The emerging integration of robots into everyday life brings several major challenges. Compared to classical industrial applications, more flexibility is needed in combination with real-time reactivity. Learning-based methods can train powerful policies based on demonstrated trajectories, such that the robot generalizes a task to similar situations. However, these black-box models lack interpretability and rigorous safety guarantees. Optimization-based methods provide these guarantees but lack the required flexibility and generalization capabilities. This work proposes SafeFlowMPC, a combination of flow matching and online optimization to combine the strengths of learning and optimization. This method guarantees safety at all times and is designed to meet the demands of real-time execution by using a suboptimal model-predictive control formulation. SafeFlowMPC achieves strong performance in three real-world experiments on a KUKA 7-DoF manipulator, namely two grasping experiment and a dynamic human-robot object handover experiment. A video of the experiments is available at http://www.acin.tuwien.ac.at/42d6. The code is available at https://github.com/TU-Wien-ACIN-CDS/SafeFlowMPC.

翻译：机器人日益融入日常生活带来了若干重大挑战。与传统的工业应用相比，需要更高的灵活性并结合实时响应能力。基于学习的方法能够基于示教轨迹训练出强大的策略，使机器人能够将任务推广到类似情境。然而，这些黑盒模型缺乏可解释性和严格的安全性保证。基于优化的方法提供了这些保证，但缺乏所需的灵活性和泛化能力。本研究提出SafeFlowMPC，一种结合流匹配与在线优化的方法，以融合学习与优化的优势。该方法通过采用次优的模型预测控制框架，始终保证安全性，并旨在满足实时执行的需求。SafeFlowMPC在KUKA七自由度机械臂上的三个真实世界实验中（即两个抓取实验和一个动态人机物体交接实验）均取得了优异性能。实验视频可见于 http://www.acin.tuwien.ac.at/42d6。代码发布于 https://github.com/TU-Wien-ACIN-CDS/SafeFlowMPC。