用神经算子加速自动驾驶安全分析，通用性强且精度高。
HJRNO: Hamilton-Jacobi Reachability with Neural Operators
- 用神经算子学习值函数映射，实现快速推理
- 在随机障碍物场景中误差低，泛化能力强
- 适合需要实时安全验证的自主系统开发
确保不确定性下的自主系统安全是关键挑战。哈密顿-雅可比可达性（HJR）分析是一种广泛使用的、在最坏扰动下保证安全的方法。本文提出HJRNO，一种基于神经算子的框架，用于高效准确地求解后向可达管（BRT）。通过利用神经算子，HJRNO学习值函数间的映射，实现跨不同障碍物形状和系统配置的快速推理与强泛化能力。我们证明了HJRNO在随机障碍物场景中表现优异，对变化的系统动态具有有效泛化性。这些结果表明，HJRNO为自主系统中可扩展、实时的安全分析提供了有前景的基础模型方法。
原文摘要 · Abstract (English)
Ensuring the safety of autonomous systems under uncertainty is a critical challenge. Hamilton-Jacobi reachability (HJR) analysis is a widely used method for guaranteeing safety under worst-case disturbances. In this work, we propose HJRNO, a neural operator-based framework for solving backward reachable tubes (BRTs) efficiently and accurately. By leveraging neural operators, HJRNO learns a mapping between value functions, enabling fast inference with strong generalization across different obstacle shapes and system configurations. We demonstrate that HJRNO achieves low error on random obstacle scenarios and generalizes effectively across varying system dynamics. These results suggest that HJRNO offers a promising foundation model approach for scalable, real-time safety analysis in autonomous systems.
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。