{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:48:46Z","timestamp":1790833726995,"version":"4.1.0"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Federated learning enables multiple autonomous vehicles (AVs) to collaboratively train machine learning models while preserving data privacy. However, performance degrades significantly under non-independent and identically distributed (non-IID) data conditions commonly encountered in real-world driving scenarios. Existing aggregation methods, particularly Federated Averaging (FedAvg), struggle to effectively handle client update divergence, leading to inefficient communication, unstable convergence, and increased privacy risks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address these challenges, we propose a Dynamic Variance-Aware Federated Tuning (DV-FedTune) framework for object detection in autonomous driving systems using YOLOv12. The proposed framework dynamically adjusts client contributions through a variance-aware aggregation strategy that jointly models update consistency, variance-based diversity, and loss-guided reliability using a round-adaptive weighting mechanism.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Comprehensive experiments were conducted on the KITTI object detection dataset under various non-IID federated learning configurations involving different numbers of clients, local training durations, and communication rounds. The results demonstrate that DV-FedTune consistently outperforms FedAvg, Exponential Moving Average in Federated Learning (EWHFed), and VINOEffiFedAV in terms of communication efficiency, computational cost, and model performance while maintaining stronger privacy preservation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed framework achieves stable aggregation behavior and effective parameter utilization as the federated network scales. These findings indicate that DV-FedTune provides an efficient and privacy-preserving federated learning solution for distributed object detection in autonomous vehicle environments operating under heterogeneous data distributions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frobt.2026.1824246","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:52:14Z","timestamp":1781671934000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic variance-aware federated tuning for efficient autonomous vehicle perception under non-IID settings"],"prefix":"10.3389","volume":"13","author":[{"given":"V.","family":"Dhanavarshini","sequence":"first","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, Tamilnadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sasikumar","family":"Periyasamy","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, Tamilnadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"80637","DOI":"10.1109\/ACCESS.2025.3562128","article-title":"Recent advances in federated learning for connected autonomous vehicles: addressing privacy, performance, and scalability challenges","volume":"13","author":"Ali","year":"2025","journal-title":"IEEE Access"},{"key":"B2","doi-asserted-by":"publisher","first-page":"103295","DOI":"10.1016\/j.rineng.2024.103295","article-title":"A comprehensive analysis of model poisoning attacks in federated learning for autonomous vehicles: a benchmark study","volume":"24","author":"Almutairi","year":"2024","journal-title":"Results Eng."},{"key":"B3","doi-asserted-by":"publisher","first-page":"5857","DOI":"10.1038\/s41598-025-89873-6","article-title":"Jointly exploring client drift and catastrophic forgetting in dynamic learning","volume":"15","author":"Babendererde","year":"2025","journal-title":"Sci. Rep."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1839","DOI":"10.1109\/TVT.2024.3404097","article-title":"Large model-assisted federated learning for object detection of autonomous vehicles in edge","volume":"74","author":"Behera","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"5276","DOI":"10.1109\/TITS.2025.3546088","article-title":"Enhancing federated learning in connected and autonomous vehicles through cost optimization and advanced model selection","volume":"26","author":"Cai","year":"2025","journal-title":"IEEE Trans. Intelligent Transp. Syst."},{"key":"B6","doi-asserted-by":"publisher","first-page":"4567","DOI":"10.1109\/TKDE.2024.3379001","article-title":"Differentially private federated learning on non-iid data: convergence analysis and adaptive optimization","volume":"36","author":"Chen","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"B7","doi-asserted-by":"publisher","first-page":"29988","DOI":"10.1038\/s41598-025-15975-w","article-title":"Pcpe-yolo with a lightweight dynamically reconfigurable backbone for small object detection","volume":"15","author":"Chen","year":"2025","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"103685","DOI":"10.1016\/j.adhoc.2024.103685","article-title":"Flav: federated learning for autonomous vehicle privacy protection","volume":"166","author":"Cui","year":"2025","journal-title":"Ad Hoc Netw."},{"key":"B9","doi-asserted-by":"publisher","first-page":"6263","DOI":"10.1109\/TCE.2024.3524585","article-title":"Explainable federated learning-based secure and transparent object detection model for autonomous vehicles","volume":"71","author":"Devarajan","year":"2025","journal-title":"IEEE Trans. Consumer Electron."},{"key":"B10","doi-asserted-by":"publisher","first-page":"101841","DOI":"10.1016\/j.iot.2025.101841","article-title":"Decentralized proximity-aware clustering for collective self-federated learning","volume":"35","author":"Domini","year":"2026","journal-title":"Internet Things"},{"key":"B11","doi-asserted-by":"publisher","first-page":"20378","DOI":"10.1109\/TITS.2024.3450726","article-title":"A secure personalized federated learning algorithm for autonomous driving","volume":"25","author":"Fu","year":"2024","journal-title":"IEEE Trans. Intelligent Transp. Syst."},{"key":"B12","doi-asserted-by":"publisher","first-page":"21061","DOI":"10.1038\/s41598-025-06831-y","article-title":"An algorithm for road target detection of autonomous vehicles based on improved yolov8","volume":"15","author":"Gao","year":"2025","journal-title":"Sci. Rep."},{"key":"B13","doi-asserted-by":"publisher","first-page":"128049","DOI":"10.1109\/ACCESS.2024.3453068","article-title":"Federated learning for sentiment analysis in presence of non-iid data: sensitivity of deep learning models","volume":"12","author":"Gholamiangonabadi","year":"2024","journal-title":"IEEE Access"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2693","DOI":"10.1109\/TPDS.2025.3611304","article-title":"Fedsr: a semi-decentralized federated learning framework for non-iid data based on incremental subgradient optimization","volume":"36","author":"Huang","year":"2025","journal-title":"IEEE Trans. Parallel Distributed Syst."},{"key":"B15","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1007\/s13177-025-00487-8","article-title":"Optimization of road object detection and localization system using yolov4 model with binocular vision fusion","volume":"23","author":"Jiang","year":"2025","journal-title":"Int. J. Intelligent Transp. Syst. Res."},{"key":"B16","volume-title":"Kitti Dataset on Roboflow Universe","author":"Krauss","year":"2025"},{"key":"B17","doi-asserted-by":"publisher","first-page":"42082","DOI":"10.1109\/ACCESS.2023.3271517","article-title":"Fedlc: optimizing federated learning in Non-iid data via label-wise clustering","volume":"11","author":"Lee","year":"2023","journal-title":"IEEE Access"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2001307","DOI":"10.1007\/s11704-025-40529-8","article-title":"Fedsin: information network representation based on federated self-adaptive learning","volume":"20","author":"Li","year":"","journal-title":"Front. Comput. Sci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"24550","DOI":"10.1038\/s41598-025-02877-0","article-title":"Dsf-yolo for robust multiscale traffic sign detection under adverse weather conditions","volume":"15","author":"Li","year":"","journal-title":"Sci. Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"100175","DOI":"10.1016\/j.commtr.2025.100175","article-title":"Fedav: federated learning for cyberattack vulnerability and resilience of cooperative driving automation","volume":"5","author":"Lin","year":"2025","journal-title":"Commun. Transp. Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"41953","DOI":"10.1038\/s41598-025-25945-x","article-title":"A feature cascade and recursive fusion architecture for traffic sign detection in vehicle perception","volume":"15","author":"Liu","year":"2025","journal-title":"Sci. Rep."},{"key":"B22","doi-asserted-by":"publisher","first-page":"26197","DOI":"10.1038\/s41598-025-09672-x","article-title":"A defense method against multi-label poisoning attacks in federated learning","volume":"15","author":"Ma","year":"2025","journal-title":"Sci. Rep."},{"key":"B23","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1007\/s13177-025-00485-w","article-title":"An attention-based risk-driven approach to object detection for autonomous vehicles","volume":"23","author":"Mohammadi","year":"2025","journal-title":"Int. J. Intelligent Transp. Syst. Res."},{"key":"B24","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/s10586-025-05291-3","article-title":"Fairness-based federated learning in autonomous vehicles with exponential moving average loss weighting","volume":"28","author":"Mollanejad","year":"2025","journal-title":"Clust. Comput."},{"key":"B25","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/OJCS.2023.3262203","article-title":"Flis: clustered federated learning via inference similarity for non-iid data distribution","volume":"4","author":"Morafah","year":"2023","journal-title":"IEEE Open J. Comput. Soc."},{"key":"B26","doi-asserted-by":"publisher","first-page":"148230","DOI":"10.1109\/ACCESS.2024.3474056","article-title":"Enhancing global model performance in federated learning with non-iid data using a data-free generative diffusion model","volume":"12","author":"Najafi","year":"2024","journal-title":"IEEE Access"},{"key":"B27","doi-asserted-by":"publisher","first-page":"38860","DOI":"10.1038\/s41598-025-22672-1","article-title":"Fedeff: efficient federated learning with optimal local epochs for heterogeneous clients","volume":"15","author":"Narmadha","year":"2025","journal-title":"Sci. Rep."},{"key":"B28","doi-asserted-by":"publisher","first-page":"78845","DOI":"10.1109\/ACCESS.2023.3298704","article-title":"Entropy to mitigate Non-iid data problem on federated learning for the edge intelligence environment","volume":"11","author":"Orlandi","year":"2023","journal-title":"IEEE Access"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.1109\/ACCESS.2023.3233983","article-title":"Gefl: gradient encryption-aided privacy preserved federated learning for autonomous vehicles","volume":"11","author":"Parekh","year":"2023","journal-title":"IEEE Access"},{"key":"B30","doi-asserted-by":"publisher","first-page":"23211","DOI":"10.1007\/s11042-024-19409-z","article-title":"Employing cross-domain modelings for robust object detection in dynamic environment of autonomous vehicles","volume":"84","author":"Rawlley","year":"2025","journal-title":"Multimedia Tools Appl."},{"key":"B31","doi-asserted-by":"publisher","first-page":"39142","DOI":"10.1038\/s41598-025-26645-2","article-title":"Analyzing the enhancement of cnn-yolo and transformer based architectures for real-time animal detection in complex ecological environments","volume":"15","author":"Raza","year":"2025","journal-title":"Sci. Rep."},{"key":"B32","doi-asserted-by":"publisher","first-page":"107752","DOI":"10.1016\/j.future.2025.107752","article-title":"Enhancing federated averaging of self-supervised monocular depth estimators for autonomous vehicles with bayesian optimization","volume":"167","author":"Soares","year":"2025","journal-title":"Future Gener. Comput. Syst."},{"key":"B33","volume-title":"Ultralytics github Repository","year":"2024"},{"key":"B34","doi-asserted-by":"publisher","first-page":"107881","DOI":"10.1016\/j.future.2025.107881","article-title":"Reducing weight divergence impact using local learning normalization in federated learning for heterogeneous data distributions","volume":"173","author":"Vieira","year":"2025","journal-title":"Future Gener. Comput. Syst."},{"key":"B35","doi-asserted-by":"publisher","first-page":"103700","DOI":"10.1016\/j.rineng.2024.103700","article-title":"Vino_effifedav: vino with efficient federated learning through selective client updates for real-time autonomous vehicle object detection","volume":"25","author":"Vinoth","year":"2025","journal-title":"Results Eng."},{"key":"B36","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s43684-021-00015-x","article-title":"Decision making framework for autonomous vehicles driving behavior in complex scenarios via hierarchical state machine","volume":"1","author":"Wang","year":"2021","journal-title":"Aut. Intell. Syst."},{"key":"B37","doi-asserted-by":"publisher","first-page":"6147","DOI":"10.1109\/TCE.2025.3551511","article-title":"Federated learning with local differential privacy for autonomous electronic vehicles: enhancing security and performance","volume":"71","author":"Wang","year":"2025","journal-title":"IEEE Trans. Consumer Electron."},{"key":"B38","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1007\/s13177-024-00401-8","article-title":"An adaptive sequencing approach for object detection in autonomous vehicles","volume":"22","author":"Wolfe","year":"2024","journal-title":"Int. J. Intelligent Transp. Syst. Res."},{"key":"B39","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s43684-024-00071-z","article-title":"Human feedback enhanced autonomous intelligent systems: a perspective from intelligent driving","volume":"4","author":"Yuan","year":"2024","journal-title":"Aut. Intell. Syst."},{"key":"B40","article-title":"Fedrav: hierarchically federated region-learning for traffic object classification of autonomous vehicles","author":"Zhai","year":"2024","journal-title":"arXiv Preprint arXiv:2411.13979"},{"key":"B41","doi-asserted-by":"publisher","first-page":"2573","DOI":"10.1007\/s10114-025-2679-7","article-title":"Privacy-preserving federated averaging on heterogeneous data","author":"Zhang","year":"","journal-title":"Acta Math. Sin."},{"key":"B42","doi-asserted-by":"publisher","first-page":"18357","DOI":"10.1038\/s41598-025-02722-4","article-title":"Fedcvg: a two-stage robust federated learning optimization algorithm","volume":"15","author":"Zhang","year":"","journal-title":"Sci. Rep."},{"key":"B43","doi-asserted-by":"publisher","first-page":"6253","DOI":"10.1109\/TCE.2025.3554180","article-title":"Fedvc: virtual clients for federated autonomous driving with imbalanced label distribution","volume":"71","author":"Zhang","year":"","journal-title":"IEEE Trans. Consumer Electron."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1824246\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T04:52:17Z","timestamp":1781671937000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1824246\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":43,"alternative-id":["10.3389\/frobt.2026.1824246"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2026.1824246","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"article-number":"1824246"}}