{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:46:02Z","timestamp":1785653162761,"version":"3.56.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31666-0_28","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:38Z","timestamp":1785649658000},"page":"422-436","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Guided Exploration for\u00a0Sample-Efficient UAV Navigation"],"prefix":"10.1007","author":[{"given":"Xianan","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junbao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"28_CR1","unstructured":"Ahn, M., et al.: Do as i can, not as i say: grounding language in robotic affordances. In: Proceedings of Conference Roboting Learning (2022)"},{"key":"28_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105321","volume":"115","author":"F AlMahamid","year":"2022","unstructured":"AlMahamid, F., Grolinger, K.: Autonomous unmanned aerial vehicle navigation using reinforcement learning: a systematic review. Eng. Appl. Artif. Intell. 115, 105321 (2022)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"28_CR3","unstructured":"Black, K., et al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. In: Lim, J., Song, S., Park, H.W. (eds.) Proceedings of The 9th Conference on Robot Learning. Proceedings of Machine Learning Research, vol.\u00a0305, pp. 17\u201340. PMLR (2025)"},{"key":"28_CR4","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods (2018)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Gandhi, D., Pinto, L., Gupta, A.: Learning to fly by crashing. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3948\u20133955 (2017)","DOI":"10.1109\/IROS.2017.8206247"},{"key":"28_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2023.103831","volume":"123","author":"V Garg","year":"2023","unstructured":"Garg, V., Niranjan, S., Prybutok, V., Pohlen, T., Gligor, D.: Drones in last-mile delivery: a systematic review on efficiency, accessibility, and sustainability. Transp. Res. Part D: Transp. Environ. 123, 103831 (2023)","journal-title":"Transp. Res. Part D: Transp. Environ."},{"issue":"2","key":"28_CR7","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1016\/j.cja.2020.05.011","volume":"34","author":"T Guo","year":"2021","unstructured":"Guo, T., Jiang, N., Li, B., Zhu, X., Wang, Y., Du, W.: UAV navigation in high dynamic environments: a deep reinforcement learning approach. Chin. J. Aeronaut. 34(2), 479\u2013489 (2021)","journal-title":"Chin. J. Aeronaut."},{"key":"28_CR8","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"28_CR9","unstructured":"Hester, T., et al.: Deep Q-learning from demonstrations. In: AAAI\u201918\/IAAI\u201918\/EAAI\u201918, AAAI Press (2018)"},{"key":"28_CR10","unstructured":"Hu, C.Y., al.: See, point, fly: a learning-free VLM framework for universal unmanned aerial navigation. In: Lim, J., Song, S., Park, H.W. (eds.) Proceedings of The 9th Conference on Robot Learning. Proceedings of Machine Learning Research, vol.\u00a0305, pp. 4697\u20134708. PMLR (2025)"},{"key":"28_CR11","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I.: Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In: Proceedings of International Conference Machine learning, pp. 9118\u20139147 (2022)"},{"key":"28_CR12","unstructured":"Huang, W., et\u00a0al.: Inner monologue: embodied reasoning through planning with language models. In: Proceedings of Conference on Robot Learning (2022)"},{"key":"28_CR13","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1177\/0278364914554813","volume":"34","author":"S Leutenegger","year":"2015","unstructured":"Leutenegger, S., Lynen, S., Bosse, M., Siegwart, R.Y., Furgale, P.T.: Keyframe-based visual-inertial odometry using nonlinear optimization. Int. J. Robot. Res. 34, 314\u2013334 (2015)","journal-title":"Int. J. Robot. Res."},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Liang, J., et al.: Code as policies: language model programs for embodied control. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 9493\u20139500 (2023)","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"28_CR15","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning (2015). arXiv: Learning"},{"key":"28_CR16","unstructured":"Ma, Y.J., et al.: Eureka: human-level reward design via coding large language models (2023). arXiv:2310.12931 arXiv preprint"},{"issue":"5","key":"28_CR17","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R., Tard\u00f3s, J.D.: ORB-SLAM2: an open-source SLAM system for monocular, stereo and RGB-D cameras. IEEE Trans. Rob. 33(5), 1255\u20131262 (2017)","journal-title":"IEEE Trans. Rob."},{"key":"28_CR18","unstructured":"OpenAI: GPT-4O System Card (2024)"},{"issue":"4","key":"28_CR19","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1109\/TRO.2018.2853729","volume":"34","author":"T Qin","year":"2018","unstructured":"Qin, T., Li, P., Shen, S.: VINS-MONO: a robust and versatile monocular visual-inertial state estimator. IEEE Trans. Rob. 34(4), 1004\u20131020 (2018)","journal-title":"IEEE Trans. Rob."},{"issue":"1","key":"28_CR20","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1109\/TITS.2019.2954952","volume":"22","author":"A Singla","year":"2021","unstructured":"Singla, A., Padakandla, S., Bhatnagar, S.: Memory-based deep reinforcement learning for obstacle avoidance in UAV with limited environment knowledge. IEEE Trans. Intell. Transp. Syst. 22(1), 107\u2013118 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"28_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.114065","volume":"326","author":"S Sun","year":"2025","unstructured":"Sun, S., Liu, R., Lyu, J., Yang, J.W., Zhang, L., Li, X.: A large language model-driven reward design framework via dynamic feedback for reinforcement learning. Knowl.-Based Syst. 326, 114065 (2025)","journal-title":"Knowl.-Based Syst."},{"key":"28_CR22","unstructured":"Vecer\u00edk, M., et al.: Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards (2017). ArXiv abs\/1707.08817"},{"issue":"1","key":"28_CR23","first-page":"52","volume":"4","author":"J Wang","year":"2025","unstructured":"Wang, J., et al.: Large language models for robotics: opportunities, challenges, and perspectives. J. Autom. Intell. 4(1), 52\u201364 (2025)","journal-title":"J. Autom. Intell."},{"key":"28_CR24","unstructured":"Wang, X., et al.: Towards realistic UAV vision-language navigation: platform, benchmark, and methodology (2024)"},{"key":"28_CR25","unstructured":"Xie, T., et al.: Text2Reward: automated dense reward function generation for reinforcement learning (2023). arXiv:2309.11489 arXiv preprint"},{"issue":"4","key":"28_CR26","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1109\/TRO.2022.3141876","volume":"38","author":"W Xu","year":"2022","unstructured":"Xu, W., Cai, Y., He, D., Lin, J., Zhang, F.: FAST-LIO2: fast direct LIDAR-inertial odometry. IEEE Trans. Rob. 38(4), 2053\u20132073 (2022)","journal-title":"IEEE Trans. Rob."},{"key":"28_CR27","unstructured":"Yang, A., et al.: Qwen3 Technical Report (2025)"},{"issue":"3","key":"28_CR28","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s10846-023-01819-0","volume":"107","author":"Y Yang","year":"2023","unstructured":"Yang, Y., Hou, Z., Chen, H., Lu, P.: DRL-based path planner and its application in real quadrotor with lidar. J. Intell. Robot. Syst. 107(3), 38 (2023)","journal-title":"J. Intell. Robot. Syst."},{"key":"28_CR29","unstructured":"Yu, W., et al.: Language to rewards for robotic skill synthesis. In: Proceedings of Conference on Robot Learning (2023)"},{"key":"28_CR30","unstructured":"Zhang, J., et al.: Bootstrap your own skills: learning to solve new tasks with large language model guidance. In: Proceedings of Conference on Robot Learning (2023)"},{"issue":"2","key":"28_CR31","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1109\/LRA.2021.3051563","volume":"6","author":"B Zhou","year":"2021","unstructured":"Zhou, B., Zhang, Y., Chen, X., Shen, S.: Fuel: fast UAV exploration using incremental frontier structure and hierarchical planning. IEEE Robot. Autom. Lett. 6(2), 779\u2013786 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"2","key":"28_CR32","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/LRA.2020.3047728","volume":"6","author":"X Zhou","year":"2021","unstructured":"Zhou, X., Wang, Z., Ye, H., Xu, C., Gao, F.: Ego-planner: an ESDF-free gradient-based local planner for quadrotors. IEEE Robot. Autom. Lett. 6(2), 478\u2013485 (2021)","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:40Z","timestamp":1785649660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}