{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T11:05:03Z","timestamp":1789383903648,"version":"build-2803163510"},"reference-count":28,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T00:00:00Z","timestamp":1789257600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Romanian Hub for Artificial Intelligence-HRIAmdm","award":["351416"],"award-info":[{"award-number":["351416"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Cooperative perception through vehicle-to-vehicle (V2V) communication can resolve occlusions that single-vehicle systems cannot overcome, yet existing frameworks rely on simulated environments and expensive multi-sensor platforms. This paper presents CoSafe, a cooperative perception and reasoning framework built on real-world data acquired from dashboard cameras with integrated GPS. CoSafe extends a previously validated image-based positioning algorithm by adding YOLOv8 object detection, cooperative state fusion, Chain-of-Thought reasoning using a Large Language Model, and a deterministic rule-based safety validation layer. The core contribution is a spatial\u2013temporal vehicle matching framework that associates frames captured from overlapping geographic locations at different timestamps, enabling cooperative hazard reasoning across asynchronous and partially observable vehicle streams. This paper also introduces the Cooperation Gain metric to quantify the proportion of cases in which hazard detection depends on inter-vehicle information sharing. On a real-world occluded-pedestrian scenario, cooperation provides an advance warning of at least 1.73 s before the following vehicle\u2019s own detector registers the pedestrian, with a Cooperation Gain of 0.533 measured against manual human annotation. An ablation across single-vehicle, rule-only, and LLM-only configurations isolates the contribution of each component, and a negative-scenario test yields zero false alarms in normal traffic.<\/jats:p>","DOI":"10.3390\/s26185797","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:19:41Z","timestamp":1789381181000},"page":"5797","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CoSafe: A Cooperative V2V Perception Framework with LLM Reasoning for Hazard Detection on Real Dashcam Data"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1820-8000","authenticated-orcid":false,"given":"Iosif-Alin","family":"Beti","sequence":"first","affiliation":[{"name":"Department of Automatic Control and Applied Informatics, Gheorghe Asachi Technical University of Iasi, 700050 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Paul-Corneliu","family":"Herghelegiu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Gheorghe Asachi Technical University of Iasi, 700050 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4026-2852","authenticated-orcid":false,"given":"Constantin-Florin","family":"Caruntu","sequence":"additional","affiliation":[{"name":"Department of Automatic Control and Applied Informatics, Gheorghe Asachi Technical University of Iasi, 700050 Iasi, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2023). Global Status Report on Road Safety 2023, World Health Organization. Technical Report."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/COMST.2015.2410831","article-title":"A Survey on Platoon-Based Vehicular Cyber-Physical Systems","volume":"18","author":"Jia","year":"2016","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s44267-025-00095-w","article-title":"DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving","volume":"3","author":"Cui","year":"2025","journal-title":"Vis. Intell."},{"key":"ref_4","unstructured":"Mao, J., Ye, J., Qian, Y., Pavone, M., and Wang, Y. (2024, January 7\u20139). A Language Agent for Autonomous Driving. Proceedings of the First Conference on Language Modeling, Philadelphia, PA, USA. Available online: https:\/\/openreview.net\/forum?id=UPE6WYE8vg."},{"key":"ref_5","unstructured":"Sima, C., Renz, K., Chitta, K., Chen, L., Zhang, H., Xie, C., Bei\u00dfwenger, J., Luo, P., Geiger, A., and Li, H. (October, January 29). DriveLM: Driving with Graph Visual Question Answering. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_6","unstructured":"Wen, L., Fu, D., Li, X., Cai, X., Ma, T., Cai, P., Dou, M., Shi, B., He, L., and Qiao, Y. (2024, January 7\u201311). DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models. Proceedings of the International Conference on Learning Representations, Vienna, Austria. Available online: https:\/\/openreview.net\/forum?id=OqTMUPuLuC."},{"key":"ref_7","unstructured":"Nie, M., Peng, R., Wang, C., Cai, X., Han, J., Xu, H., and Zhang, L. (October, January 29). Reason2Drive: Towards Interpretable and Chain-Based Reasoning for Autonomous Driving. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, J., Xu, C., Hang, P., and Sun, J. (2025). LeAD: The LLM Enhanced Planning System Converged with End-to-End Autonomous Driving. arXiv.","DOI":"10.1109\/ITSC60802.2025.11423844"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Nazar, A.M., Selim, M.Y., Gaffar, A., and Qiao, D. (2025). Situational Perception in Distracted Driving: An Agentic Multi-Modal LLM Framework. Front. Artif. Intell., 8.","DOI":"10.3389\/frai.2025.1669937"},{"key":"ref_10","unstructured":"Wang, Y., Luo, W., Bai, J., Cao, Y., Che, T., Chen, K., Chen, Y., Diamond, J., Ding, Y., and Ding, W. (2025). Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail. arXiv."},{"key":"ref_11","unstructured":"Wang, Y., Jiao, R., Zhan, S.S., Lang, C., Huang, C., Wang, Z., Yang, Z., and Zhu, Q. (2024, January 11). Empowering Autonomous Driving with Large Language Models: A Safety Perspective. Proceedings of the LLM Agent Workshop at the International Conference on Learning Representations (ICLR), Vienna, Austria. Available online: https:\/\/openreview.net\/pdf\/4f19e21a6f2e0cc1a4f40c22877f679993782c48.pdf."},{"key":"ref_12","unstructured":"Hu, Y., Fang, S., Lei, Z., Zhong, Y., and Chen, S. (2022). Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Neural Information Processing Systems Foundation. Available online: https:\/\/papers.neurips.cc\/paper_files\/paper\/2022\/file\/1f5c5cd01b864d53cc5fa0a3472e152e-Paper-Conference.pdf."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Xu, R., Xiang, H., Tu, Z., Xia, X., Yang, M.H., and Ma, J. (2022, January 23\u201327). V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19842-7_7"},{"key":"ref_14","unstructured":"Chiu, H.K., Hachiuma, R., Wang, C.Y., Smith, S.F., Wang, Y.C.F., and Chen, M.H. (2026). V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), IEEE."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Xu, R., Xia, X., Li, J., Li, H., Zhang, S., Tu, Z., Meng, Z., Xiang, H., Dong, X., and Song, R. (2023, January 17\u201324). V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01318"},{"key":"ref_16","unstructured":"Chiu, H.K., Hachiuma, R., Wang, C.Y., Wang, Y.C.F., Chen, M.H., and Smith, S.F. (2026, January 1\u20135). V2V-GoT: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models and Graph-of-Thoughts. Proceedings of the IEEE International Conference on Robotics and Automation, Vienna, Austria. Available online: https:\/\/research.nvidia.com\/labs\/twn\/publication\/icra_2026_v2vgot\/."},{"key":"ref_17","unstructured":"Cui, J., Tang, C., Holtz, J., Nguyen, J., Allievi, A.G., Qiu, H., and Stone, P. (2025). Towards Natural Language Communication for Cooperative Autonomous Driving via Self-Play. arXiv."},{"key":"ref_18","unstructured":"Hu, S., Fang, Z., Fang, Z., Deng, Y., Chen, X., and Fang, Y. (2024). AgentsCoDriver: Large Language Model Empowered Collaborative Driving with Lifelong Learning. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Beti, I.A., Herghelegiu, P.C., and Caruntu, C.F. (2024). Architectural Framework to Enhance Image-Based Vehicle Positioning for Advanced Functionalities. Information, 15.","DOI":"10.3390\/info15060323"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., and Bradski, G. (2011, January 6\u201313). ORB: An Efficient Alternative to SIFT or SURF. Proceedings of the International Conference on Computer Vision (ICCV), Barcelona, Spain.","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/j.patrec.2020.04.005","article-title":"BEBLID: Boosted Efficient Binary Local Image Descriptor","volume":"133","author":"Sfeir","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"ref_22","unstructured":"Lowe, D.G. (1999, January 20\u201327). Object Recognition from Local Scale-Invariant Features. Proceedings of the 7th IEEE International Conference on Computer Vision, Kerkyra, Greece."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Beti, I.A., Herghelegiu, P.C., Amarandei, C.M., and Caruntu, C.F. (2024, January 10\u201312). Cloud Architectural Design for Image-Based Vehicle Positioning in Traffic Management. Proceedings of the 28th International Conference on System Theory, Control and Computing (ICSTCC), Sinaia, Romania.","DOI":"10.1109\/ICSTCC62912.2024.10744705"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Beti, I.A., Herghelegiu, P.C., and Caruntu, C.F. (2025, January 1\u20133). Enhanced Frame-Matching Algorithm for Image-Based Vehicle Positioning Using Segmented Regions of Interest. Proceedings of the 2025 International Conference on Control, Automation and Diagnosis, Barcelona, Spain.","DOI":"10.1109\/ICCAD64771.2025.11099109"},{"key":"ref_25","first-page":"12077","article-title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","volume":"Volume 34","author":"Ranzato","year":"2021","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., and Schiele, B. (2016, January 27\u201330). The Cityscapes Dataset for Semantic Urban Scene Understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref_27","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2026, September 09). Ultralytics YOLO, Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Popescu, F., and Stanescu, D. (2026). AICEBERG: A Novel Agentic AI Framework for Autonomous Radio Monitoring, Compliance and Governance Based on LLM, MCP, and SCPI in Smart Cities. Smart Cities, 9.","DOI":"10.3390\/smartcities9050073"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5797\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:21:55Z","timestamp":1789381315000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,13]]},"references-count":28,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26185797"],"URL":"https:\/\/doi.org\/10.3390\/s26185797","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,13]]}}}