让无人船在感知不确定下更安全航行，自动调节信任度并遵守航海规则。
Credibility-Aware Learning and Control for Safe USV Navigation under Perception Uncertainty
- 用感知误差动态调整信任权重，防止错误信息误导决策。
- 仿真中对10艘未训练目标船避碰成功率达82.0%，且符合国际海事规则。
- 适合做海上无人系统安全控制的研究者与工程师参考。
在动态海况下，无人水面艇（USV）遵循《国际海上避碰规则》（COLREGs）进行安全导航仍具挑战性，尤其当感知不确定性未被准确校准时。状态估计误差会导致不可靠的信念状态，误导价值学习；基于离散规则的逻辑则可能引发突兀的动作修正。为此，本文将可信度加权价值学习（CWVL）与协方差及恢复感知控制屏障函数二次规划（CoReCBF-QP）结合。CWVL通过滤波器估计协方差与实际误差统计之间的差异，生成动态信任因子，调节评论家的异方差损失，抑制对校准错误观测的过拟合。CoReCBF根据不确定性扩展碰撞几何，并引入制动与转向恢复项，形成双曲型安全边界，保证可行规避速度并提供QP安全约束。目标函数中嵌入连续的COLREGs感知参考，在规则14迎面相遇和规则15让路交叉场景中促进右舷避让。仿真显示，该方法在超过训练范围的十艘目标船场景中，实现82.0%的避碰成功率，显著提升鲁棒性与规则合规性。
原文摘要 · Abstract (English)
Safe navigation for Unmanned Surface Vehicles (USVs) under the International Regulations for Preventing Collisions at Sea (COLREGs) remains challenging in dynamic maritime environments, especially when perception uncertainty is miscalibrated. Errors in state estimation can produce unreliable belief states that mislead value learning, while logic based on discrete traffic rules can cause abrupt action corrections. To address these challenges, we integrate Credibility-Weighted Value Learning (CWVL) with Covariance- and Recovery-Aware Control Barrier Function Quadratic Programming (CoReCBF-QP). CWVL derives a dynamic trust factor from the discrepancy between the covariance estimated by the filter and empirical error statistics. This factor modulates the critic's heteroscedastic loss and limits overfitting to miscalibrated observations. CoReCBF expands the collision geometry according to uncertainty and incorporates terms for braking and turning recovery. The resulting hyperbolic safety boundary preserves feasible avoidance velocities and supplies the QP safety constraint. A continuous COLREGs-aware reference in the objective promotes starboard maneuvers in Rule 14 head-on and Rule 15 give-way crossing encounters. Simulations show improved robustness in collision avoidance and COLREGs event compliance, achieving an 82.0\% success rate with ten target ships beyond the training range.
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。