Paper Reading AI Learner

DroneFL: Federated Learning for Multi-UAV Visual Target Tracking

2025-09-25 20:09:15
Xiaofan Yu, Yuwei Wu, Katherine Mao, Ye Tian, Vijay Kumar, Tajana Rosing

Abstract

Multi-robot target tracking is a fundamental problem that requires coordinated monitoring of dynamic entities in applications such as precision agriculture, environmental monitoring, disaster response, and security surveillance. While Federated Learning (FL) has the potential to enhance learning across multiple robots without centralized data aggregation, its use in multi-Unmanned Aerial Vehicle (UAV) target tracking remains largely underexplored. Key challenges include limited onboard computational resources, significant data heterogeneity in FL due to varying targets and the fields of view, and the need for tight coupling between trajectory prediction and multi-robot planning. In this paper, we introduce DroneFL, the first federated learning framework specifically designed for efficient multi-UAV target tracking. We design a lightweight local model to predict target trajectories from sensor inputs, using a frozen YOLO backbone and a shallow transformer for efficient onboard training. The updated models are periodically aggregated in the cloud for global knowledge sharing. To alleviate the data heterogeneity that hinders FL convergence, DroneFL introduces a position-invariant model architecture with altitude-based adaptive instance normalization. Finally, we fuse predictions from multiple UAVs in the cloud and generate optimal trajectories that balance target prediction accuracy and overall tracking performance. Our results show that DroneFL reduces prediction error by 6%-83% and tracking distance by 0.4%-4.6% compared to a distributed non-FL framework. In terms of efficiency, DroneFL runs in real time on a Raspberry Pi 5 and has on average just 1.56 KBps data rate to the cloud.

Abstract (translated)

多机器人目标跟踪是需要协调监控动态实体的基本问题,这在精准农业、环境监测、灾害响应和安全监控等应用中至关重要。虽然联邦学习(FL)具有通过分散式而非集中化的数据聚合来增强多个机器人之间学习的潜力,但在多无人机目标跟踪中的应用仍鲜有探索。这一领域面临的挑战包括有限的机载计算资源、由于不同目标及视野范围导致的数据异质性显著增加,以及轨迹预测与多机器人规划间紧密耦合的需求。本文中,我们提出了DroneFL,这是首个专为高效多无人机目标跟踪设计的联邦学习框架。 为了在每架无人机上进行高效的本地模型训练,我们设计了一种轻量级的局部模型,用于从传感器输入中预测目标轨迹。该模型采用冻结的YOLO主干和浅层Transformer结构,并通过基于高度适应的实例归一化来缓解位置不变性带来的数据异质性问题。 在云端定期聚合更新后的模型以实现全局知识共享后,DroneFL会在云服务器上融合来自多架无人机的预测结果,并生成综合了目标预测精度与整体跟踪性能的最佳轨迹。实验结果显示,相较于分布式的非联邦学习框架,DroneFL能够将预测误差降低6%-83%,并将追踪距离减少0.4%-4.6%。 此外,在效率方面,DroneFL可以在Raspberry Pi 5上实时运行,并且平均数据传输速率仅为1.56KBps。

URL

https://arxiv.org/abs/2509.21523

PDF

https://arxiv.org/pdf/2509.21523.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot