用概率保证方法生成更安全、更宽松的神经控制屏障函数。
CP-NCBF: A Conformal Prediction-based Approach to Synthesize Verified Neural Control Barrier Functions
- 基于分拆共形预测，实现可验证的神经控制屏障函数生成。
- 在自动驾驶避障和飞行器地理围栏中，安全区域更大且保守性更低。
- 无需限制神经网络的Lipschitz性质，提升可扩展性和实用性。
控制屏障函数（CBFs）是设计安全关键控制器的有效方法，但针对任意非线性动态系统构建仍具挑战。近期研究尝试通过学习方法（如神经CBFs，NCBFs）解决该问题，但难以确保其有效性，因存在学习误差。本文提出一种新框架——基于共形预测的CP-NCBF，利用分拆共形预测，在用户定义的误差率下生成具有概率保证的正式验证神经CBFs。与现有方法强制要求神经CBF满足Lipschitz约束不同，本方法无需此类限制，具备样本高效、可扩展性强的优势，且生成的安全集更宽松。通过自动驾驶避障与空中飞行器地理围栏的案例验证，结果表明其能生成比传统方法更大、更少保守的安全区域。
原文摘要 · Abstract (English)
Control Barrier Functions (CBFs) are a practical approach for designing safety-critical controllers, but constructing them for arbitrary nonlinear dynamical systems remains a challenge. Recent efforts have explored learning-based methods, such as neural CBFs (NCBFs), to address this issue. However, ensuring the validity of NCBFs is difficult due to potential learning errors. In this letter, we propose a novel framework that leverages split-conformal prediction to generate formally verified neural CBFs with probabilistic guarantees based on a user-defined error rate, referred to as CP-NCBF. Unlike existing methods that impose Lipschitz constraints on neural CBF-leading to scalability limitations and overly conservative safe sets--our approach is sample-efficient, scalable, and results in less restrictive safety regions. We validate our framework through case studies on obstacle avoidance in autonomous driving and geo-fencing of aerial vehicles, demonstrating its ability to generate larger and less conservative safe sets compared to conventional techniques.
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。