arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.00352cs.RO

使用数据驱动 Koopman 算子与 Conformal Prediction 的动态环境安全导航

Safe Navigation in Dynamic Environments Using Data-Driven Koopman Operators and Conformal Prediction

Mechanical Engineering and Mechanics Department at Lehigh University(莱维大学机械工程与力学系);Department of Mechanical Engineering at University of California Riverside(加州大学河滨分校机械工程系)

Kaier Liang, Guang Yang, Mingyu Cai, Cristian-Ioan Vasile

AI总结:

本文提出一种动态环境安全导航框架,结合数据驱动 Koopman 算子与 conformal prediction 量化不确定性,并通过约束收紧融入 MPC 以确保安全,经仿真验证有效。

摘要:

我们提出了一种动态环境安全导航的新框架,将 Koopman 算子理论与 conformal prediction 相结合。该方法利用数据驱动的 Koopman 逼近学习非线性动力学,并采用 conformal prediction 量化不确定性,为逼近误差提供统计保证。该不确定性通过约束收紧有效融入 Model Predictive Controller (MPC) 公式中,确保稳健的安全保证。我们实现了分层控制架构,参考生成器为安全导航提供航点。我们在仿真中验证了方法的有效性。

英文摘要:

We propose a novel framework for safe navigation in dynamic environments by integrating Koopman operator theory with conformal prediction. Our approach leverages data-driven Koopman approximation to learn nonlinear dynamics and employs conformal prediction to quantify uncertainty, providing statistical guarantees on approximation errors. This uncertainty is effectively incorporated into a Model Predictive Controller (MPC) formulation through constraint tightening, ensuring robust safety guarantees. We implement a layered control architecture with a reference generator providing waypoints for safe navigation. The effectiveness of our methods is validated in simulation.

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。

↑