检测护理机器人神经网络模仿策略中的不安全行为
Detecting Unsafe Behavior in Neural Network Imitation Policies for Caregiving Robotics
AI总结：
本文研究护理机器人模仿学习中的不安全行为检测，针对扩散策略提出集成预测器与改进归一化流算法以解决“Policy Stopping”问题，在辅助机器人基准上优于 VAE 和 Tran-AD。
摘要：
本文探讨了模仿学习在护理机器人中的应用，旨在应对老年人和残疾人护理中日益增长的自动化辅助需求。利用深度学习与控制算法的进展，本研究聚焦于使用离线演示训练神经网络策略。研究解决的一个关键挑战是“Policy Stopping”问题，这对于提升基于模仿学习的策略（尤其是扩散策略）的安全性至关重要。提出的创新方案包括集成预测器以及对基于归一化流的算法的改进，用于早期异常检测。与 VAE 和 Tran-AD 等异常检测方法进行的对比评估表明，所提方法在辅助机器人基准上表现更优。论文最后讨论了将安全模型融入策略训练的进一步研究，这对于在护理机器人中可靠部署神经网络策略至关重要。
英文摘要：
In this paper, the application of imitation learning in caregiving robotics is explored, aiming at addressing the increasing demand for automated assistance in caring for the elderly and disabled. Leveraging advancements in deep learning and control algorithms, the study focuses on training neural network policies using offline demonstrations. A key challenge addressed is the "Policy Stopping" problem, crucial for enhancing safety in imitation learning-based policies, particularly diffusion policies. Novel solutions proposed include ensemble predictors and adaptations of the normalizing flow-based algorithm for early anomaly detection. Comparative evaluations against anomaly detection methods like VAE and Tran-AD demonstrate superior performance on assistive robotics benchmarks. The paper concludes by discussing the further research in integrating safety models into policy training, crucial for the reliable deployment of neural network policies in caregiving robotics.
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。
