{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:11:35Z","timestamp":1757614295798,"version":"3.44.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,1]]},"DOI":"10.1109\/rcar65431.2025.11139480","type":"proceedings-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T18:16:38Z","timestamp":1757009798000},"page":"311-316","source":"Crossref","is-referenced-by-count":0,"title":["RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Xiaojian","family":"Li","sequence":"first","affiliation":[{"name":"Hefei University of Technology,School of Management,Hefei,China"}]},{"given":"Sheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Electrical Engineering and Automation,Hefei,China"}]},{"given":"Chao","family":"Chen","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Management,Hefei,China"}]},{"given":"Hailong","family":"Wei","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Management,Hefei,China"}]},{"given":"Yudong","family":"Shi","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Management,Hefei,China"}]},{"given":"Hangjie","family":"Mo","sequence":"additional","affiliation":[{"name":"Hefei University of Technology,School of Management,Hefei,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","year":"2023","author":"Awadalla","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref5"},{"article-title":"Mobile ALOHA: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","year":"2024","author":"Fu","key":"ref6"},{"article-title":"Vision-language foundation models as effective robot imitators","year":"2023","author":"Li","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref9"},{"key":"ref10","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conf. Robot Learn","author":"Jang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.047"},{"article-title":"VIMA: General robot manipulation with multimodal prompts","year":"2022","author":"Jiang","key":"ref12"},{"issue":"1","key":"ref13","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2029"},{"key":"ref17","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learning","author":"Tan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Auto-encoding variational Bayes","year":"2013","author":"Kingma","key":"ref20"},{"article-title":"PaLM-E: An embodied multimodal language model","year":"2023","author":"Driess","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01368"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conf. Robot Learning","author":"Jang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"year":"2023","key":"ref26","article-title":"Introducing MPT-7B: A new standard for open-source, commercially usable LLMs"},{"year":"2023","key":"ref27","article-title":"GPT-4 technical report"}],"event":{"name":"2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2025,6,1]]},"location":"Toyama, Japan","end":{"date-parts":[[2025,6,6]]}},"container-title":["2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11139128\/11139096\/11139480.pdf?arnumber=11139480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T05:50:52Z","timestamp":1757051452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11139480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/rcar65431.2025.11139480","relation":{},"subject":[],"published":{"date-parts":[[2025,6,1]]}}}