arXiv：cs.LG（机器学习，全量分类）· Kaizhen Li, Xi Zhou, Zihao Wang, Dan Zhang, Jianjian Liu, Xiaowei Li·· 15 小时前AI 评分27
基于多任务学习与自适应中心化的无人水面艇可靠性感知短期横摇预测
Reliability-aware short-term roll prediction for unmanned surface vehicles via multi-task learning and adaptive centralization
AI 导读
该研究提出一种可靠性感知预测范式，将置信度评估融入预测流程，用于无人水面艇（USV）的短期横摇预测。架构采用多任务学习结构，共享特征提取主干分别连接回归头与量化头，在输出横摇预测值的同时给出置信度评分，并引入自适应中心化策略提升不同工况下的泛化能力。真实海况数据集实验表明，该方法能有效量化预测可靠性并保持更优泛化性能。
正文
Abstract:Reliable roll prediction of unmanned surface vehicles (USVs) is essential for ensuring navi?gational safety and enhancing autonomous decision-making. While existing studies primarily focus on improving prediction accuracy, the quantification of prediction reliability remains insufficiently addressed. To bridge this gap, this paper proposes a reliability-aware prediction paradigm that integrates confidence assessment into the predictive pipeline. The architecture utilizes a multi-task learning structure where a shared feature extraction backbone feeds into dual heads: a regression head for precise roll prediction and a quantification head for confidence scoring. This configuration provides accurate prediction and corresponding confidence for risk?sensitive downstream tasks. In addition, an adaptive centralization strategy tailored for short?term real-time roll prediction is introduced to improve model generalization under varying operational conditions. Experiments conducted on a real-sea dataset demonstrate that the proposed method effectively quantifies the reliability of prediction results and maintains superior generalization under varying conditions, offering significant potential for practical engineering applications.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00996 [cs.LG] |
| (or arXiv:2610.00996v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00996 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kaizhen Li [view email]
[v1]
Thu, 1 Oct 2026 03:33:22 UTC (21,706 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org