saf."},{"key":"7_CR25","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol.\u00a030 (2017)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Mohamed, A., Qian, K., Elhoseiny, M., Claudel, C.: Social-STGCNN: a social spatio-temporal graph convolutional neural network for human trajectory prediction (2020), preprint or unpublished","DOI":"10.1109\/CVPR42600.2020.01443"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Nasernejad, P., Sayed, T., Alsaleh, R.: Modeling pedestrian behavior in pedestrian-vehicle near misses: a continuous gaussian process inverse reinforcement learning (GP-IRL) approach. Accid. Anal. Prev. 161 (2021)","DOI":"10.1016\/j.aap.2021.106355"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Nasernejad, P., Sayed, T., Alsaleh, R.: Multiagent modeling of pedestrian-vehicle conflicts using adversarial inverse reinforcement learning. Transportmetrica A Transp. Sci. 19(3) (2023)","DOI":"10.1080\/23249935.2022.2061081"},{"key":"7_CR29","unstructured":"Ng, A.Y., Russell, S.J.: Algorithms for inverse reinforcement learning. In: Proceedings of a Conference in San Francisco (2000)"},{"key":"7_CR30","doi-asserted-by":"crossref","first-page":"4354","DOI":"10.1016\/j.trpro.2016.05.357","volume":"14","author":"E Papadimitriou","year":"2016","unstructured":"Papadimitriou, E., Lassarre, S., Yannis, G.: Pedestrian risk taking while road crossing: a comparison of observed and declared behaviour. Transp. Res. Procedia 14, 4354\u20134363 (2016)","journal-title":"Transp. Res. Procedia"},{"key":"7_CR31","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.1016\/j.trpro.2017.05.396","volume":"25","author":"E Papadimitriou","year":"2017","unstructured":"Papadimitriou, E., Lassarre, S., Yannis, G.: Human factors of pedestrian walking and crossing behaviour. Transp. Res. Procedia 25, 2002\u20132015 (2017)","journal-title":"Transp. Res. Procedia"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-D\u2019Arpino, C., Liu, C., Goebel, P., Mart\u00edn-Mart\u00edn, R., Savarese, S.: Robot navigation in constrained pedestrian environments using reinforcement learning. In: Proceedings of a Conference in Xi\u2019an (2021)","DOI":"10.1109\/ICRA48506.2021.9560893"},{"key":"7_CR33","doi-asserted-by":"crossref","first-page":"6228","DOI":"10.1007\/s00034-023-02399-y","volume":"42","author":"K Radha","year":"2023","unstructured":"Radha, K., Bansal, M.: Feature fusion and ablation analysis in gender identification of preschool children from spontaneous speech. Circ. Syst. Signal Process. 42, 6228\u20136252 (2023)","journal-title":"Circ. Syst. Signal Process."},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Saleh, K., Hossny, M., Nahavandi, S.: Long-term recurrent predictive model for intent prediction of pedestrians via inverse reinforcement learning. In: Proceedings of a Conference in Canberra (2018)","DOI":"10.1109\/DICTA.2018.8615854"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Sheu, Y.h.: Illuminating the black box: Interpreting deep neural network models for psychiatric research. Front. Psychiatry 11 (2020)","DOI":"10.3389\/fpsyt.2020.551299"},{"key":"7_CR36","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.trf.2021.08.014","volume":"82","author":"F Soares","year":"2021","unstructured":"Soares, F., Silva, E., Pereira, F., Silva, C., Sousa, E., Freitas, E.: To cross or not to cross: impact of visual and auditory cues on pedestrians\u2019 crossing decision-making. Transport. Res. F: Traffic Psychol. Behav. 82, 202\u2013220 (2021)","journal-title":"Transport. Res. F: Traffic Psychol. Behav."},{"key":"7_CR37","first-page":"1","volume":"11","author":"E Strumbelj","year":"2010","unstructured":"Strumbelj, E., Kononenko, I.: An efficient explanation of individual classifications using game theory. J. Mach. Learn. Res. 11, 1\u201318 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Tong, Y., Bode, N.W.F.: The principles of pedestrian route choice. J. R. Soc. Interface 19(189) (2022)","DOI":"10.1098\/rsif.2022.0061"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Wedagamaa, D.M.P., Bennettb, S., Dissanayake, D.: Analyzing pedestrian perceptions towards traffic safety using discrete choice models. Int. J. Adv. Sci. Eng. Inf. Technol. 10(6) (2020)","DOI":"10.18517\/ijaseit.10.6.12662"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Yang, Y., Sun, J.: Study on pedestrian red-time crossing behavior: integrated field observation and questionnaire data. Transp. Res. Record J. Transp. Res. Board 2393(1) (2013)","DOI":"10.3141\/2393-13"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Zhangl, G., Yu, Z., Jin, D., Li, Y.: Physics-infused machine learning for crowd simulation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2022)","DOI":"10.1145\/3534678.3539440"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent-Based Simulation XXV"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88017-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T02:16:54Z","timestamp":1743905814000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88017-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031880162","9783031880179"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88017-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"6 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MABS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Multi-Agent Systems and Agent-Based Simulation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mabs2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mabsworkshop.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}