用物理约束神经网络提升无人机分类准确率与训练效率
Object Identification Under Known Dynamics: A PIRNN Approach for UAV Classification
- 将物理规律嵌入残差网络，实现状态与状态导数联合预测
- 在四旋翼、固定翼、直升机上达到高分类精度，训练更快
- 适合已知动力学模型的无人机系统识别任务
本文研究已知动力学下的无人飞行器目标识别问题，提出一种物理信息残差神经网络框架，结合学习与分类。该方法利用物理信息学习进行状态映射与状态导数预测，通过softmax层实现多类别置信度估计。以四旋翼、固定翼和直升机为案例研究，结果表明分类准确率高且训练时间显著减少，为动力学明确的领域提供了有前景的系统辨识解决方案。
原文摘要 · Abstract (English)
This work addresses object identification under known dynamics in unmanned aerial vehicle applications, where learning and classification are combined through a physics-informed residual neural network. The proposed framework leverages physics-informed learning for state mapping and state-derivative prediction, while a softmax layer enables multi-class confidence estimation. Quadcopter, fixed-wing, and helicopter aerial vehicles are considered as case studies. The results demonstrate high classification accuracy with reduced training time, offering a promising solution for system identification problems in domains where the underlying dynamics are well understood.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。