{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:56:30Z","timestamp":1757314590653,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723407"},{"type":"electronic","value":"9783031723414"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72341-4_18","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:02:55Z","timestamp":1726491775000},"page":"261-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Details Make a\u00a0Difference: Object State-Sensitive Neurorobotic Task Planning"],"prefix":"10.1007","author":[{"given":"Xiaowen","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xufeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae Hee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Kerzel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"18_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/978-3-030-30487-4_47","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Theoretical Neural Computation","author":"H Beik Mohammadi","year":"2019","unstructured":"Beik Mohammadi, H., Zamani, M.A., Kerzel, M., Wermter, S.: Mixed-reality deep reinforcement learning for a reach-to-grasp task. In: Tetko, I.V., Kurkov\u00e1, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11727, pp. 611\u2013623. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30487-4_47"},{"key":"18_CR2","unstructured":"Brohan, A., et al.: RT-1: robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2023)"},{"key":"18_CR3","unstructured":"Brohan, A., et\u00a0al.: Do as I can, not as I say: grounding language in robotic affordances. In: Conference on Robot Learning (CoRL), pp. 287\u2013318. PMLR (2023)"},{"key":"18_CR4","unstructured":"Chen, A., Sharma, A., Levine, S., Finn, C.: You only live once: single-life reinforcement learning. Adv. Neural Inf. Process. Syst. 35, 14784\u201314797 (2022)"},{"key":"18_CR5","unstructured":"Durante, Z., et\u00a0al.: Agent AI: surveying the horizons of multimodal interaction. arXiv preprint arXiv:2401.03568 (2024)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Gong, R., et\u00a0al.: MindAgent: emergent gaming interaction. arXiv preprint arXiv:2309.09971 (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.200"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Gouidis, F., Patkos, T., Argyros, A., Plexousakis, D.: Detecting object states vs detecting objects: a new dataset and a quantitative experimental study. In: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol.\u00a05, pp. 590\u2013600 (2022)","DOI":"10.5220\/0010898400003124"},{"key":"18_CR8","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: International Conference Don Learning Representations (2022)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Gutman, D., et al.: Evaluating levels of automation with different feedback modes in an assistive robotic table clearing task for eldercare. In: Appl. Ergon. 106, 103859 (2023)","DOI":"10.1016\/j.apergo.2022.103859"},{"key":"18_CR10","unstructured":"Hu, Y., Lin, F., Zhang, T., Yi, L., Gao, Y.: Look before you leap: unveiling the power of GPT-4V in robotic vision-language planning. arXiv preprint arXiv:2311.17842 (2023)"},{"key":"18_CR11","unstructured":"Huang, W., et\u00a0al.: Inner monologue: embodied reasoning through planning with language models. In: Conference on Robot Learning (CoRL), vol.\u00a0205, pp. 1769\u20131782. PMLR (2022)"},{"key":"18_CR12","unstructured":"Jang, E., et al.: BC-Z: zero-shot task generalization with robotic imitation learning. In: Conference on Robot Learning (CoRL), pp. 991\u20131002. PMLR (2022)"},{"key":"18_CR13","unstructured":"Jelodar, A.B., Salekin, M.S., Sun, Y.: Identifying object states in cooking-related images. arXiv preprint arXiv:1805.06956 (2018)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"18_CR15","unstructured":"Kalashnikov, D., et\u00a0al.: Scalable deep reinforcement learning for vision-based robotic manipulation. In: Conference on Robot Learning (CoRL), pp. 651\u2013673. PMLR (2018)"},{"key":"18_CR16","unstructured":"Lin, K., et\u00a0al.: MM-VID: advancing video understanding with GPT-4V (ision). arXiv preprint arXiv:2310.19773 (2023)"},{"key":"18_CR17","unstructured":"Minderer, M., et\u00a0al.: Simple open-vocabulary object detection with vision transformers. arXiv preprint arXiv:2205.06230 (2022)"},{"key":"18_CR18","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"18_CR19","unstructured":"Nyga, D., et al.: Grounding robot plans from natural language instructions with incomplete world knowledge. In: Conference on Robot Learning (CoRL), pp. 714\u2013723. PMLR (2018)"},{"key":"18_CR20","unstructured":"OpenAI: GPT-4V(ision) system card (2023)"},{"issue":"4","key":"18_CR21","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1109\/TCDS.2022.3204452","volume":"15","author":"O \u00d6zdemir","year":"2023","unstructured":"\u00d6zdemir, O., Kerzel, M., Weber, C., Lee, J.H., Wermter, S.: Language model-based paired variational autoencoders for robotic language learning. IEEE Trans. Cogn. Dev. Syst. 15(4), 1812\u20131824 (2023)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"18_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"18_CR23","unstructured":"Rana, K., Haviland, J., Garg, S., Abou-Chakra, J., Reid, I., Suenderhauf, N.: SayPlan: grounding large language models using 3D scene graphs for scalable task planning. In: Conference on Robot Learning (CoRL) (2023)"},{"key":"18_CR24","unstructured":"Ren, A.Z., et\u00a0al.: Robots that ask for help: uncertainty alignment for large language model planners. In: Conference on Robot Learning (CoRL) (2023)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Singh, I., et\u00a0al.: PROGPROMPT: generating situated robot task plans using large language models. In: IEEE International Conference on Robotics and Automation (ICRA), pp. 11523\u201311530. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Song, C.H., Wu, J., Washington, C., Sadler, B.M., Chao, W.L., Su, Y.: LLM-planner: few-shot grounded planning for embodied agents with large language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2998\u20133009 (2023)","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"18_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-031-15931-2_22","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2022","author":"X Sun","year":"2022","unstructured":"Sun, X., Weber, C., Kerzel, M., Weber, T., Li, M., Wermter, S.: Learning visually grounded human-robot dialog in\u00a0a\u00a0hybrid neural architecture. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds.) Artificial Neural Networks and Machine Learning \u2013 ICANN 2022. LNCS, pp. 258\u2013269. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15931-2_22"},{"key":"18_CR29","unstructured":"Valmeekam, K., Marquez, M., Olmo, A., Sreedharan, S., Kambhampati, S.: PlanBench: an extensible benchmark for evaluating large language models on planning and reasoning about change. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Wake, N., Kanehira, A., Sasabuchi, K., Takamatsu, J., Ikeuchi, K.: GPT-4V (ision) for robotics: multimodal task planning from human demonstration. arXiv preprint arXiv:2311.12015 (2023)","DOI":"10.1109\/LRA.2024.3477090"},{"key":"18_CR31","unstructured":"Wang, J., et\u00a0al.: Large language models for robotics: opportunities, challenges, and perspectives. arXiv preprint arXiv:2401.04334 (2024)"},{"key":"18_CR32","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: Large-scale multi-modal pre-trained models: a comprehensive survey. Mach. Intell. Res. 20, 447\u2013482 (2023). https:\/\/doi.org\/10.1007\/s11633-022-1410-8","DOI":"10.1007\/s11633-022-1410-8"},{"key":"18_CR33","unstructured":"Wei, J., et\u00a0al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inf. Process. Syst. 35, 24824\u201324837 (2022)"},{"key":"18_CR34","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","DOI":"10.1007\/b139051","volume-title":"Biomimetic Neural Learning for Intelligent Robots","year":"2005","unstructured":"Wermter, S., Palm, G., Elshaw, M. (eds.): Biomimetic Neural Learning for Intelligent Robots. LNCS (LNAI), vol. 3575. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/b139051"},{"key":"18_CR35","unstructured":"Wu, J., et al.: GRiT: a generative region-to-text transformer for object understanding. arXiv preprint arXiv:2212.00280 (2022)"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Wu, J., et al.: TidyBot: personalized robot assistance with large language models. Auton. Robot. 47, 1087\u20131102 (2023). https:\/\/doi.org\/10.1007\/s10514-023-10139-z","DOI":"10.1007\/s10514-023-10139-z"},{"key":"18_CR37","unstructured":"Yang, Z., et al.: The dawn of LMMs: preliminary explorations with GPT-4V (ision). In: arXiv preprint arXiv:2309.17421 (2023)"},{"key":"18_CR38","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"18_CR39","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, X., Li, M., Weber, C., Hafez, M.B., Wermter, S.: Chat with the Environment: interactive multimodal perception using large language models. In: Conference on Intelligent Robots and Systems (IROS), pp. 3590\u20133596 (2023)","DOI":"10.1109\/IROS55552.2023.10342363"},{"key":"18_CR41","unstructured":"Zhao, Z., Lee, W.S., Hsu, D.: Large language models as commonsense knowledge for large-scale task planning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"18_CR42","unstructured":"Zhou, H., et al.: Language-conditioned learning for robotic manipulation: a survey. arXiv preprint arXiv:2312.10807 (2023)"},{"key":"18_CR43","unstructured":"Zitkovich, B., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning (CoRL), pp. 2165\u20132183. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72341-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T06:15:16Z","timestamp":1732774516000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72341-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723407","9783031723414"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72341-4_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}