{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:57:50Z","timestamp":1771516670252,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007787","name":"National Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246686","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"17672-17679","source":"Crossref","is-referenced-by-count":1,"title":["Free-form language-based robotic reasoning and grasping"],"prefix":"10.1109","author":[{"given":"Runyu","family":"Jiao","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alice","family":"Fasoli","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Giuliari","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Bortolon","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Povoli","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guofeng","family":"Mei","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Poiesi","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 Technical Report","year":"2024"},{"key":"ref2","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"CoRL"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161534"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10145-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3524910"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3460416"},{"key":"ref9","article-title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","author":"Huang","year":"2024","journal-title":"CoRL"},{"key":"ref10","article-title":"MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting","volume-title":"RSS","author":"Liu"},{"key":"ref11","article-title":"ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter","author":"Qian","year":"2024","journal-title":"CoRL"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3328964"},{"key":"ref14","article-title":"Robopoint: A vision-language model for spatial affordance prediction in robotics","author":"Yuan","year":"2024","journal-title":"CoRL"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref16","article-title":"GLOVER: Generalizable open-vocabulary affordance reasoning for task-oriented grasping","author":"Ma","year":"2024"},{"key":"ref17","article-title":"SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning","author":"Liu","year":"2025"},{"key":"ref18","article-title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","author":"Ma","year":"2024","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8625071"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342196"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142401"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3524910"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981960"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802508"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3434610"},{"key":"ref26","article-title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models","author":"Deitke","year":"2024"},{"key":"ref27","article-title":"Language Segment-Anything","author":"Medeiros","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00114"},{"key":"ref30","article-title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","author":"Yang","year":"2023"},{"key":"ref31","article-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","author":"Wei","year":"2023","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02747"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref36","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246686.pdf?arnumber=11246686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:55Z","timestamp":1766061415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246686","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}