{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:12Z","timestamp":1735198812505,"version":"3.32.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020962","name":"ACT-X","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020962","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801903","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"7367-7374","source":"Crossref","is-referenced-by-count":0,"title":["Proposal and Demonstration of a Robot Behavior Planning System Utilizing Video with Open Source Models in Real-World Environments"],"prefix":"10.1109","author":[{"given":"Yuki","family":"Akutsu","sequence":"first","affiliation":[{"name":"Osaka University,Graduate School of Engineering,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Yoshida","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Kato","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuichiro","family":"Sueoka","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"Osuka","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"PaLM-E: An Embodied Multimodal Language Model","year":"2023","author":"Driess","key":"ref1"},{"key":"ref2","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Proceedings of the 5th Conference on Robot Learning","volume":"164","author":"Shridhar"},{"article-title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","year":"2022","author":"Ahn","key":"ref3"},{"article-title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","year":"2023","author":"Brohan","key":"ref4"},{"article-title":"Learning Universal Policies via Text-Guided Video Generation","year":"2023","author":"Du","key":"ref5"},{"article-title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","year":"2021","author":"Skorokhodov","key":"ref6"},{"article-title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","year":"2022","author":"Hong","key":"ref7"},{"article-title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","year":"2022","author":"Yu","key":"ref8"},{"article-title":"You Only Look Once: Unified, Real-Time Object Detection","year":"2015","author":"Redmon","key":"ref9"},{"article-title":"Video generation models as world simulators","year":"2024","author":"Brooks","key":"ref10"},{"article-title":"Imagen Video: High Definition Video Generation with Diffusion Models","year":"2022","author":"Ho","key":"ref11"},{"year":"2023","key":"ref12","article-title":"Gpt-4 technical report"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref13"},{"article-title":"Palm: Scaling language modeling with pathways","year":"2022","author":"Chowdhery","key":"ref14"},{"article-title":"ModelScope Text-to-Video Technical Report","year":"2023","author":"Wang","key":"ref15"},{"article-title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","year":"2022","author":"Singer","key":"ref16"},{"article-title":"LoRA: Low-Rank Adaptation of Large Language Models","year":"2021","author":"Hu","key":"ref17"},{"article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","year":"2016","author":"Coumans","key":"ref18"},{"article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","year":"2023","author":"Li","key":"ref19"},{"article-title":"Decoupled Weight Decay Regularization","year":"2017","author":"Loshchilov","key":"ref20"},{"issue":"15","key":"ref21","article-title":"Sf-yolov5: A lightweight small object detection algorithm based on improved feature fusion mode","volume-title":"Sensors","volume":"22","author":"Liu","year":"2022"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801903.pdf?arnumber=10801903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:58:42Z","timestamp":1735196322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801903","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}