{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:17:50Z","timestamp":1754151470563,"version":"3.41.2"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ur65550.2025.11078036","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T17:42:30Z","timestamp":1752860550000},"page":"199-206","source":"Crossref","is-referenced-by-count":0,"title":["Robocskbench: Benchmarking Embodied Commonsense Capabilities of Large Language Models"],"prefix":"10.1109","author":[{"given":"Jan-Philipp","family":"T\u00f6berg","sequence":"first","affiliation":[{"name":"Cluster of Excellence Cognitive Interaction Technology (CITEC), Bielefeld University,Germany"}]},{"given":"Svenja","family":"Kenneweg","sequence":"additional","affiliation":[{"name":"Cluster of Excellence Cognitive Interaction Technology (CITEC), Bielefeld University,Germany"}]},{"given":"Philipp","family":"Cimiano","sequence":"additional","affiliation":[{"name":"Cluster of Excellence Cognitive Interaction Technology (CITEC), Bielefeld University,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1108\/IR-01-2017-0018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2024.2407136"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00111-7_12"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3615355"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1328934"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_21"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3233\/SW-223084"},{"key":"ref10","first-page":"605","article-title":"Common Sense Data Acquisition for Indoor Mobile Robot","volume-title":"in Proc. of the 19th National Conference on Artifical Intelligence, ser. AAAI\u201904","author":"Gupta","year":"2004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1332"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref13","article-title":"GPT-4 Technical Report","volume-title":"Tech. Rep.","year":"2023"},{"key":"ref14","article-title":"Gemma 2: Improving Open Language Models at a Practical Size","volume-title":"Tech. Rep.","author":"Team","year":"2024"},{"key":"ref15","article-title":"The Llama 3 Herd of Models","volume-title":"Tech. Rep.","author":"Grattafiori","year":"2024"},{"key":"ref16","author":"Yang","year":"2025","journal-title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref18","article-title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref19","article-title":"VALUE: A MultiTask Benchmark for Video-and-Language Understanding Evaluation","volume-title":"Proc. of the 35th Conference on Neural Information Processing Systems (NeurIPS), Virtual Event","author":"Li","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1454"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.382"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5220\/0013046100003838"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.374"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref25","article-title":"LaNMP: A Language-Conditioned Mobile Manipulation Benchmark for Autonomous Robots","volume-title":"Proc. of the Workshop on Lifelong Learning for Home Robots at the Conference on Robot Learning (CoRL), Munich, Germany","author":"Jaafar","year":"2024"},{"key":"ref26","author":"Wang","year":"2024","journal-title":"LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulation"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.133"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref29","article-title":"Creative Robot Tool Use with Large Language Models","volume-title":"Proc. of the Foundation Models for Decision Making Workshop at the 37th Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Xu","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1142\/S1793351X25410041"},{"key":"ref31","article-title":"Exploring Large Language Models as a Source of Common-Sense Knowledge for Robots","volume-title":"Proc. of the 22nd International Semantic Web Conference (ISWC Posters and Demos), Athens, Greece","author":"Ocker","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.conll-1.27"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/429816"},{"key":"ref34","article-title":"Physical Reasoning and Object Planning for Household Embodied Agents","author":"Agrawal","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77385-4_41"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3206505"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222906"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2927476"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref42","volume-title":"Extraction of Prototypical Household Object Locations from the CommonSense Knowledge Graph (CSKG)","author":"Toraman","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref44","author":"Kolve","year":"2017","journal-title":"AI2THOR: An Interactive 3D Environment for Visual AI"},{"key":"ref45","first-page":"6","article-title":"Narrative Objects","volume-title":"Proc. of the Workshop on Semantic Techniques for Narrative-Based Understanding at the 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence (IJCAI-ECAI), Vienna, Austria","author":"Pomarlan","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.476084"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CCECE.2019.8861780"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1177\/1094428120947794"},{"key":"ref51","article-title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","volume-title":"Proc. of the 10th International Conference on Learning Representations (ICLR)","author":"Gu","year":"2022"}],"event":{"name":"2025 22nd International Conference on Ubiquitous Robots (UR)","location":"College Station, TX, USA","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,2]]}},"container-title":["2025 22nd International Conference on Ubiquitous Robots (UR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11078013\/11077977\/11078036.pdf?arnumber=11078036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T04:51:06Z","timestamp":1752900666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11078036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/ur65550.2025.11078036","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}