{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T08:21:20Z","timestamp":1792743680157,"version":"4.5.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T00:00:00Z","timestamp":1693267200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T00:00:00Z","timestamp":1693267200000},"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":["Auton Robot"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s10514-023-10133-5","type":"journal-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T05:03:08Z","timestamp":1693285388000},"page":"981-997","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":59,"title":["Integrating action knowledge and LLMs for task planning and situation handling in open worlds"],"prefix":"10.1007","volume":"47","author":[{"given":"Yan","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saeid","family":"Amiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nieqing","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andy","family":"Kaminski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chad","family":"Esselink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,29]]},"reference":[{"key":"10133_CR1","volume-title":"PDDL| the planning domain definition language","author":"C Aeronautiques","year":"1998","unstructured":"Aeronautiques, C., Howe, A., Knoblock, C., McDermott, I. D., Ram, A., Veloso, M., et al. (1998). PDDL| the planning domain definition language. Tech Rep: Technical Report."},{"key":"10133_CR2","doi-asserted-by":"crossref","unstructured":"Amiri, S., Bajracharya, S., Goktolgal, C., Thomason, J., & Zhang, S. (2019). Augmenting knowledge through statistical, goal-oriented human-robot dialog. In: 2019 IEEE\/RSJ International conference on intelligent robots and systems (IROS). IEEE; 2019. p. 744\u2013750.","DOI":"10.1109\/IROS40897.2019.8968269"},{"key":"10133_CR3","unstructured":"Brohan, A., Chebotar, Y., Finn, C., Hausman, K., Herzog, A., & Ho, D., et\u00a0al. (2023a). Do as i can, not as i say: Grounding language in robotic affordances. In: Conference on robot learning; 287\u2013318."},{"key":"10133_CR4","unstructured":"Brohan, A., Brown, N., Carbajal, J., Chebotar, Y., Chen, X., Choromanski, K., Ding, T., Driess, D., Dubey, A., Finn, C., et al. (2023b). RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control, arXiv preprint arXiv:2307.15818."},{"key":"10133_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems., 33, 1877\u20131901.","journal-title":"Advances in neural information processing systems."},{"key":"10133_CR6","unstructured":"Chen, M., Tworek, J., Jun, H., & Yuan, Q. (2021). Pinto HPdO, Kaplan J, et\u00a0al. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374."},{"key":"10133_CR7","doi-asserted-by":"crossref","unstructured":"Chernova, S., Chu, V., Daruna, A., Garrison, H., Hahn, M., & Khante, P. et\u00a0al. (2020) Situated bayesian reasoning framework for robots operating in diverse everyday environments. In: Robotics research. Springer; . p. 353\u2013369.","DOI":"10.1007\/978-3-030-28619-4_29"},{"issue":"9","key":"10133_CR8","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1145\/2701413","volume":"58","author":"E Davis","year":"2015","unstructured":"Davis, E., & Marcus, G. (2015). Commonsense reasoning and commonsense knowledge in artificial intelligence. Communications of the ACM, 58(9), 92\u2013103.","journal-title":"Communications of the ACM"},{"key":"10133_CR9","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of naacL-HLT, 1(2)-2."},{"key":"10133_CR10","unstructured":"Ding, Y., Zhang, X., Paxton, C., & Zhang, S. (2023). Task and Motion Planning with Large Language Models for Object Rearrangement. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)."},{"key":"10133_CR11","doi-asserted-by":"crossref","unstructured":"Elsweiler, D., Hauptmann, H., & Trattner, C. (2022). Food recommender systems. In: Recommender systems handbook. Springer; 871\u2013925.","DOI":"10.1007\/978-1-0716-2197-4_23"},{"issue":"11","key":"10133_CR12","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1016\/j.robot.2008.08.007","volume":"56","author":"C Galindo","year":"2008","unstructured":"Galindo, C., Fern\u00e1ndez-Madrigal, J. A., Gonz\u00e1lez, J., & Saffiotti, A. (2008). Robot task planning using semantic maps. Robotics and Autonomous Systems, 56(11), 955\u2013966.","journal-title":"Robotics and Autonomous Systems"},{"key":"10133_CR13","unstructured":"Gao, P., Han, J., Zhang, R., Lin, Z., Geng, S., & Zhou, A.,et\u00a0al. (2023). Llama-adapter v2: Parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010."},{"key":"10133_CR14","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1609\/icaps.v30i1.6739","volume":"30","author":"CR Garrett","year":"2020","unstructured":"Garrett, C. R., Lozano-P\u00e9rez, T., & Kaelbling, L. P. (2020). Pddlstream: Integrating symbolic planners and blackbox samplers via optimistic adaptive planning. Proceedings of the international conference on automated planning and scheduling., 30, 440\u2013448.","journal-title":"Proceedings of the international conference on automated planning and scheduling."},{"key":"10133_CR15","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1146\/annurev-control-091420-084139","volume":"4","author":"CR Garrett","year":"2021","unstructured":"Garrett, C. R., Chitnis, R., Holladay, R., Kim, B., Silver, T., Kaelbling, L. P., et al. (2021). Integrated task and motion planning. Annual Review of Control, Robotics, and Autonomous Systems, 4, 265\u2013293.","journal-title":"Annual Review of Control, Robotics, and Autonomous Systems"},{"key":"10133_CR16","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139583923","volume-title":"Automated planning and acting","author":"M Ghallab","year":"2016","unstructured":"Ghallab, M., Nau, D., & Traverso, P. (2016). Automated planning and acting. Cambridge University Press."},{"key":"10133_CR17","unstructured":"Google.: Bard FAQ. Accessed on April 7, (2023). https:\/\/bard.google.com\/faq."},{"key":"10133_CR18","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.artint.2015.08.008","volume":"247","author":"M Hanheide","year":"2017","unstructured":"Hanheide, M., G\u00f6belbecker, M., Horn, G. S., Pronobis, A., Sj\u00f6\u00f6, K., Aydemir, A., et al. (2017). Robot task planning and explanation in open and uncertain worlds. Artificial Intelligence, 247, 119\u2013150.","journal-title":"Artificial Intelligence"},{"issue":"2","key":"10133_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-01584-7","volume":"13","author":"P Haslum","year":"2019","unstructured":"Haslum, P., Lipovetzky, N., Magazzeni, D., & Muise, C. (2019). An introduction to the planning domain definition language. Synthesis Lectures on Artificial Intelligence and Machine Learning, 13(2), 1\u2013187.","journal-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning"},{"key":"10133_CR20","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1613\/jair.1705","volume":"26","author":"M Helmert","year":"2006","unstructured":"Helmert, M. (2006). The fast downward planning system. Journal of Artificial Intelligence Research, 26, 191\u2013246.","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"3","key":"10133_CR21","first-page":"57","volume":"22","author":"J Hoffmann","year":"2001","unstructured":"Hoffmann, J. (2001). FF: The fast-forward planning system. AI magazine, 22(3), 57\u201357.","journal-title":"AI magazine"},{"key":"10133_CR22","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I. (2022) Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. Thirty-ninth international conference on machine learning."},{"key":"10133_CR23","unstructured":"Huang, W., Xia, F., Shah, D., Driess, D., Zeng, A., & Lu, Y., et\u00a0al.(2023). Grounded Decoding: Guiding text generation with grounded models for robot control. arXiv preprint arXiv:2303.00855."},{"key":"10133_CR24","unstructured":"Huang, W., Xia, F., Xiao, T., Chan, H., Liang, J., & Florence, P., et\u00a0al. (2022). Inner Monologue: Embodied Reasoning through Planning with Language Models. In: 6th Annual conference on robot learning."},{"key":"10133_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Walker, N., Hart, J., &Stone, P. (2019) Open-world reasoning for service robots. In: Proceedings of the international conference on automated planning and scheduling. vol. 29; . p. 725\u2013733.","DOI":"10.1609\/icaps.v29i1.3541"},{"key":"10133_CR26","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., & Michael, K., et\u00a0al. (2022). ultralytics\/yolov5: v7. 0-yolov5 sota realtime instance segmentation. Zenodo."},{"key":"10133_CR27","doi-asserted-by":"crossref","unstructured":"Kant, Y., Ramachandran, A., Yenamandra, S., Gilitschenski, I., Batra, D., & Szot, A. et\u00a0al. (2022) Housekeep: Tidying virtual households using commonsense reasoning. In: Computer vision\u2013ECCV 2022. Springer; . p. 355\u2013373.","DOI":"10.1007\/978-3-031-19842-7_21"},{"key":"10133_CR28","unstructured":"Knoblock C.A., & Tenenberg, J.D., Yang, Q. (1991) Characterizing abstraction hierarchies for planning. In: Proceedings of the ninth national conference on artificial intelligence2692\u2013697."},{"key":"10133_CR29","unstructured":"Li, S., Puig, X., Paxton, C., Du, Y., Wang, C., & Fan, L., et al. (2022). Pre-trained language models for interactive decision-making. Advances in Neural Information Processing Systems."},{"key":"10133_CR30","doi-asserted-by":"crossref","unstructured":"Lin, K., Agia, C., Migimatsu, T., Pavone, M., & Bohg, J. (2023). Text2Motion: From natural language instructions to feasible plans. arXiv preprint arXiv:2303.12153.","DOI":"10.1007\/s10514-023-10131-7"},{"key":"10133_CR31","unstructured":"Liu, B., Jiang, Y., Zhang, X., Liu, Q., Zhang, S., & Biswas, J., et\u00a0al. (2023). LLM+P: Empowering large language models with optimal planning proficiency. arXiv preprint arXiv:2304.11477."},{"issue":"9","key":"10133_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9), 1\u201335.","journal-title":"ACM Computing Surveys"},{"key":"10133_CR33","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1613\/jair.1.12181","volume":"69","author":"SY Lo","year":"2020","unstructured":"Lo, S. Y., Zhang, S., & Stone, P. (2020). The petlon algorithm to plan efficiently for task-level-optimal navigation. Journal of Artificial Intelligence Research., 69, 471\u2013500.","journal-title":"Journal of Artificial Intelligence Research."},{"key":"10133_CR34","doi-asserted-by":"crossref","unstructured":"Morrison, D., Corke, P., & Leitner, J. (2018). Closing the loop for robotic grasping: A real-time, generative grasp synthesis approach. In: Robotics: Science and Systems (RSS).","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"10133_CR35","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1613\/jair.1141","volume":"20","author":"DS Nau","year":"2003","unstructured":"Nau, D. S., Au, T. C., Ilghami, O., Kuter, U., Murdock, J. W., Wu, D., et al. (2003). SHOP2: An HTN planning system. Journal of artificial intelligence research, 20, 379\u2013404.","journal-title":"Journal of artificial intelligence research"},{"key":"10133_CR36","unstructured":"OpenAI.: ChatGPT. Cit. on pp. 1, 16. Accessed: 2023-02-08. Retrieved from: https:\/\/openai.com\/blog\/chatgpt\/."},{"key":"10133_CR37","unstructured":"OpenAI.: GPT-4 technical report."},{"key":"10133_CR38","unstructured":"OpenAI.: Models\u2013OpenAI API. Retrieved: 2023-07-10. https:\/\/platform.openai.com\/docs\/models\/overview."},{"issue":"2","key":"10133_CR39","doi-asserted-by":"publisher","first-page":"223","DOI":"10.3390\/robotics4020223","volume":"4","author":"V Perera","year":"2015","unstructured":"Perera, V., Soetens, R., Kollar, T., Samadi, M., Sun, Y., Nardi, D., et al. (2015). Learning task knowledge from dialog and web access. Robotics, 4(2), 223\u2013252.","journal-title":"Robotics"},{"key":"10133_CR40","doi-asserted-by":"crossref","unstructured":"Puig, X., Ra, K., Boben, M., Li, J., Wang, T., & Fidler, S., et\u00a0al. (2018). Virtualhome: Simulating household activities via programs. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2018. 8494\u20138502.","DOI":"10.1109\/CVPR.2018.00886"},{"key":"10133_CR41","unstructured":"Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., & Leibs, J., et\u00a0al. (2009). ROS: an open-source Robot Operating System. In: ICRA workshop on open source software. vol. 3. Kobe, Japan; p. 5."},{"key":"10133_CR42","doi-asserted-by":"crossref","unstructured":"Reiter, R. (1981) On closed world data bases. In: Readings in artificial intelligence. Elsevier. p. 119\u2013140.","DOI":"10.1016\/B978-0-934613-03-3.50014-3"},{"key":"10133_CR43","doi-asserted-by":"crossref","unstructured":"Singh, I., Blukis, V., Mousavian, A., Goyal, A., Xu, D., & Tremblay, J., et\u00a0al. (2023). Progprompt: Generating situated robot task plans using large language models. International Conference on Robotics and Automation (ICRA).","DOI":"10.1007\/s10514-023-10135-3"},{"key":"10133_CR44","doi-asserted-by":"crossref","unstructured":"Song, CH., Wu, J., Washington, C., Sadler, BM., Chao, WL., & Su, Y. (2023). Llm-planner: Few-shot grounded planning for embodied agents with large language models. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"10133_CR45","doi-asserted-by":"crossref","unstructured":"Tucker, M., Aksaray, D., Paul, R., Stein, G.J., & Roy, N.(2020) Learning unknown groundings for natural language interaction with mobile robots. In: Robotics research. Springer; 317\u2013333.","DOI":"10.1007\/978-3-030-28619-4_27"},{"key":"10133_CR46","unstructured":"Valmeekam, K., Olmo, A., Sreedharan, S., & Kambhampati, S. (2022). Large language models still can\u2019t plan (a benchmark for llms on planning and reasoning about change). In: Foundation Models for Decision Making Workshop at Neural Information Processing Systems."},{"key":"10133_CR47","unstructured":"Valmeekam, K., Sreedharan, S., Marquez, M., Olmo, A., & Kambhampati, S. (2023). On the planning abilities of large language models (a critical investigation with a proposed benchmark). arXiv preprint arXiv:2302.06706. 2023;."},{"key":"10133_CR48","doi-asserted-by":"crossref","unstructured":"Wang, C., Liu, P., & Zhang, Y. (2021). Can generative pre-trained language models serve as knowledge bases for closed-book QA? In: Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing; 3241\u20133251.","DOI":"10.18653\/v1\/2021.acl-long.251"},{"key":"10133_CR49","doi-asserted-by":"crossref","unstructured":"West, P., Bhagavatula, C., Hessel, J., Hwang, JD., Jiang, L., & Bras, RL, et\u00a0al. (2022). Symbolic knowledge distillation: From general language models to commonsense models. Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: Human language technologies.","DOI":"10.18653\/v1\/2022.naacl-main.341"},{"key":"10133_CR50","unstructured":"Xie, Y., Yu, C., Zhu, T., Bai, J., Gong, Z., & Soh, H.(2023). Translating natural language to planning goals with large-language models. arXiv preprint arXiv:2302.05128."},{"issue":"3","key":"10133_CR51","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1631\/FITEE.1800514","volume":"20","author":"Jiang Yq","year":"2019","unstructured":"Yq, Jiang, Sq, Zhang, Khandelwal, P., & Stone, P. (2019). Task planning in robotics: An empirical comparison of PDDL-and ASP-based systems. Frontiers of Information Technology & Electronic Engineering., 20(3), 363\u2013373.","journal-title":"Frontiers of Information Technology & Electronic Engineering."},{"key":"10133_CR52","unstructured":"Zhao, Z., Lee, WS., & Hsu, D (2023). Large Language Models as Commonsense Knowledge for Large-Scale Task Planning, RSS Workshop on Learning for Task and Motion Planning"},{"key":"10133_CR53","unstructured":"Zhang, X., Ding, Y., Amiri, S., Yang, H., Kaminski, A., & Esselink, C, et\u00a0al. (2023). Grounding classical task planners via vision-language models. In: ICRA Workshop on Robot Execution Failures and Failure Management Strategies."},{"key":"10133_CR54","unstructured":"Zhang, N., Li, L., Chen, X., Deng, S., Bi, Z., & Tan, C. et\u00a0al (2021). ifferentiable prompt makes pre-trained language models better few-shot learners. In: International conference on learning representations."},{"key":"10133_CR55","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., & Chen, S., et\u00a0al. (2022). OPT: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068."},{"key":"10133_CR56","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., & Elhoseiny, M. (2023). Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592."}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-023-10133-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10514-023-10133-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-023-10133-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T20:46:31Z","timestamp":1729975591000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10514-023-10133-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,29]]},"references-count":56,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10133"],"URL":"https:\/\/doi.org\/10.1007\/s10514-023-10133-5","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,29]]},"assertion":[{"value":"2 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}