轻量安全控制算法，低算力下仍保安全与最优
Safety and optimality in learning-based control at low computational cost
- 采用子线性复杂度设计，计算开销随数据量增长缓慢
- 在七自由度机械臂上实现安全与最优控制，验证有效性
- 适合嵌入式设备等算力受限场景使用
将机器学习应用于需在真实世界中运行的物理系统时，必须提供安全保证。然而，具备此类保证的方法往往计算开销巨大，难以应用于大规模数据集或算力有限的嵌入式设备。本文提出 CoLSafe，一种计算轻量的安全学习算法，其计算复杂度随数据点数量呈亚线性增长。我们推导了该算法的安全性和最优性保障，并在七自由度机械臂上展示了其有效性。
原文摘要 · Abstract (English)
Applying machine learning methods to physical systems that are supposed to act in the real world requires providing safety guarantees. However, methods that include such guarantees often come at a high computational cost, making them inapplicable to large datasets and embedded devices with low computational power. In this paper, we propose CoLSafe, a computationally lightweight safe learning algorithm whose computational complexity grows sublinearly with the number of data points. We derive both safety and optimality guarantees and showcase the effectiveness of our algorithm on a seven-degrees-of-freedom robot arm.
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。