数据属性自适应控制屏障函数:通过影响分析实现安全认证的训练数据筛选
Data-Attributed Adaptive Control Barrier Functions: Safety-Certified Training Data Curation via Influence Analysis
AI总结:
本文提出数据属性自适应控制屏障函数(DA-CBF),通过影响分析实现安全认证的训练数据筛选,改进了安全损失代理与控制屏障函数约束边界的关联,提升了闭环安全保证。
摘要:
基于控制屏障函数(CBF)参数的学习适应方法为安全自主导航提供了有前景的路径,平衡了保守性与性能。然而,底层安全预测器的准确性最终受限于训练数据质量,且无先前工作正式表征预测误差如何通过自适应管道传播以降低闭环安全保证。我们引入数据属性自适应CBF(DA-CBF),该框架将TracIn基于的数据属性整合到自适应CBF学习中。我们的理论贡献有四点:(i)修正了安全损失代理与CBF约束边界的双侧界限;(ii)安全边界的保护定理表明预测误差导致可量化的边界退化,并通过平滑参数选择器产生不依赖固定轨迹的真实闭环前向不变性保证;(iii)CBF-QP约束扰动界限将预测准确性直接与递归可行性联系起来;(iv)在显式平滑性假设下,为基于影响的数据筛选提供了原则性留一法证明。在DynamicUnicycle2D基准测试中,DA-CBF将预测RMSE减少35.6%,扩大认证安全操作集39%,并在16障碍环境中实现无碰撞导航,而未筛选的基线方法导致3次碰撞。
英文摘要:
Learning-based adaptation of Control Barrier Function (CBF) parameters offers a promising path toward safe autonomous navigation that balances conservatism with performance. Yet the accuracy of the underlying safety predictor is ultimately constrained by training data quality, and no prior work has formally characterized how prediction errors propagate through the adaptive pipeline to degrade closed-loop safety guarantees. We introduce Data-Attributed Adaptive CBF (DA-CBF), a framework that integrates TracIn-based data attribution into adaptive CBF learning. Our theoretical contributions are fourfold: (i) corrected two-sided bounds relating the safety-loss surrogate to the CBF constraint margin; (ii) a safety margin preservation theorem showing that prediction error induces quantifiable margin degradation and, via a smooth parameter selector, yields a genuine closed-loop forward invariance guarantee not conditioned on a fixed trajectory; (iii) a CBF-QP constraint perturbation bound that links prediction accuracy directly to recursive feasibility; and (iv) a principled leave-one-out justification for influence-based data curation under explicit smoothness assumptions. On a DynamicUnicycle2D benchmark, DA-CBF reduces prediction RMSE by 35.6\%, expands the certified safe operating set by 39\%, and achieves collision-free navigation in a 16-obstacle environment where the uncurated baseline incurs 3 collisions.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。