用近似高斯过程实现实时在线学习，提升控制精度
Real-Time Online Learning for Model Predictive Control using a Spatio-Temporal Gaussian Process Approximation
- 构建时空高斯过程近似模型，实现恒定计算开销的在线学习
- 在微型竞速车实验中，实时学习动态并提升控制性能
- 适合需要实时自适应的复杂控制系统研究者
基于学习的模型预测控制（MPC）可通过修正模型误差来提升控制性能，实现比传统MPC更精确的状态轨迹预测。常见方法是将未知残差动力学建模为高斯过程（GP），该方法利用数据并提供相关不确定性估计。然而，在线学习的高计算成本严重制约了实时GP-MPC应用。本文提出一种高效的近似时空高斯过程模型实现，可在恒定计算复杂度下实现在线学习。该方法专为GP-MPC优化，能够在实时中学习更准确的系统动态，即使面对时变系统也能提升控制性能。通过仿真和硬件实验，在自主微型竞速车应用中验证了该方法的有效性。
原文摘要 · Abstract (English)
Learning-based model predictive control (MPC) can enhance control performance by correcting for model inaccuracies, enabling more precise state trajectory predictions than traditional MPC. A common approach is to model unknown residual dynamics as a Gaussian process (GP), which leverages data and also provides an estimate of the associated uncertainty. However, the high computational cost of online learning poses a major challenge for real-time GP-MPC applications. This work presents an efficient implementation of an approximate spatio-temporal GP model, offering online learning at constant computational complexity. It is optimized for GP-MPC, where it enables improved control performance by learning more accurate system dynamics online in real-time, even for time-varying systems. The performance of the proposed method is demonstrated by simulations and hardware experiments in the exemplary application of autonomous miniature racing.
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。